fix(skills): harden slash skill activation across chat channels (#3466)

* support slash skill activation

* format slash skill activation

* Preserve slash skill activation with uploads

* Address slash skill review feedback

* Address slash skill follow-up review

* Fix lazy slash skill storage resolution

* Keep slash skill activation out of system prompt

* Address slash skill review issues

* fix: harden slash skill command handling

* feat(frontend): add slash skill autocomplete

* fix: address slash skill review feedback

* fix: preserve slash skill text for IM uploads

README.md

@@ -585,6 +585,8 @@ A standard Agent Skill is a structured capability module — a Markdown file tha
 
 Skills are loaded progressively — only when the task needs them, not all at once. This keeps the context window lean and makes DeerFlow work well even with token-sensitive models.
 
+Users can explicitly activate an enabled skill for a single turn by starting the request with `/skill-name`, for example `/data-analysis analyze uploads/foo.csv`. DeerFlow loads that skill's `SKILL.md` as hidden current-turn context while leaving the base prompt limited to skill metadata. Slash activation respects disabled skills, custom-agent skill whitelists, and existing channel commands such as `/new` and `/help`.
+
 When you install `.skill` archives through the Gateway, DeerFlow accepts standard optional frontmatter metadata such as `version`, `author`, and `compatibility` instead of rejecting otherwise valid external skills.
 
 Tools follow the same philosophy. DeerFlow comes with a core toolset — web search, web fetch, file operations, bash execution — and supports custom tools via MCP servers and Python functions. Swap anything. Add anything.

backend/CLAUDE.md

@@ -202,16 +202,17 @@ Lead-agent middlewares are assembled in strict append order across `packages/har
 6. **GuardrailMiddleware** - Pre-tool-call authorization via pluggable `GuardrailProvider` protocol (optional, if `guardrails.enabled` in config). Evaluates each tool call and returns error ToolMessage on deny. Three provider options: built-in `AllowlistProvider` (zero deps), OAP policy providers (e.g. `aport-agent-guardrails`), or custom providers. See [docs/GUARDRAILS.md](docs/GUARDRAILS.md) for setup, usage, and how to implement a provider.
 7. **SandboxAuditMiddleware** - Audits sandboxed shell/file operations for security logging before tool execution continues
 8. **ToolErrorHandlingMiddleware** - Converts tool exceptions into error `ToolMessage`s so the run can continue instead of aborting
-9. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
+9. **SkillActivationMiddleware** - Detects strict `/skill-name task` syntax on the latest real user message, resolves only enabled and runtime-allowed skills, reads `SKILL.md` from trusted skill storage, injects the skill body as hidden current-turn model context, and records a `middleware:skill_activation` audit event with skill name, category, path, and content hash
-10. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)
+10. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
-11. **TokenUsageMiddleware** - Records token usage metrics when token tracking is enabled (optional); subagent usage is cached by `tool_call_id` only while token usage is enabled and merged back into the dispatching AIMessage by message position rather than message id
+11. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)
-12. **TitleMiddleware** - Auto-generates thread title after first complete exchange and normalizes structured message content before prompting the title model
+12. **TokenUsageMiddleware** - Records token usage metrics when token tracking is enabled (optional); subagent usage is cached by `tool_call_id` only while token usage is enabled and merged back into the dispatching AIMessage by message position rather than message id
-13. **MemoryMiddleware** - Queues conversations for async memory update (filters to user + final AI responses)
+13. **TitleMiddleware** - Auto-generates thread title after first complete exchange and normalizes structured message content before prompting the title model
-14. **ViewImageMiddleware** - Injects base64 image data before LLM call (conditional on vision support)
+14. **MemoryMiddleware** - Queues conversations for async memory update (filters to user + final AI responses)
-15. **DeferredToolFilterMiddleware** - Hides deferred (MCP) tool schemas from the bound model using a build-time deferred-name set + catalog hash, reading per-thread promotions from `ThreadState.promoted` (hash-scoped, no ContextVar); a tool becomes bound on subsequent turns after `tool_search` returns its schema (optional, if `tool_search.enabled`)
+15. **ViewImageMiddleware** - Injects base64 image data before LLM call (conditional on vision support)
-16. **SubagentLimitMiddleware** - Truncates excess `task` tool calls from model response to enforce `MAX_CONCURRENT_SUBAGENTS` limit (optional, if `subagent_enabled`)
+16. **DeferredToolFilterMiddleware** - Hides deferred (MCP) tool schemas from the bound model using a build-time deferred-name set + catalog hash, reading per-thread promotions from `ThreadState.promoted` (hash-scoped, no ContextVar); a tool becomes bound on subsequent turns after `tool_search` returns its schema (optional, if `tool_search.enabled`)
-17. **LoopDetectionMiddleware** - Detects repeated tool-call loops; hard-stop responses clear both structured `tool_calls` and raw provider tool-call metadata before forcing a final text answer
+17. **SubagentLimitMiddleware** - Truncates excess `task` tool calls from model response to enforce `MAX_CONCURRENT_SUBAGENTS` limit (optional, if `subagent_enabled`)
-18. **ClarificationMiddleware** - Intercepts `ask_clarification` tool calls, interrupts via `Command(goto=END)` (must be last)
+18. **LoopDetectionMiddleware** - Detects repeated tool-call loops; hard-stop responses clear both structured `tool_calls` and raw provider tool-call metadata before forcing a final text answer
+19. **ClarificationMiddleware** - Intercepts `ask_clarification` tool calls, interrupts via `Command(goto=END)` (must be last)
 
 ### Configuration System
 
@@ -348,6 +349,7 @@ Proxied through nginx: `/api/langgraph/*` → Gateway LangGraph-compatible runti
 - **Format**: Directory with `SKILL.md` (YAML frontmatter: name, description, license, allowed-tools)
 - **Loading**: `load_skills()` recursively scans `skills/{public,custom}` for `SKILL.md`, parses metadata, and reads enabled state from extensions_config.json
 - **Injection**: Enabled skills listed in agent system prompt with container paths
+- **Slash activation**: `/skill-name task` loads that enabled skill's `SKILL.md` for the current model call only. The resolver rejects leading whitespace, missing separators, reserved channel commands (`/new`, `/help`, `/bootstrap`, `/status`, `/models`, `/memory`), disabled skills, and skills outside a custom agent's whitelist.
 - **Installation**: `POST /api/skills/install` extracts .skill ZIP archive to custom/ directory
 
 ### Model Factory (`packages/harness/deerflow/models/factory.py`)

backend/app/channels/commands.py

@@ -18,3 +18,10 @@ KNOWN_CHANNEL_COMMANDS: frozenset[str] = frozenset(
         "/help",
     }
 )
+
+
+def is_known_channel_command(text: str) -> bool:
+    """Return whether text starts with a registered channel control command."""
+    if not text.startswith("/"):
+        return False
+    return text.split(maxsplit=1)[0].lower() in KNOWN_CHANNEL_COMMANDS

backend/app/channels/dingtalk.py

@@ -14,7 +14,7 @@ from typing import Any
 import httpx
 
 from app.channels.base import Channel
-from app.channels.commands import KNOWN_CHANNEL_COMMANDS
+from app.channels.commands import is_known_channel_command
 from app.channels.message_bus import InboundMessage, InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
 
 logger = logging.getLogger(__name__)
@@ -59,9 +59,7 @@ def _normalize_allowed_users(allowed_users: Any) -> set[str]:
 
 
 def _is_dingtalk_command(text: str) -> bool:
-    if not text.startswith("/"):
+    return is_known_channel_command(text)
-        return False
-    return text.split(maxsplit=1)[0].lower() in KNOWN_CHANNEL_COMMANDS
 
 
 def _extract_text_from_rich_text(rich_text_list: list) -> str:

backend/app/channels/discord.py

@@ -10,6 +10,7 @@ from pathlib import Path
 from typing import Any
 
 from app.channels.base import Channel
+from app.channels.commands import is_known_channel_command
 from app.channels.message_bus import InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
 
 logger = logging.getLogger(__name__)
@@ -300,7 +301,7 @@ class DiscordChannel(Channel):
 
             # If this is a known active thread, process normally
             if thread_id in self._active_thread_ids:
-                msg_type = InboundMessageType.COMMAND if text.startswith("/") else InboundMessageType.CHAT
+                msg_type = InboundMessageType.COMMAND if is_known_channel_command(text) else InboundMessageType.CHAT
                 inbound = self._make_inbound(
                     chat_id=chat_id,
                     user_id=str(message.author.id),
@@ -407,7 +408,7 @@ class DiscordChannel(Channel):
             chat_id = channel_id
             typing_target = message.channel  # Type into the channel
 
-        msg_type = InboundMessageType.COMMAND if text.startswith("/") else InboundMessageType.CHAT
+        msg_type = InboundMessageType.COMMAND if is_known_channel_command(text) else InboundMessageType.CHAT
         inbound = self._make_inbound(
             chat_id=chat_id,
             user_id=str(message.author.id),

backend/app/channels/feishu.py

@@ -11,7 +11,7 @@ import time
 from typing import Any, Literal
 
 from app.channels.base import Channel
-from app.channels.commands import KNOWN_CHANNEL_COMMANDS
+from app.channels.commands import is_known_channel_command
 from app.channels.message_bus import (
     PENDING_CLARIFICATION_METADATA_KEY,
     RESOLVED_FROM_PENDING_CLARIFICATION_METADATA_KEY,
@@ -30,9 +30,7 @@ PENDING_CLARIFICATION_TTL_SECONDS = 30 * 60
 
 
 def _is_feishu_command(text: str) -> bool:
-    if not text.startswith("/"):
+    return is_known_channel_command(text)
-        return False
-    return text.split(maxsplit=1)[0].lower() in KNOWN_CHANNEL_COMMANDS
 
 
 class FeishuChannel(Channel):

backend/app/channels/manager.py

@@ -8,6 +8,7 @@ import mimetypes
 import re
 import time
 from collections.abc import Awaitable, Callable, Mapping
+from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
 
@@ -26,8 +27,13 @@ from app.channels.message_bus import (
 from app.channels.store import ChannelStore
 from app.gateway.csrf_middleware import CSRF_COOKIE_NAME, CSRF_HEADER_NAME, generate_csrf_token
 from app.gateway.internal_auth import create_internal_auth_headers
+from deerflow.config.agents_config import load_agent_config
 from deerflow.config.paths import make_safe_user_id
 from deerflow.runtime.user_context import get_effective_user_id
+from deerflow.skills.slash import parse_slash_skill_reference
+from deerflow.skills.storage import get_or_new_skill_storage
+from deerflow.skills.storage.skill_storage import SkillStorage
+from deerflow.utils.messages import ORIGINAL_USER_CONTENT_KEY
 
 logger = logging.getLogger(__name__)
 
@@ -124,6 +130,16 @@ class InvalidChannelSessionConfigError(ValueError):
     """Raised when IM channel session overrides contain invalid agent config."""
 
 
+class SlashSkillCommandResolutionError(RuntimeError):
+    """Raised when IM slash-skill command resolution cannot complete safely."""
+
+
+@dataclass(frozen=True, slots=True)
+class _SlashSkillCommandResolution:
+    route_to_chat: bool = False
+    failure_message: str | None = None
+
+
 def _is_thread_busy_error(exc: BaseException | None) -> bool:
     if exc is None:
         return False
@@ -410,6 +426,46 @@ def _format_artifact_text(artifacts: list[str]) -> str:
 _OUTPUTS_VIRTUAL_PREFIX = "/mnt/user-data/outputs/"
 
 
+def _unknown_command_reply(command: str | None = None) -> str:
+    available = " | ".join(sorted(KNOWN_CHANNEL_COMMANDS))
+    if command:
+        return f"Unknown command: /{command}. Available commands: {available}"
+    return f"Unknown command. Available commands: {available}"
+
+
+def _human_input_message(content: str, *, original_content: str | None = None) -> dict[str, Any]:
+    message: dict[str, Any] = {"role": "human", "content": content}
+    if original_content is not None and original_content != content:
+        message["additional_kwargs"] = {ORIGINAL_USER_CONTENT_KEY: original_content}
+    return message
+
+
+def _resolve_slash_skill_command(
+    text: str,
+    available_skills: set[str] | None = None,
+    storage: SkillStorage | Callable[[], SkillStorage] | None = None,
+) -> _SlashSkillCommandResolution | None:
+    reference = parse_slash_skill_reference(text)
+    if reference is None:
+        return None
+    try:
+        resolved_storage = storage() if callable(storage) else storage or get_or_new_skill_storage()
+        skills = resolved_storage.load_skills(enabled_only=False)
+
+        skill = next((candidate for candidate in skills if candidate.name == reference.name), None)
+        if skill is None:
+            return None
+        if not skill.enabled:
+            return _SlashSkillCommandResolution(failure_message=f"Skill `/{reference.name}` is installed but disabled. Enable it before using slash activation.")
+        if available_skills is not None and reference.name not in available_skills:
+            return _SlashSkillCommandResolution(failure_message=f"Skill `/{reference.name}` is not available for this agent.")
+
+        return _SlashSkillCommandResolution(route_to_chat=True)
+    except Exception as exc:
+        logger.exception("[Manager] failed to resolve slash skill command")
+        raise SlashSkillCommandResolutionError("Failed to resolve slash skill command. Please check the skill configuration.") from exc
+
+
 def _resolve_attachments(thread_id: str, artifacts: list[str]) -> list[ResolvedAttachment]:
     """Resolve virtual artifact paths to host filesystem paths with metadata.
 
@@ -624,6 +680,7 @@ class ChannelManager:
         self._default_session = _as_dict(default_session)
         self._channel_sessions = dict(channel_sessions or {})
         self._client = None  # lazy init — langgraph_sdk async client
+        self._skill_storage: SkillStorage | None = None
         self._csrf_token = generate_csrf_token()
         self._semaphore: asyncio.Semaphore | None = None
         self._running = False
@@ -696,6 +753,21 @@ class ChannelManager:
 
         return assistant_id, run_config, run_context
 
+    def _resolve_available_skill_names(self, msg: InboundMessage) -> set[str] | None:
+        thread_id = self.store.get_thread_id(msg.channel_name, msg.chat_id, topic_id=msg.topic_id) or ""
+        _, _, run_context = self._resolve_run_params(msg, thread_id)
+        if run_context.get("is_bootstrap"):
+            return {"bootstrap"}
+
+        agent_name = run_context.get("agent_name")
+        if not isinstance(agent_name, str) or not agent_name.strip():
+            return None
+
+        agent_config = load_agent_config(_normalize_custom_agent_name(agent_name))
+        if agent_config and agent_config.skills is not None:
+            return set(agent_config.skills)
+        return None
+
     # -- LangGraph SDK client (lazy) ----------------------------------------
 
     def _get_client(self):
@@ -713,6 +785,11 @@ class ChannelManager:
             )
         return self._client
 
+    def _get_skill_storage(self) -> SkillStorage:
+        if self._skill_storage is None:
+            self._skill_storage = get_or_new_skill_storage()
+        return self._skill_storage
+
     # -- lifecycle ---------------------------------------------------------
 
     async def start(self) -> None:
@@ -782,6 +859,14 @@ class ChannelManager:
                     exc,
                 )
                 await self._send_error(msg, str(exc))
+            except SlashSkillCommandResolutionError as exc:
+                logger.warning(
+                    "Slash skill command resolution failed for %s (chat=%s): %s",
+                    msg.channel_name,
+                    msg.chat_id,
+                    exc,
+                )
+                await self._send_error(msg, str(exc))
             except Exception:
                 logger.exception(
                     "Error handling message from %s (chat=%s)",
@@ -836,9 +921,11 @@ class ChannelManager:
         if extra_context:
             run_context.update(extra_context)
 
+        original_text = msg.text
         uploaded = await _ingest_inbound_files(thread_id, msg)
         if uploaded:
             msg.text = f"{_format_uploaded_files_block(uploaded)}\n\n{msg.text}".strip()
+        human_message = _human_input_message(msg.text, original_content=original_text)
 
         if self._channel_supports_streaming(msg.channel_name):
             await self._handle_streaming_chat(
@@ -848,6 +935,7 @@ class ChannelManager:
                 assistant_id,
                 run_config,
                 run_context,
+                human_message,
             )
             return
 
@@ -856,7 +944,7 @@ class ChannelManager:
             result = await client.runs.wait(
                 thread_id,
                 assistant_id,
-                input={"messages": [{"role": "human", "content": msg.text}]},
+                input={"messages": [human_message]},
                 config=run_config,
                 context=run_context,
                 multitask_strategy="reject",
@@ -909,6 +997,7 @@ class ChannelManager:
         assistant_id: str,
         run_config: dict[str, Any],
         run_context: dict[str, Any],
+        human_message: dict[str, Any],
     ) -> None:
         logger.info("[Manager] invoking runs.stream(thread_id=%s, text=%r)", thread_id, msg.text[:100])
 
@@ -924,7 +1013,7 @@ class ChannelManager:
             async for chunk in client.runs.stream(
                 thread_id,
                 assistant_id,
-                input={"messages": [{"role": "human", "content": msg.text}]},
+                input={"messages": [human_message]},
                 config=run_config,
                 context=run_context,
                 stream_mode=["messages-tuple", "values"],
@@ -1011,11 +1100,20 @@ class ChannelManager:
     # -- command handling --------------------------------------------------
 
     async def _handle_command(self, msg: InboundMessage) -> None:
-        text = msg.text.strip()
+        raw_text = msg.text
+        text = raw_text.strip()
         parts = text.split(maxsplit=1)
-        command = parts[0].lower().lstrip("/")
+        reply: str | None = None
+        if not parts:
+            command = None
+            reply = _unknown_command_reply()
+        else:
+            command = parts[0].lower().removeprefix("/")
 
-        if command == "bootstrap":
+        if reply is None and not raw_text.startswith("/"):
+            reply = _unknown_command_reply(command)
+
+        if reply is None and command == "bootstrap":
             from dataclasses import replace as _dc_replace
 
             chat_text = parts[1] if len(parts) > 1 else "Initialize workspace"
@@ -1023,7 +1121,7 @@ class ChannelManager:
             await self._handle_chat(chat_msg, extra_context={"is_bootstrap": True})
             return
 
-        if command == "new":
+        if reply is None and command == "new":
             # Create a new thread through Gateway
             client = self._get_client()
             thread = await client.threads.create()
@@ -1036,14 +1134,14 @@ class ChannelManager:
                 user_id=msg.user_id,
             )
             reply = "New conversation started."
-        elif command == "status":
+        elif reply is None and command == "status":
             thread_id = self.store.get_thread_id(msg.channel_name, msg.chat_id, topic_id=msg.topic_id)
             reply = f"Active thread: {thread_id}" if thread_id else "No active conversation."
-        elif command == "models":
+        elif reply is None and command == "models":
             reply = await self._fetch_gateway("/api/models", "models")
-        elif command == "memory":
+        elif reply is None and command == "memory":
             reply = await self._fetch_gateway("/api/memory", "memory")
-        elif command == "help":
+        elif reply is None and command == "help":
             reply = (
                 "Available commands:\n"
                 "/bootstrap — Start a bootstrap session (enables agent setup)\n"
@@ -1051,16 +1149,32 @@ class ChannelManager:
                 "/status — Show current thread info\n"
                 "/models — List available models\n"
                 "/memory — Show memory status\n"
+                "/<skill-name> <task> — Activate an enabled skill for one turn\n"
                 "/help — Show this help"
             )
-        else:
+        elif reply is None:
-            available = " | ".join(sorted(KNOWN_CHANNEL_COMMANDS))
+            slash_resolution = await asyncio.to_thread(
-            reply = f"Unknown command: /{command}. Available commands: {available}"
+                lambda: _resolve_slash_skill_command(
+                    raw_text,
+                    self._resolve_available_skill_names(msg),
+                    self._get_skill_storage,
+                )
+            )
+            if slash_resolution and slash_resolution.failure_message:
+                reply = slash_resolution.failure_message
+            elif slash_resolution and slash_resolution.route_to_chat:
+                from dataclasses import replace as _dc_replace
+
+                chat_msg = _dc_replace(msg, msg_type=InboundMessageType.CHAT)
+                await self._handle_chat(chat_msg)
+                return
+            else:
+                reply = _unknown_command_reply(command)
 
         outbound = OutboundMessage(
             channel_name=msg.channel_name,
             chat_id=msg.chat_id,
-            thread_id=self.store.get_thread_id(msg.channel_name, msg.chat_id) or "",
+            thread_id=self.store.get_thread_id(msg.channel_name, msg.chat_id, topic_id=msg.topic_id) or "",
             text=reply,
             thread_ts=msg.thread_ts,
             metadata=_slim_metadata(msg.metadata),
@@ -1098,7 +1212,7 @@ class ChannelManager:
         outbound = OutboundMessage(
             channel_name=msg.channel_name,
             chat_id=msg.chat_id,
-            thread_id=self.store.get_thread_id(msg.channel_name, msg.chat_id) or "",
+            thread_id=self.store.get_thread_id(msg.channel_name, msg.chat_id, topic_id=msg.topic_id) or "",
             text=error_text,
             thread_ts=msg.thread_ts,
             metadata=_slim_metadata(msg.metadata),

backend/app/channels/slack.py

@@ -9,6 +9,7 @@ from typing import Any
 from markdown_to_mrkdwn import SlackMarkdownConverter
 
 from app.channels.base import Channel
+from app.channels.commands import is_known_channel_command
 from app.channels.message_bus import InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
 
 logger = logging.getLogger(__name__)
@@ -32,6 +33,20 @@ def _normalize_allowed_users(allowed_users: Any) -> set[str]:
     return {str(user_id) for user_id in values if str(user_id)}
 
 
+def _strip_leading_slack_bot_mention(text: str, bot_user_id: str | None) -> str:
+    if not bot_user_id:
+        return text
+    if not text.startswith("<@"):
+        return text
+    end = text.find(">")
+    if end <= 2:
+        return text
+    mentioned_user_id = text[2:end].split("|", 1)[0].lstrip("!")
+    if mentioned_user_id != bot_user_id:
+        return text
+    return text[end + 1 :].lstrip()
+
+
 class SlackChannel(Channel):
     """Slack IM channel using Socket Mode (WebSocket, no public IP).
 
@@ -49,6 +64,8 @@ class SlackChannel(Channel):
         self._web_client = None
         self._loop: asyncio.AbstractEventLoop | None = None
         self._allowed_users = _normalize_allowed_users(config.get("allowed_users", []))
+        configured_bot_user_id = config.get("bot_user_id")
+        self._bot_user_id = str(configured_bot_user_id).lstrip("@") if configured_bot_user_id else None
 
     async def start(self) -> None:
         if self._running:
@@ -72,6 +89,17 @@ class SlackChannel(Channel):
             return
 
         self._web_client = WebClient(token=bot_token)
+        if self._bot_user_id is None:
+            try:
+                auth_info = await asyncio.to_thread(self._web_client.auth_test)
+                user_id = auth_info.get("user_id") if isinstance(auth_info, dict) else None
+                if user_id is None:
+                    auth_get = getattr(auth_info, "get", None)
+                    user_id = auth_get("user_id") if callable(auth_get) else None
+                if isinstance(user_id, str) and user_id:
+                    self._bot_user_id = user_id
+            except Exception:
+                logger.warning("[Slack] failed to resolve bot user id; app mention text may include the bot mention", exc_info=True)
         self._socket_client = SocketModeClient(
             app_token=app_token,
             web_client=self._web_client,
@@ -210,6 +238,12 @@ class SlackChannel(Channel):
             if event_type != "events_api":
                 return
 
+            if self._bot_user_id is None:
+                authorization = next((item for item in req.payload.get("authorizations", []) if isinstance(item, dict)), None)
+                user_id = authorization.get("user_id") if authorization else None
+                if isinstance(user_id, str) and user_id:
+                    self._bot_user_id = user_id
+
             event = req.payload.get("event", {})
             etype = event.get("type", "")
 
@@ -233,13 +267,15 @@ class SlackChannel(Channel):
             return
 
         text = event.get("text", "").strip()
+        if event.get("type") == "app_mention":
+            text = _strip_leading_slack_bot_mention(text, self._bot_user_id)
         if not text:
             return
 
         channel_id = event.get("channel", "")
         thread_ts = event.get("thread_ts") or event.get("ts", "")
 
-        if text.startswith("/"):
+        if is_known_channel_command(text):
             msg_type = InboundMessageType.COMMAND
         else:
             msg_type = InboundMessageType.CHAT

backend/app/channels/telegram.py

@@ -60,12 +60,17 @@ class TelegramChannel(Channel):
 
         # Command handlers
         app.add_handler(CommandHandler("start", self._cmd_start))
+        app.add_handler(CommandHandler("bootstrap", self._cmd_generic))
         app.add_handler(CommandHandler("new", self._cmd_generic))
         app.add_handler(CommandHandler("status", self._cmd_generic))
         app.add_handler(CommandHandler("models", self._cmd_generic))
         app.add_handler(CommandHandler("memory", self._cmd_generic))
         app.add_handler(CommandHandler("help", self._cmd_generic))
 
+        # Slash skill commands are dynamic and cannot all be pre-registered
+        # with Telegram, so route unknown slash commands through chat handling.
+        app.add_handler(MessageHandler(filters.TEXT & filters.COMMAND, self._on_text))
+
         # General message handler
         app.add_handler(MessageHandler(filters.TEXT & ~filters.COMMAND, self._on_text))
 
@@ -228,6 +233,33 @@ class TelegramChannel(Channel):
             return True
         return user_id in self._allowed_users
 
+    def _get_bot_username(self, context) -> str | None:
+        bot = getattr(context, "bot", None)
+        username = getattr(bot, "username", None)
+        if not username and self._application is not None:
+            username = getattr(getattr(self._application, "bot", None), "username", None)
+        return str(username) if username else None
+
+    @staticmethod
+    def _strip_bot_username_from_leading_command(text: str, bot_username: str | None) -> str:
+        username = (bot_username or "").lstrip("@").lower()
+        if not username or not text.startswith("/"):
+            return text
+
+        parts = text.split(maxsplit=1)
+        command_token = parts[0]
+        if "@" not in command_token:
+            return text
+
+        command_name, addressed_username = command_token[1:].rsplit("@", 1)
+        if not command_name or addressed_username.lower() != username:
+            return text
+
+        normalized = f"/{command_name}"
+        if len(parts) > 1:
+            normalized = f"{normalized} {parts[1]}"
+        return normalized
+
     async def _cmd_start(self, update, context) -> None:
         """Handle /start command."""
         if not self._check_user(update.effective_user.id):
@@ -243,7 +275,7 @@ class TelegramChannel(Channel):
         if not self._check_user(update.effective_user.id):
             return
 
-        text = update.message.text
+        text = self._strip_bot_username_from_leading_command(update.message.text.strip(), self._get_bot_username(context))
         chat_id = str(update.effective_chat.id)
         user_id = str(update.effective_user.id)
         msg_id = str(update.message.message_id)
@@ -279,7 +311,7 @@ class TelegramChannel(Channel):
         if not self._check_user(update.effective_user.id):
             return
 
-        text = update.message.text.strip()
+        text = self._strip_bot_username_from_leading_command(update.message.text.strip(), self._get_bot_username(context))
         if not text:
             return
 

backend/app/channels/wechat.py

@@ -22,6 +22,7 @@ from cryptography.hazmat.primitives import padding
 from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
 
 from app.channels.base import Channel
+from app.channels.commands import is_known_channel_command
 from app.channels.message_bus import InboundMessageType, MessageBus, OutboundMessage, ResolvedAttachment
 
 logger = logging.getLogger(__name__)
@@ -620,7 +621,7 @@ class WechatChannel(Channel):
             chat_id=chat_id,
             user_id=chat_id,
             text=text,
-            msg_type=InboundMessageType.COMMAND if text.startswith("/") else InboundMessageType.CHAT,
+            msg_type=InboundMessageType.COMMAND if is_known_channel_command(text) else InboundMessageType.CHAT,
             thread_ts=thread_ts,
             files=files,
             metadata={

backend/app/channels/wecom.py

@@ -8,6 +8,7 @@ from collections.abc import Awaitable, Callable
 from typing import Any, cast
 
 from app.channels.base import Channel
+from app.channels.commands import is_known_channel_command
 from app.channels.message_bus import (
     InboundMessageType,
     MessageBus,
@@ -270,7 +271,7 @@ class WeComChannel(Channel):
 
         user_id = (body.get("from") or {}).get("userid")
 
-        inbound_type = InboundMessageType.COMMAND if text.startswith("/") else InboundMessageType.CHAT
+        inbound_type = InboundMessageType.COMMAND if is_known_channel_command(text) else InboundMessageType.CHAT
         inbound = self._make_inbound(
             chat_id=user_id,  # keep user's conversation in memory
             user_id=user_id,

backend/packages/harness/deerflow/agents/lead_agent/agent.py

@@ -49,6 +49,8 @@ from deerflow.tracing import build_tracing_callbacks
 
 logger = logging.getLogger(__name__)
 
+_BOOTSTRAP_SKILL_NAMES = {"bootstrap"}
+
 
 def _get_runtime_config(config: RunnableConfig) -> dict:
     """Merge legacy configurable options with LangGraph runtime context."""
@@ -271,6 +273,7 @@ def build_middlewares(
     agent_name: str | None = None,
     custom_middlewares: list[AgentMiddleware] | None = None,
     *,
+    available_skills: set[str] | None = None,
     app_config: AppConfig | None = None,
     deferred_setup=None,
 ):
@@ -302,6 +305,13 @@ def build_middlewares(
 
     middlewares.append(DynamicContextMiddleware(agent_name=agent_name, app_config=resolved_app_config))
 
+    # Deterministically load a full SKILL.md when the user starts the turn with
+    # /skill-name. This keeps the base system prompt metadata-only while giving
+    # explicit user activation priority over model-side relevance guessing.
+    from deerflow.agents.middlewares.skill_activation_middleware import SkillActivationMiddleware
+
+    middlewares.append(SkillActivationMiddleware(available_skills=available_skills, app_config=resolved_app_config))
+
     # Add summarization middleware if enabled
     summarization_middleware = _create_summarization_middleware(app_config=resolved_app_config)
     if summarization_middleware is not None:
@@ -369,7 +379,7 @@ def build_middlewares(
 
 def _available_skill_names(agent_config, is_bootstrap: bool) -> set[str] | None:
     if is_bootstrap:
-        return {"bootstrap"}
+        return set(_BOOTSTRAP_SKILL_NAMES)
     if agent_config and agent_config.skills is not None:
         return set(agent_config.skills)
     return None
@@ -475,17 +485,25 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
 
     if is_bootstrap:
         # Special bootstrap agent with minimal prompt for initial custom agent creation flow
+        # Keep the bootstrap skill set intentionally narrow so agent creation
+        # remains deterministic before the custom agent's own config exists.
         raw_tools = get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled, app_config=resolved_app_config) + [setup_agent]
         filtered = filter_tools_by_skill_allowed_tools(raw_tools, skills_for_tool_policy)
         final_tools, setup = assemble_deferred_tools(filtered, enabled=resolved_app_config.tool_search.enabled)
         return create_agent(
             model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=resolved_app_config, attach_tracing=False),
             tools=final_tools,
-            middleware=build_middlewares(config, model_name=model_name, app_config=resolved_app_config, deferred_setup=setup),
+            middleware=build_middlewares(
+                config,
+                model_name=model_name,
+                available_skills=set(_BOOTSTRAP_SKILL_NAMES),
+                app_config=resolved_app_config,
+                deferred_setup=setup,
+            ),
             system_prompt=apply_prompt_template(
                 subagent_enabled=subagent_enabled,
                 max_concurrent_subagents=max_concurrent_subagents,
-                available_skills=set(["bootstrap"]),
+                available_skills=set(_BOOTSTRAP_SKILL_NAMES),
                 app_config=resolved_app_config,
                 deferred_names=setup.deferred_names,
             ),
@@ -502,12 +520,19 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
     return create_agent(
         model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort, app_config=resolved_app_config, attach_tracing=False),
         tools=final_tools,
-        middleware=build_middlewares(config, model_name=model_name, agent_name=agent_name, app_config=resolved_app_config, deferred_setup=setup),
+        middleware=build_middlewares(
+            config,
+            model_name=model_name,
+            agent_name=agent_name,
+            available_skills=available_skills,
+            app_config=resolved_app_config,
+            deferred_setup=setup,
+        ),
         system_prompt=apply_prompt_template(
             subagent_enabled=subagent_enabled,
             max_concurrent_subagents=max_concurrent_subagents,
             agent_name=agent_name,
-            available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None,
+            available_skills=available_skills,
             app_config=resolved_app_config,
             deferred_names=setup.deferred_names,
         ),

backend/packages/harness/deerflow/agents/lead_agent/prompt.py

@@ -625,6 +625,11 @@ You have access to skills that provide optimized workflows for specific tasks. E
 4. Load referenced resources only when needed during execution
 5. Follow the skill's instructions precisely
 
+**Explicit Slash Skill Activation:**
+- If the user starts a request with `/<skill-name>`, that skill was explicitly requested for the current turn.
+- Follow the activated skill before choosing a general workflow.
+- The runtime injects the activated skill content for explicit slash activations; do not call `read_file` for that SKILL.md again unless the injected skill references supporting resources you need.
+
 **Skills are located at:** {container_base_path}
 {skill_evolution_section}
 {skills_list}

backend/packages/harness/deerflow/agents/middlewares/skill_activation_middleware.py

@@ -0,0 +1,289 @@
+"""Middleware for explicit slash skill activation."""
+
+from __future__ import annotations
+
+import asyncio
+import hashlib
+import html
+import logging
+import uuid
+from collections.abc import Awaitable, Callable
+from dataclasses import dataclass
+from pathlib import Path
+from typing import TYPE_CHECKING, override
+
+from langchain.agents.middleware import AgentMiddleware
+from langchain.agents.middleware.types import ModelRequest, ModelResponse
+from langchain_core.messages import AIMessage, HumanMessage
+
+from deerflow.skills.slash import parse_slash_skill_reference, resolve_slash_skill
+from deerflow.skills.storage import get_or_new_skill_storage
+from deerflow.skills.storage.skill_storage import SkillStorage
+from deerflow.skills.types import SKILL_MD_FILE
+from deerflow.utils.messages import get_original_user_content_text
+
+if TYPE_CHECKING:
+    from deerflow.config.app_config import AppConfig
+
+logger = logging.getLogger(__name__)
+
+_SLASH_SKILL_ACTIVATION_KEY = "slash_skill_activation"
+_SLASH_SKILL_ACTIVATION_TARGET_ID_KEY = "slash_skill_activation_target_id"
+_SUMMARY_MESSAGE_NAME = "summary"
+
+
+@dataclass(frozen=True, slots=True)
+class _Activation:
+    skill_name: str
+    category: str
+    container_file_path: str
+    skill_content: str
+    content_hash: str
+    remaining_text: str
+
+
+@dataclass(frozen=True, slots=True)
+class _ActivationResolution:
+    activation: _Activation | None = None
+    failure_message: str | None = None
+
+
+def is_slash_skill_activation_reminder(message: object) -> bool:
+    """Return whether a message is hidden slash-skill activation context."""
+    return isinstance(message, HumanMessage) and bool(message.additional_kwargs.get(_SLASH_SKILL_ACTIVATION_KEY))
+
+
+def _is_user_activation_target(message: object) -> bool:
+    if not isinstance(message, HumanMessage):
+        return False
+    if message.name == _SUMMARY_MESSAGE_NAME:
+        return False
+    if message.additional_kwargs.get("hide_from_ui"):
+        return False
+    return True
+
+
+class SkillActivationMiddleware(AgentMiddleware):
+    """Inject full SKILL.md content when the user explicitly types /skill-name."""
+
+    def __init__(
+        self,
+        *,
+        available_skills: set[str] | None = None,
+        app_config: AppConfig | None = None,
+    ) -> None:
+        super().__init__()
+        self._available_skills = set(available_skills) if available_skills is not None else None
+        self._app_config = app_config
+
+    def _storage(self) -> SkillStorage:
+        if self._app_config is not None:
+            return get_or_new_skill_storage(app_config=self._app_config)
+        return get_or_new_skill_storage()
+
+    @staticmethod
+    def _read_skill_content(skill_file: Path, skills_root: Path) -> str:
+        if skill_file.name != SKILL_MD_FILE:
+            raise ValueError(f"Expected {SKILL_MD_FILE}, got {skill_file.name}")
+        resolved_root = skills_root.resolve()
+        resolved_file = skill_file.resolve()
+        try:
+            resolved_file.relative_to(resolved_root)
+        except ValueError as exc:
+            raise ValueError("Resolved skill file must stay within the configured skills root.") from exc
+        if not resolved_file.is_file():
+            raise FileNotFoundError(resolved_file)
+        return resolved_file.read_text(encoding="utf-8")
+
+    def _resolve_activation(self, text: str) -> _ActivationResolution | None:
+        reference = parse_slash_skill_reference(text)
+        if reference is None:
+            return None
+
+        storage = self._storage()
+        skills = storage.load_skills(enabled_only=False)
+        skill = next((candidate for candidate in skills if candidate.name == reference.name), None)
+        if skill is None:
+            return _ActivationResolution(failure_message=f"Skill `/{reference.name}` is not installed.")
+        if not skill.enabled:
+            return _ActivationResolution(failure_message=f"Skill `/{reference.name}` is installed but disabled. Enable it before using slash activation.")
+        if self._available_skills is not None and reference.name not in self._available_skills:
+            return _ActivationResolution(failure_message=f"Skill `/{reference.name}` is not available for this agent.")
+
+        resolved = resolve_slash_skill(
+            text,
+            skills,
+            available_skills=self._available_skills,
+            container_base_path=storage.get_container_root(),
+        )
+        if resolved is None:
+            return _ActivationResolution(failure_message=f"Skill `/{reference.name}` could not be resolved.")
+
+        try:
+            skill_content = self._read_skill_content(resolved.skill.skill_file, storage.get_skills_root_path())
+        except (OSError, ValueError):
+            logger.exception("Failed to read slash-activated skill %s", resolved.skill.name)
+            return _ActivationResolution(failure_message=f"Skill `/{reference.name}` could not be loaded safely. Please check the skill installation.")
+
+        content_hash = hashlib.sha256(skill_content.encode("utf-8")).hexdigest()
+        return _ActivationResolution(
+            activation=_Activation(
+                skill_name=resolved.skill.name,
+                category=str(resolved.skill.category),
+                container_file_path=resolved.container_file_path,
+                skill_content=skill_content,
+                content_hash=content_hash,
+                remaining_text=resolved.remaining_text,
+            )
+        )
+
+    @staticmethod
+    def _build_activation_reminder(activation: _Activation) -> str:
+        user_request = activation.remaining_text or ("No additional task text was provided after the slash skill command. Ask the user what they want to do with this skill if the next step is unclear.")
+        escaped_user_request = html.escape(user_request, quote=False)
+        escaped_skill_content = html.escape(activation.skill_content, quote=False)
+        escaped_skill_name = html.escape(activation.skill_name, quote=True)
+        escaped_category = html.escape(activation.category, quote=True)
+        escaped_path = html.escape(activation.container_file_path, quote=True)
+        escaped_content_hash = html.escape(activation.content_hash, quote=True)
+        return f"""<slash_skill_activation>
+The user explicitly activated the `{activation.skill_name}` skill for this turn.
+Treat the task text as:
+<user_request>
+{escaped_user_request}
+</user_request>
+
+Follow this skill before choosing a general workflow. Load supporting resources from the same skill directory only when needed.
+
+<skill name="{escaped_skill_name}" category="{escaped_category}" path="{escaped_path}" sha256="{escaped_content_hash}">
+<skill_content encoding="xml-escaped">
+{escaped_skill_content}
+</skill_content>
+</skill>
+</slash_skill_activation>"""
+
+    @staticmethod
+    def _has_existing_activation_for_target(messages: list, target_index: int, target: HumanMessage) -> bool:
+        if target_index <= 0:
+            return False
+
+        if target.id:
+            for previous in messages[:target_index]:
+                if not is_slash_skill_activation_reminder(previous):
+                    continue
+                target_id = previous.additional_kwargs.get(_SLASH_SKILL_ACTIVATION_TARGET_ID_KEY)
+                if target_id == target.id or previous.id == f"{target.id}__slash_activation":
+                    return True
+
+        previous = messages[target_index - 1]
+        return is_slash_skill_activation_reminder(previous)
+
+    def _find_activation_target(self, messages: list) -> tuple[int, HumanMessage, _ActivationResolution] | None:
+        if not messages:
+            return None
+
+        target_index = next((idx for idx in range(len(messages) - 1, -1, -1) if _is_user_activation_target(messages[idx])), None)
+        if target_index is None:
+            return None
+
+        target = messages[target_index]
+        if target is None:
+            return None
+        if self._has_existing_activation_for_target(messages, target_index, target):
+            return None
+
+        content = get_original_user_content_text(target.content, target.additional_kwargs)
+        resolution = self._resolve_activation(content)
+        if resolution is None:
+            return None
+        return target_index, target, resolution
+
+    @staticmethod
+    def _record_activation(request: ModelRequest, activation: _Activation, *, hook: str) -> None:
+        runtime = getattr(request, "runtime", None)
+        context = getattr(runtime, "context", None)
+        journal = context.get("__run_journal") if isinstance(context, dict) else None
+        if journal is None:
+            return
+        try:
+            journal.record_middleware(
+                "skill_activation",
+                name="SkillActivationMiddleware",
+                hook=hook,
+                action="activate",
+                changes={
+                    "skill_name": activation.skill_name,
+                    "category": activation.category,
+                    "path": activation.container_file_path,
+                    "content_hash": activation.content_hash,
+                },
+            )
+        except Exception:
+            logger.debug("Failed to record slash skill activation audit event", exc_info=True)
+
+    def _prepare_model_request(self, request: ModelRequest, *, hook: str) -> ModelRequest | AIMessage | None:
+        target_and_resolution = self._find_activation_target(list(request.messages))
+        if target_and_resolution is None:
+            return None
+
+        target_index, target, resolution = target_and_resolution
+        if resolution.failure_message:
+            return AIMessage(content=resolution.failure_message)
+
+        activation = resolution.activation
+        if activation is None:
+            return None
+
+        logger.info(
+            "SkillActivationMiddleware: activating slash skill %s category=%s path=%s hash=%s",
+            activation.skill_name,
+            activation.category,
+            activation.container_file_path,
+            activation.content_hash,
+        )
+        self._record_activation(request, activation, hook=hook)
+        activation_msg = self._make_activation_message(target, self._build_activation_reminder(activation))
+        messages = list(request.messages)
+        messages.insert(target_index, activation_msg)
+        return request.override(messages=messages)
+
+    @staticmethod
+    def _make_activation_message(target: HumanMessage, activation_content: str) -> HumanMessage:
+        stable_id = target.id or str(uuid.uuid4())
+        additional_kwargs = {
+            "hide_from_ui": True,
+            _SLASH_SKILL_ACTIVATION_KEY: True,
+        }
+        if target.id:
+            additional_kwargs[_SLASH_SKILL_ACTIVATION_TARGET_ID_KEY] = target.id
+        return HumanMessage(
+            content=activation_content,
+            id=f"{stable_id}__slash_activation",
+            additional_kwargs=additional_kwargs,
+        )
+
+    @override
+    def wrap_model_call(
+        self,
+        request: ModelRequest,
+        handler: Callable[[ModelRequest], ModelResponse],
+    ) -> ModelResponse | AIMessage:
+        prepared = self._prepare_model_request(request, hook="wrap_model_call")
+        if prepared is None:
+            return handler(request)
+        if isinstance(prepared, AIMessage):
+            return prepared
+        return handler(prepared)
+
+    @override
+    async def awrap_model_call(
+        self,
+        request: ModelRequest,
+        handler: Callable[[ModelRequest], Awaitable[ModelResponse]],
+    ) -> ModelResponse | AIMessage:
+        prepared = await asyncio.to_thread(self._prepare_model_request, request, hook="awrap_model_call")
+        if prepared is None:
+            return await handler(request)
+        if isinstance(prepared, AIMessage):
+            return prepared
+        return await handler(prepared)

backend/packages/harness/deerflow/agents/middlewares/uploads_middleware.py

@@ -13,6 +13,7 @@ from langgraph.runtime import Runtime
 from deerflow.config.paths import Paths, get_paths
 from deerflow.runtime.user_context import get_effective_user_id
 from deerflow.utils.file_conversion import extract_outline
+from deerflow.utils.messages import ORIGINAL_USER_CONTENT_KEY, message_content_to_text
 
 logger = logging.getLogger(__name__)
 
@@ -265,6 +266,8 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
 
         # Extract original content - handle both string and list formats
         original_content = last_message.content
+        additional_kwargs = dict(last_message.additional_kwargs or {})
+        additional_kwargs.setdefault(ORIGINAL_USER_CONTENT_KEY, message_content_to_text(original_content))
         if isinstance(original_content, str):
             # Simple case: string content, just prepend files message
             updated_content = f"{files_message}\n\n{original_content}"
@@ -285,7 +288,7 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
             content=updated_content,
             id=last_message.id,
             name=last_message.name,
-            additional_kwargs=last_message.additional_kwargs,
+            additional_kwargs=additional_kwargs,
         )
 
         messages[last_message_index] = updated_message

backend/packages/harness/deerflow/client.py

@@ -247,7 +247,15 @@ class DeerFlowClient:
             # Attaching them again on the model would emit duplicate spans.
             "model": create_chat_model(name=model_name, thinking_enabled=thinking_enabled, attach_tracing=False),
             "tools": final_tools,
-            "middleware": build_middlewares(config, model_name=model_name, agent_name=self._agent_name, custom_middlewares=self._middlewares, deferred_setup=deferred_setup),
+            "middleware": build_middlewares(
+                config,
+                model_name=model_name,
+                agent_name=self._agent_name,
+                available_skills=self._available_skills,
+                custom_middlewares=self._middlewares,
+                app_config=self._app_config,
+                deferred_setup=deferred_setup,
+            ),
             "system_prompt": apply_prompt_template(
                 subagent_enabled=subagent_enabled,
                 max_concurrent_subagents=max_concurrent_subagents,

backend/packages/harness/deerflow/skills/slash.py

@@ -0,0 +1,65 @@
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass
+
+from deerflow.skills.types import Skill
+
+RESERVED_SLASH_SKILL_NAMES = frozenset({"bootstrap", "help", "memory", "models", "new", "status"})
+_SLASH_SKILL_RE = re.compile(r"^/([a-z0-9]+(?:-[a-z0-9]+)*)(?:\s+|$)")
+
+
+@dataclass(frozen=True, slots=True)
+class SlashSkillReference:
+    """Parsed slash-skill command with the skill name and remaining task text."""
+
+    name: str
+    remaining_text: str
+
+
+@dataclass(frozen=True, slots=True)
+class ResolvedSlashSkill:
+    """Slash-skill activation resolved against enabled runtime-visible skills."""
+
+    skill: Skill
+    remaining_text: str
+    container_file_path: str
+
+
+def parse_slash_skill_reference(text: str) -> SlashSkillReference | None:
+    """Parse strict `/skill-name task` syntax, ignoring reserved control commands."""
+    match = _SLASH_SKILL_RE.match(text)
+    if not match:
+        return None
+    name = match.group(1)
+    if name in RESERVED_SLASH_SKILL_NAMES:
+        return None
+    return SlashSkillReference(
+        name=name,
+        remaining_text=text[match.end() :].lstrip(),
+    )
+
+
+def resolve_slash_skill(
+    text: str,
+    skills: list[Skill],
+    *,
+    available_skills: set[str] | None = None,
+    container_base_path: str = "/mnt/skills",
+) -> ResolvedSlashSkill | None:
+    """Resolve text into an enabled, whitelisted skill activation if possible."""
+    reference = parse_slash_skill_reference(text)
+    if reference is None:
+        return None
+    if available_skills is not None and reference.name not in available_skills:
+        return None
+
+    skill = next((candidate for candidate in skills if candidate.name == reference.name and candidate.enabled), None)
+    if skill is None:
+        return None
+
+    return ResolvedSlashSkill(
+        skill=skill,
+        remaining_text=reference.remaining_text,
+        container_file_path=skill.get_container_file_path(container_base_path),
+    )

backend/packages/harness/deerflow/utils/messages.py

@@ -0,0 +1,31 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any
+
+ORIGINAL_USER_CONTENT_KEY = "original_user_content"
+
+
+def message_content_to_text(content: Any) -> str:
+    """Extract text from LangChain message content shapes."""
+    if isinstance(content, str):
+        return content
+    if isinstance(content, list):
+        parts: list[str] = []
+        for item in content:
+            if isinstance(item, str):
+                parts.append(item)
+            elif isinstance(item, dict):
+                text = item.get("text")
+                if isinstance(text, str):
+                    parts.append(text)
+        return "\n".join(part for part in parts if part)
+    return str(content)
+
+
+def get_original_user_content_text(content: Any, additional_kwargs: Mapping[str, Any] | None) -> str:
+    """Return pre-middleware user text when available, otherwise content text."""
+    original_content = (additional_kwargs or {}).get(ORIGINAL_USER_CONTENT_KEY)
+    if isinstance(original_content, str):
+        return original_content
+    return message_content_to_text(content)

backend/tests/test_channels.py

@@ -21,6 +21,42 @@ from app.channels.message_bus import (
     ResolvedAttachment,
 )
 from app.channels.store import ChannelStore
+from deerflow.skills.types import Skill, SkillCategory
+from deerflow.utils.messages import ORIGINAL_USER_CONTENT_KEY
+
+
+def test_known_channel_command_detection_only_matches_control_commands():
+    from app.channels.commands import is_known_channel_command
+
+    assert is_known_channel_command("/new")
+    assert is_known_channel_command("/HELP now")
+    assert not is_known_channel_command("/mnt/user-data/uploads/report.pdf")
+    assert not is_known_channel_command("/data-analysis analyze uploads/foo.csv")
+    assert not is_known_channel_command(" /new")
+
+
+def _make_channel_skill(tmp_path: Path, name: str, *, enabled: bool = True) -> Skill:
+    skill_dir = tmp_path / name
+    skill_dir.mkdir(parents=True, exist_ok=True)
+    skill_file = skill_dir / "SKILL.md"
+    skill_file.write_text(f"# {name}\n", encoding="utf-8")
+    return Skill(
+        name=name,
+        description=f"Description for {name}",
+        license="MIT",
+        skill_dir=skill_dir,
+        skill_file=skill_file,
+        relative_path=Path(name),
+        category=SkillCategory.CUSTOM,
+        enabled=enabled,
+    )
+
+
+def _make_channel_skill_storage(skills: list[Skill]):
+    return SimpleNamespace(
+        load_skills=lambda *, enabled_only: [skill for skill in skills if skill.enabled] if enabled_only else skills,
+        get_container_root=lambda: "/mnt/skills",
+    )
 
 
 def _run(coro):
@@ -1334,6 +1370,496 @@ class TestChannelManager:
 
         _run(go())
 
+    def test_handle_command_blank_text_is_reported_without_running_agent(self):
+        from app.channels.manager import ChannelManager
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="   ",
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_not_called()
+            assert outbound_received[0].text.startswith("Unknown command.")
+
+        _run(go())
+
+    def test_handle_command_rejects_multi_slash_control_command(self):
+        from app.channels.manager import ChannelManager
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="//help",
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_not_called()
+            assert outbound_received[0].text.startswith("Unknown command: //help.")
+
+        _run(go())
+
+    def test_handle_command_requires_control_command_at_start(self):
+        from app.channels.manager import ChannelManager
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+
+            mock_client = _make_mock_langgraph_client(thread_id="new-thread-456")
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text=" /new",
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.threads.create.assert_not_called()
+            assert store.get_thread_id("test", "chat1") is None
+            assert outbound_received[0].text.startswith("Unknown command: /new.")
+
+        _run(go())
+
+    def test_handle_command_outbound_thread_id_uses_topic_thread(self):
+        from app.channels.manager import ChannelManager
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+            store.set_thread_id("test", "chat1", "base-thread")
+            store.set_thread_id("test", "chat1", "topic-thread", topic_id="topic-1")
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="/status",
+                msg_type=InboundMessageType.COMMAND,
+                topic_id="topic-1",
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            assert outbound_received[0].text == "Active thread: topic-thread"
+            assert outbound_received[0].thread_id == "topic-thread"
+
+        _run(go())
+
+    def test_handle_command_slash_skill_routes_to_chat(self, tmp_path):
+        from app.channels.manager import ChannelManager
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+            manager._skill_storage = _make_channel_skill_storage([_make_channel_skill(tmp_path, "data-analysis")])
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="/data-analysis analyze uploads/foo.csv",
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_called_once()
+            call_args = mock_client.runs.wait.call_args
+            assert call_args[1]["input"]["messages"][0]["content"] == "/data-analysis analyze uploads/foo.csv"
+            assert outbound_received[0].text == "Hello from agent!"
+
+        _run(go())
+
+    def test_handle_command_slash_skill_with_attachment_preserves_original_content(self, monkeypatch, tmp_path):
+        from app.channels.manager import ChannelManager
+
+        async def fake_ingest(thread_id, msg):
+            return [
+                {
+                    "filename": "report.pdf",
+                    "size": 12,
+                    "path": "/mnt/user-data/uploads/report.pdf",
+                    "is_image": False,
+                }
+            ]
+
+        monkeypatch.setattr("app.channels.manager._ingest_inbound_files", fake_ingest)
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+            manager._skill_storage = _make_channel_skill_storage([_make_channel_skill(tmp_path, "data-analysis")])
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            original_text = "/data-analysis analyze report.pdf"
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text=original_text,
+                files=[{"filename": "report.pdf"}],
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_called_once()
+            human_message = mock_client.runs.wait.call_args[1]["input"]["messages"][0]
+            assert human_message["content"].startswith("<uploaded_files>")
+            assert original_text in human_message["content"]
+            assert human_message["additional_kwargs"][ORIGINAL_USER_CONTENT_KEY] == original_text
+            assert outbound_received[0].text == "Hello from agent!"
+
+        _run(go())
+
+    def test_streaming_slash_skill_with_attachment_preserves_original_content(self, monkeypatch, tmp_path):
+        from app.channels.manager import ChannelManager
+
+        async def fake_ingest(thread_id, msg):
+            return [
+                {
+                    "filename": "report.pdf",
+                    "size": 12,
+                    "path": "/mnt/user-data/uploads/report.pdf",
+                    "is_image": False,
+                }
+            ]
+
+        monkeypatch.setattr("app.channels.manager._ingest_inbound_files", fake_ingest)
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+            manager._skill_storage = _make_channel_skill_storage([_make_channel_skill(tmp_path, "data-analysis")])
+
+            mock_client = _make_mock_langgraph_client()
+            mock_client.runs.stream = MagicMock(
+                return_value=_make_async_iterator(
+                    [
+                        _make_stream_part(
+                            "values",
+                            {"messages": [{"type": "ai", "content": "streamed response"}]},
+                        )
+                    ]
+                )
+            )
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            original_text = "/data-analysis analyze report.pdf"
+            inbound = InboundMessage(
+                channel_name="feishu",
+                chat_id="chat1",
+                user_id="user1",
+                text=original_text,
+                files=[{"filename": "report.pdf"}],
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: any(message.is_final for message in outbound_received))
+            await manager.stop()
+
+            mock_client.runs.stream.assert_called_once()
+            human_message = mock_client.runs.stream.call_args[1]["input"]["messages"][0]
+            assert human_message["content"].startswith("<uploaded_files>")
+            assert original_text in human_message["content"]
+            assert human_message["additional_kwargs"][ORIGINAL_USER_CONTENT_KEY] == original_text
+
+        _run(go())
+
+    def test_handle_command_slash_skill_requires_command_at_start(self, tmp_path):
+        from app.channels.manager import ChannelManager
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+            manager._skill_storage = _make_channel_skill_storage([_make_channel_skill(tmp_path, "data-analysis")])
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="  /data-analysis analyze uploads/foo.csv",
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_not_called()
+            assert outbound_received[0].text.startswith("Unknown command: /data-analysis.")
+
+        _run(go())
+
+    def test_handle_command_slash_skill_respects_custom_agent_skill_whitelist(self, monkeypatch, tmp_path):
+        from app.channels.manager import ChannelManager
+
+        monkeypatch.setattr("app.channels.manager.load_agent_config", lambda name: SimpleNamespace(skills=["frontend-design"]))
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(
+                bus=bus,
+                store=store,
+                default_session={"assistant_id": "analyst-agent"},
+            )
+            manager._skill_storage = _make_channel_skill_storage([_make_channel_skill(tmp_path, "data-analysis")])
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="/data-analysis analyze uploads/foo.csv",
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_not_called()
+            assert outbound_received[0].text == "Skill `/data-analysis` is not available for this agent."
+
+        _run(go())
+
+    def test_handle_command_slash_skill_reports_disabled_skill(self, tmp_path):
+        from app.channels.manager import ChannelManager
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+            manager._skill_storage = _make_channel_skill_storage([_make_channel_skill(tmp_path, "data-analysis", enabled=False)])
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="/data-analysis analyze uploads/foo.csv",
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_not_called()
+            assert outbound_received[0].text == "Skill `/data-analysis` is installed but disabled. Enable it before using slash activation."
+
+        _run(go())
+
+    def test_handle_command_uninstalled_slash_skill_stays_unknown_command(self, tmp_path):
+        from app.channels.manager import ChannelManager
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+            manager._skill_storage = _make_channel_skill_storage([_make_channel_skill(tmp_path, "frontend-design")])
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="/data-analysis analyze uploads/foo.csv",
+                msg_type=InboundMessageType.COMMAND,
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_not_called()
+            assert outbound_received[0].text.startswith("Unknown command: /data-analysis.")
+
+        _run(go())
+
+    def test_handle_command_slash_skill_resolution_error_is_reported(self, monkeypatch):
+        from app.channels.manager import ChannelManager, SlashSkillCommandResolutionError
+
+        def fail_resolution(text, available_skills=None, storage=None):
+            raise SlashSkillCommandResolutionError("Failed to resolve slash skill command. Please check the skill configuration.")
+
+        monkeypatch.setattr("app.channels.manager._resolve_slash_skill_command", fail_resolution)
+
+        async def go():
+            bus = MessageBus()
+            store = ChannelStore(path=Path(tempfile.mkdtemp()) / "store.json")
+            manager = ChannelManager(bus=bus, store=store)
+            store.set_thread_id("test", "chat1", "base-thread")
+            store.set_thread_id("test", "chat1", "topic-thread", topic_id="topic-1")
+
+            mock_client = _make_mock_langgraph_client()
+            manager._client = mock_client
+
+            outbound_received = []
+
+            async def capture_outbound(msg):
+                outbound_received.append(msg)
+
+            bus.subscribe_outbound(capture_outbound)
+            await manager.start()
+
+            inbound = InboundMessage(
+                channel_name="test",
+                chat_id="chat1",
+                user_id="user1",
+                text="/data-analysis analyze uploads/foo.csv",
+                msg_type=InboundMessageType.COMMAND,
+                topic_id="topic-1",
+            )
+            await bus.publish_inbound(inbound)
+            await _wait_for(lambda: len(outbound_received) >= 1)
+            await manager.stop()
+
+            mock_client.runs.wait.assert_not_called()
+            assert outbound_received[0].text == "Failed to resolve slash skill command. Please check the skill configuration."
+            assert outbound_received[0].thread_id == "topic-thread"
+
+        _run(go())
+
     def test_handle_command_new(self):
         from app.channels.manager import ChannelManager
 
@@ -2440,6 +2966,36 @@ class TestWeComChannel:
 
         _run(go())
 
+    def test_publish_ws_inbound_treats_slash_prefixed_paths_as_chat(self, monkeypatch):
+        from app.channels.wecom import WeComChannel
+
+        async def go():
+            bus = MessageBus()
+            bus.publish_inbound = AsyncMock()
+            channel = WeComChannel(bus, config={})
+            channel._ws_client = SimpleNamespace(reply_stream=AsyncMock())
+
+            monkeypatch.setitem(
+                __import__("sys").modules,
+                "aibot",
+                SimpleNamespace(generate_req_id=lambda prefix: "stream-1"),
+            )
+
+            frame = {
+                "body": {
+                    "msgid": "msg-1",
+                    "from": {"userid": "user-1"},
+                }
+            }
+
+            await channel._publish_ws_inbound(frame, "/mnt/user-data/uploads/report.pdf")
+
+            inbound = bus.publish_inbound.await_args.args[0]
+            assert inbound.text == "/mnt/user-data/uploads/report.pdf"
+            assert inbound.msg_type == InboundMessageType.CHAT
+
+        _run(go())
+
     def test_on_outbound_sends_attachment_before_clearing_context(self, tmp_path):
         from app.channels.wecom import WeComChannel
 
@@ -2788,6 +3344,219 @@ class TestSlackAllowedUsers:
         assert inbound.chat_id == "C123"
         assert inbound.text == "hello from slack"
 
+    def test_app_mention_strips_leading_bot_mention_before_command_detection(self):
+        from app.channels.slack import SlackChannel
+
+        bus = MessageBus()
+        bus.publish_inbound = AsyncMock()
+        channel = SlackChannel(bus=bus, config={"bot_user_id": "UBOT"})
+        channel._loop = MagicMock()
+        channel._loop.is_running.return_value = True
+        channel._add_reaction = MagicMock()
+        channel._send_running_reply = MagicMock()
+
+        event = {
+            "type": "app_mention",
+            "user": "U123456",
+            "text": "<@UBOT> /help",
+            "channel": "C123",
+            "ts": "1710000000.000100",
+        }
+
+        with patch(
+            "app.channels.slack.asyncio.run_coroutine_threadsafe",
+            side_effect=self._submit_coro,
+        ):
+            channel._handle_message_event(event)
+
+        inbound = bus.publish_inbound.call_args.args[0]
+        assert inbound.text == "/help"
+        assert inbound.msg_type == InboundMessageType.COMMAND
+
+    def test_app_mention_strips_labelled_leading_bot_mention(self):
+        from app.channels.slack import SlackChannel
+
+        bus = MessageBus()
+        bus.publish_inbound = AsyncMock()
+        channel = SlackChannel(bus=bus, config={"bot_user_id": "UBOT"})
+        channel._loop = MagicMock()
+        channel._loop.is_running.return_value = True
+        channel._add_reaction = MagicMock()
+        channel._send_running_reply = MagicMock()
+
+        event = {
+            "type": "app_mention",
+            "user": "U123456",
+            "text": "<@UBOT|deerflow> /help",
+            "channel": "C123",
+            "ts": "1710000000.000100",
+        }
+
+        with patch(
+            "app.channels.slack.asyncio.run_coroutine_threadsafe",
+            side_effect=self._submit_coro,
+        ):
+            channel._handle_message_event(event)
+
+        inbound = bus.publish_inbound.call_args.args[0]
+        assert inbound.text == "/help"
+        assert inbound.msg_type == InboundMessageType.COMMAND
+
+    def test_app_mention_strips_leading_bot_mention_before_slash_skill(self):
+        from app.channels.slack import SlackChannel
+
+        bus = MessageBus()
+        bus.publish_inbound = AsyncMock()
+        channel = SlackChannel(bus=bus, config={"bot_user_id": "UBOT"})
+        channel._loop = MagicMock()
+        channel._loop.is_running.return_value = True
+        channel._add_reaction = MagicMock()
+        channel._send_running_reply = MagicMock()
+
+        event = {
+            "type": "app_mention",
+            "user": "U123456",
+            "text": "<@UBOT> /data-analysis analyze uploads/foo.csv",
+            "channel": "C123",
+            "ts": "1710000000.000100",
+        }
+
+        with patch(
+            "app.channels.slack.asyncio.run_coroutine_threadsafe",
+            side_effect=self._submit_coro,
+        ):
+            channel._handle_message_event(event)
+
+        inbound = bus.publish_inbound.call_args.args[0]
+        assert inbound.text == "/data-analysis analyze uploads/foo.csv"
+        assert inbound.msg_type == InboundMessageType.CHAT
+
+    def test_app_mention_preserves_following_user_mention(self):
+        from app.channels.slack import SlackChannel
+
+        bus = MessageBus()
+        bus.publish_inbound = AsyncMock()
+        channel = SlackChannel(bus=bus, config={"bot_user_id": "UBOT"})
+        channel._loop = MagicMock()
+        channel._loop.is_running.return_value = True
+        channel._add_reaction = MagicMock()
+        channel._send_running_reply = MagicMock()
+
+        event = {
+            "type": "app_mention",
+            "user": "U123456",
+            "text": "<@UBOT> <@UASSIGNEE> please review this",
+            "channel": "C123",
+            "ts": "1710000000.000100",
+        }
+
+        with patch(
+            "app.channels.slack.asyncio.run_coroutine_threadsafe",
+            side_effect=self._submit_coro,
+        ):
+            channel._handle_message_event(event)
+
+        inbound = bus.publish_inbound.call_args.args[0]
+        assert inbound.text == "<@UASSIGNEE> please review this"
+        assert inbound.msg_type == InboundMessageType.CHAT
+
+    def test_app_mention_preserves_leading_non_bot_mention_when_bot_id_known(self):
+        from app.channels.slack import SlackChannel
+
+        bus = MessageBus()
+        bus.publish_inbound = AsyncMock()
+        channel = SlackChannel(bus=bus, config={"bot_user_id": "UBOT"})
+        channel._loop = MagicMock()
+        channel._loop.is_running.return_value = True
+        channel._add_reaction = MagicMock()
+        channel._send_running_reply = MagicMock()
+
+        event = {
+            "type": "app_mention",
+            "user": "U123456",
+            "text": "<@UASSIGNEE> <@UBOT> please review this",
+            "channel": "C123",
+            "ts": "1710000000.000100",
+        }
+
+        with patch(
+            "app.channels.slack.asyncio.run_coroutine_threadsafe",
+            side_effect=self._submit_coro,
+        ):
+            channel._handle_message_event(event)
+
+        inbound = bus.publish_inbound.call_args.args[0]
+        assert inbound.text == "<@UASSIGNEE> <@UBOT> please review this"
+        assert inbound.msg_type == InboundMessageType.CHAT
+
+    def test_app_mention_preserves_leading_non_bot_mention_when_bot_id_unknown(self):
+        from app.channels.slack import SlackChannel
+
+        bus = MessageBus()
+        bus.publish_inbound = AsyncMock()
+        channel = SlackChannel(bus=bus, config={})
+        channel._loop = MagicMock()
+        channel._loop.is_running.return_value = True
+        channel._add_reaction = MagicMock()
+        channel._send_running_reply = MagicMock()
+
+        event = {
+            "type": "app_mention",
+            "user": "U123456",
+            "text": "<@UASSIGNEE> /help <@UBOT>",
+            "channel": "C123",
+            "ts": "1710000000.000100",
+        }
+
+        with patch(
+            "app.channels.slack.asyncio.run_coroutine_threadsafe",
+            side_effect=self._submit_coro,
+        ):
+            channel._handle_message_event(event)
+
+        inbound = bus.publish_inbound.call_args.args[0]
+        assert inbound.text == "<@UASSIGNEE> /help <@UBOT>"
+        assert inbound.msg_type == InboundMessageType.CHAT
+
+    def test_socket_event_resolves_bot_user_id_before_app_mention_command_detection(self):
+        from app.channels.slack import SlackChannel
+
+        bus = MessageBus()
+        bus.publish_inbound = AsyncMock()
+        channel = SlackChannel(bus=bus, config={})
+        channel._SocketModeResponse = lambda envelope_id: SimpleNamespace(envelope_id=envelope_id)
+        channel._loop = MagicMock()
+        channel._loop.is_running.return_value = True
+        channel._add_reaction = MagicMock()
+        channel._send_running_reply = MagicMock()
+
+        client = SimpleNamespace(send_socket_mode_response=MagicMock())
+        req = SimpleNamespace(
+            envelope_id="env-1",
+            type="events_api",
+            payload={
+                "authorizations": [{"user_id": "UBOT"}],
+                "event": {
+                    "type": "app_mention",
+                    "user": "U123456",
+                    "text": "<@UBOT> /help",
+                    "channel": "C123",
+                    "ts": "1710000000.000100",
+                },
+            },
+        )
+
+        with patch(
+            "app.channels.slack.asyncio.run_coroutine_threadsafe",
+            side_effect=self._submit_coro,
+        ):
+            channel._on_socket_event(client, req)
+
+        inbound = bus.publish_inbound.call_args.args[0]
+        assert channel._bot_user_id == "UBOT"
+        assert inbound.text == "/help"
+        assert inbound.msg_type == InboundMessageType.COMMAND
+
     def test_scalar_allowed_users_warns_and_matches_stringified_event_user_id(self, caplog):
         from app.channels.slack import SlackChannel
 
@@ -2861,6 +3630,86 @@ class TestSlackAllowedUsers:
 
 
 class TestTelegramSendRetry:
+    def test_start_registers_known_channel_commands(self, monkeypatch):
+        import sys
+        from types import ModuleType
+
+        from app.channels.commands import KNOWN_CHANNEL_COMMANDS
+        from app.channels.telegram import TelegramChannel
+
+        class FakeFilter:
+            def __init__(self, expr: str):
+                self.expr = expr
+
+            def __and__(self, other):
+                return FakeFilter(f"{self.expr}&{other.expr}")
+
+            def __invert__(self):
+                return FakeFilter(f"~{self.expr}")
+
+        class FakeApplication:
+            def __init__(self):
+                self.handlers = []
+
+            def add_handler(self, handler):
+                self.handlers.append(handler)
+
+        fake_app = FakeApplication()
+
+        class FakeApplicationBuilder:
+            def token(self, token):
+                assert token == "test-token"
+                return self
+
+            def build(self):
+                return fake_app
+
+        def fake_command_handler(command, callback):
+            return SimpleNamespace(kind="command", command=command, callback=callback)
+
+        def fake_message_handler(filter_expr, callback):
+            return SimpleNamespace(kind="message", filter_expr=filter_expr, callback=callback)
+
+        telegram_mod = ModuleType("telegram")
+        telegram_ext_mod = ModuleType("telegram.ext")
+        telegram_ext_mod.ApplicationBuilder = FakeApplicationBuilder
+        telegram_ext_mod.CommandHandler = fake_command_handler
+        telegram_ext_mod.MessageHandler = fake_message_handler
+        telegram_ext_mod.filters = SimpleNamespace(TEXT=FakeFilter("TEXT"), COMMAND=FakeFilter("COMMAND"))
+        telegram_mod.ext = telegram_ext_mod
+        monkeypatch.setitem(sys.modules, "telegram", telegram_mod)
+        monkeypatch.setitem(sys.modules, "telegram.ext", telegram_ext_mod)
+
+        class FakeThread:
+            def __init__(self, *, target, daemon):
+                self.target = target
+                self.daemon = daemon
+
+            def start(self):
+                return None
+
+            def join(self, timeout=None):
+                return None
+
+        monkeypatch.setattr("app.channels.telegram.threading.Thread", FakeThread)
+
+        async def go():
+            bus = MessageBus()
+            ch = TelegramChannel(bus=bus, config={"bot_token": "test-token"})
+
+            await ch.start()
+            try:
+                registered_commands = {handler.command for handler in fake_app.handlers if handler.kind == "command"}
+                expected_commands = {command.removeprefix("/") for command in KNOWN_CHANNEL_COMMANDS}
+                assert expected_commands <= registered_commands
+                assert "start" in registered_commands
+                message_filters = {handler.filter_expr.expr for handler in fake_app.handlers if handler.kind == "message"}
+                assert {"TEXT&COMMAND", "TEXT&~COMMAND"} <= message_filters
+            finally:
+                await ch.stop()
+
+        _run(go())
+
     def test_retries_on_failure_then_succeeds(self):
         from app.channels.telegram import TelegramChannel
 
@@ -2984,6 +3833,47 @@ class TestTelegramPrivateChatThread:
 
         _run(go())
 
+    def test_private_chat_slash_skill_text_routes_as_chat(self):
+        from app.channels.telegram import TelegramChannel
+
+        async def go():
+            bus = MessageBus()
+            ch = TelegramChannel(bus=bus, config={"bot_token": "test-token"})
+            ch._main_loop = asyncio.get_event_loop()
+
+            update = _make_telegram_update("private", message_id=12, text="/data-analysis analyze uploads/foo.csv")
+            await ch._on_text(update, None)
+
+            msg = await asyncio.wait_for(bus.get_inbound(), timeout=2)
+            assert msg.text == "/data-analysis analyze uploads/foo.csv"
+            assert msg.msg_type == InboundMessageType.CHAT
+            assert msg.topic_id is None
+
+        _run(go())
+
+    def test_slash_skill_addressed_to_telegram_bot_strips_username(self):
+        from app.channels.telegram import TelegramChannel
+
+        async def go():
+            bus = MessageBus()
+            ch = TelegramChannel(bus=bus, config={"bot_token": "test-token"})
+            ch._main_loop = asyncio.get_event_loop()
+
+            update = _make_telegram_update(
+                "group",
+                message_id=13,
+                text="/data-analysis@DeerFlowBot analyze uploads/foo.csv",
+            )
+            context = SimpleNamespace(bot=SimpleNamespace(username="DeerFlowBot"))
+            await ch._on_text(update, context)
+
+            msg = await asyncio.wait_for(bus.get_inbound(), timeout=2)
+            assert msg.text == "/data-analysis analyze uploads/foo.csv"
+            assert msg.msg_type == InboundMessageType.CHAT
+            assert msg.topic_id == "13"
+
+        _run(go())
+
     def test_private_chat_with_reply_still_uses_none_topic(self):
         from app.channels.telegram import TelegramChannel
 
@@ -3099,6 +3989,25 @@ class TestTelegramPrivateChatThread:
 
         _run(go())
 
+    def test_cmd_generic_strips_addressed_telegram_bot_username(self):
+        from app.channels.telegram import TelegramChannel
+
+        async def go():
+            bus = MessageBus()
+            ch = TelegramChannel(bus=bus, config={"bot_token": "test-token"})
+            ch._main_loop = asyncio.get_event_loop()
+
+            update = _make_telegram_update("group", message_id=33, text="/status@DeerFlowBot")
+            context = SimpleNamespace(bot=SimpleNamespace(username="DeerFlowBot"))
+            await ch._cmd_generic(update, context)
+
+            msg = await asyncio.wait_for(bus.get_inbound(), timeout=2)
+            assert msg.text == "/status"
+            assert msg.topic_id == "33"
+            assert msg.msg_type == InboundMessageType.COMMAND
+
+        _run(go())
+
 
 class TestTelegramProcessingOrder:
     """Ensure 'working on it...' is sent before inbound is published."""

backend/tests/test_discord_channel.py

@@ -2,9 +2,13 @@
 
 from __future__ import annotations
 
+from types import SimpleNamespace
+
+import pytest
+
 from app.channels.discord import DiscordChannel
 from app.channels.manager import CHANNEL_CAPABILITIES
-from app.channels.message_bus import MessageBus
+from app.channels.message_bus import InboundMessageType, MessageBus
 from app.channels.service import _CHANNEL_REGISTRY
 
 
@@ -21,3 +25,64 @@ def test_discord_channel_init() -> None:
     channel = DiscordChannel(bus=bus, config={"bot_token": "token"})
 
     assert channel.name == "discord"
+
+
+def _make_discord_message(text: str):
+    return SimpleNamespace(
+        id=111,
+        content=text,
+        author=SimpleNamespace(id=123, bot=False, display_name="alice"),
+        guild=SimpleNamespace(id=321),
+        channel=SimpleNamespace(id=456),
+        add_reaction=lambda _emoji: None,
+    )
+
+
+@pytest.mark.asyncio
+async def test_discord_bot_mention_slash_skill_routes_as_chat() -> None:
+    bus = MessageBus()
+    channel = DiscordChannel(bus=bus, config={"bot_token": "token"})
+    captured = []
+    channel._running = True
+    channel._client = SimpleNamespace(user=SimpleNamespace(id=999, mention="<@999>"))
+    channel._discord_module = SimpleNamespace(Thread=type("FakeThread", (), {}))
+    channel._publish = captured.append
+
+    async def noop(*_args, **_kwargs):
+        return None
+
+    channel._start_typing = noop
+    channel._add_reaction = noop
+
+    await channel._on_message(_make_discord_message("<@999> /data-analysis analyze uploads/foo.csv"))
+
+    assert len(captured) == 1
+    inbound = captured[0]
+    assert inbound.text == "/data-analysis analyze uploads/foo.csv"
+    assert inbound.msg_type == InboundMessageType.CHAT
+    assert inbound.topic_id == "456"
+
+
+@pytest.mark.asyncio
+async def test_discord_bot_mention_known_command_routes_as_command() -> None:
+    bus = MessageBus()
+    channel = DiscordChannel(bus=bus, config={"bot_token": "token"})
+    captured = []
+    channel._running = True
+    channel._client = SimpleNamespace(user=SimpleNamespace(id=999, mention="<@999>"))
+    channel._discord_module = SimpleNamespace(Thread=type("FakeThread", (), {}))
+    channel._publish = captured.append
+
+    async def noop(*_args, **_kwargs):
+        return None
+
+    channel._start_typing = noop
+    channel._add_reaction = noop
+
+    await channel._on_message(_make_discord_message("<@999> /help"))
+
+    assert len(captured) == 1
+    inbound = captured[0]
+    assert inbound.text == "/help"
+    assert inbound.msg_type == InboundMessageType.COMMAND
+    assert inbound.topic_id == "456"

backend/tests/test_lead_agent_skills.py

@@ -60,6 +60,17 @@ def test_get_skills_prompt_section_returns_all_when_available_skills_is_none(mon
     assert "skill2" in result
 
 
+def test_get_skills_prompt_section_includes_slash_activation_guidance(monkeypatch):
+    skills = [_make_skill("data-analysis")]
+    monkeypatch.setattr("deerflow.agents.lead_agent.prompt._get_enabled_skills", lambda: skills)
+
+    result = get_skills_prompt_section(available_skills={"data-analysis"})
+
+    assert "Explicit Slash Skill Activation" in result
+    assert "The runtime injects the activated skill content" in result
+    assert "do not call `read_file` for that SKILL.md again" in result
+
+
 def test_get_skills_prompt_section_includes_self_evolution_rules(monkeypatch):
     skills = [_make_skill("skill1")]
     monkeypatch.setattr("deerflow.agents.lead_agent.prompt._get_enabled_skills", lambda: skills)

backend/tests/test_slash_skills.py

@@ -0,0 +1,557 @@
+import asyncio
+import hashlib
+from pathlib import Path
+from types import SimpleNamespace
+
+from langchain.agents.middleware.types import ModelRequest
+from langchain_core.messages import AIMessage, HumanMessage
+
+from app.channels.commands import KNOWN_CHANNEL_COMMANDS
+from deerflow.agents.middlewares import skill_activation_middleware as middleware_module
+from deerflow.agents.middlewares.skill_activation_middleware import SkillActivationMiddleware, is_slash_skill_activation_reminder
+from deerflow.skills.slash import RESERVED_SLASH_SKILL_NAMES, parse_slash_skill_reference, resolve_slash_skill
+from deerflow.skills.types import Skill, SkillCategory
+from deerflow.utils.messages import ORIGINAL_USER_CONTENT_KEY
+
+
+def _make_skill(tmp_path: Path, name: str, content: str = "skill body") -> Skill:
+    skill_dir = tmp_path / name
+    skill_dir.mkdir()
+    skill_file = skill_dir / "SKILL.md"
+    skill_file.write_text(content, encoding="utf-8")
+    return Skill(
+        name=name,
+        description=f"Description for {name}",
+        license="MIT",
+        skill_dir=skill_dir,
+        skill_file=skill_file,
+        relative_path=Path(name),
+        category=SkillCategory.CUSTOM,
+        enabled=True,
+    )
+
+
+def _make_storage(tmp_path: Path, skills: list[Skill]):
+    return SimpleNamespace(
+        load_skills=lambda *, enabled_only: [skill for skill in skills if skill.enabled] if enabled_only else skills,
+        get_container_root=lambda: "/mnt/skills",
+        get_skills_root_path=lambda: tmp_path,
+    )
+
+
+def _make_model_request(messages: list[HumanMessage], *, runtime=None) -> ModelRequest:
+    return ModelRequest(
+        model=object(),
+        messages=messages,
+        state={"messages": list(messages)},
+        runtime=runtime,
+    )
+
+
+def test_parse_slash_skill_reference_extracts_name_and_remaining_text():
+    parsed = parse_slash_skill_reference("/data-analysis analyze uploads/foo.csv")
+
+    assert parsed is not None
+    assert parsed.name == "data-analysis"
+    assert parsed.remaining_text == "analyze uploads/foo.csv"
+
+
+def test_parse_slash_skill_reference_accepts_skill_name_without_task():
+    parsed = parse_slash_skill_reference("/data-analysis")
+
+    assert parsed is not None
+    assert parsed.name == "data-analysis"
+    assert parsed.remaining_text == ""
+
+
+def test_parse_slash_skill_reference_rejects_invalid_names():
+    assert parse_slash_skill_reference("/DataAnalysis run") is None
+    assert parse_slash_skill_reference("/data_analysis run") is None
+    assert parse_slash_skill_reference("please use /data-analysis") is None
+    assert parse_slash_skill_reference("  /data-analysis run") is None
+    assert parse_slash_skill_reference("/data-analysis分析这个文档") is None
+
+
+def test_resolve_slash_skill_ignores_reserved_control_commands(tmp_path):
+    for command in ["bootstrap", "help", "memory", "models", "new", "status"]:
+        skill = _make_skill(tmp_path, command)
+
+        assert resolve_slash_skill(f"/{command} create an agent", [skill]) is None
+
+
+def test_reserved_slash_skill_names_match_channel_commands():
+    assert RESERVED_SLASH_SKILL_NAMES == {command.removeprefix("/") for command in KNOWN_CHANNEL_COMMANDS}
+
+
+def test_resolve_slash_skill_respects_available_skill_whitelist(tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis")
+
+    assert resolve_slash_skill("/data-analysis run", [skill], available_skills=set()) is None
+
+    resolved = resolve_slash_skill("/data-analysis run", [skill], available_skills={"data-analysis"})
+    assert resolved is not None
+    assert resolved.skill.name == "data-analysis"
+    assert resolved.remaining_text == "run"
+    assert resolved.container_file_path == "/mnt/skills/custom/data-analysis/SKILL.md"
+
+
+def test_resolve_slash_skill_rejects_disabled_skills(tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis")
+    skill.enabled = False
+
+    assert resolve_slash_skill("/data-analysis run", [skill]) is None
+
+
+def test_skill_activation_middleware_injects_hidden_human_context_for_model_call(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis analyze uploads/foo.csv", id="msg-1")
+    request = _make_model_request([original])
+    captured = {}
+
+    def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(request, handler)
+
+    assert isinstance(result, AIMessage)
+    assert result.content == "ok"
+    activation_msg, user_msg = captured["messages"]
+    assert is_slash_skill_activation_reminder(activation_msg)
+    assert activation_msg.additional_kwargs["hide_from_ui"] is True
+    assert "Use pandas." in activation_msg.content
+    assert "<user_request>\nanalyze uploads/foo.csv\n</user_request>" in activation_msg.content
+    assert user_msg.content == original.content
+    assert request.state["messages"] == [original]
+
+
+def test_skill_activation_middleware_does_not_duplicate_existing_activation(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis analyze uploads/foo.csv", id="msg-1")
+    first_capture = {}
+
+    def first_handler(model_request: ModelRequest):
+        first_capture["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    first_result = middleware.wrap_model_call(_make_model_request([original]), first_handler)
+
+    assert isinstance(first_result, AIMessage)
+    activation_msg, user_msg = first_capture["messages"]
+    assert is_slash_skill_activation_reminder(activation_msg)
+
+    second_capture = {}
+
+    def second_handler(model_request: ModelRequest):
+        second_capture["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    second_result = middleware.wrap_model_call(_make_model_request([activation_msg, user_msg]), second_handler)
+
+    assert isinstance(second_result, AIMessage)
+    assert second_capture["messages"] == [activation_msg, user_msg]
+    assert sum(is_slash_skill_activation_reminder(message) for message in second_capture["messages"]) == 1
+
+
+def test_skill_activation_middleware_does_not_duplicate_activation_separated_by_hidden_context(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis analyze uploads/foo.csv", id="msg-1")
+    first_capture = {}
+
+    def first_handler(model_request: ModelRequest):
+        first_capture["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    middleware.wrap_model_call(_make_model_request([original]), first_handler)
+    activation_msg, user_msg = first_capture["messages"]
+    hidden_context = HumanMessage(content="dynamic context", additional_kwargs={"hide_from_ui": True})
+    second_capture = {}
+
+    def second_handler(model_request: ModelRequest):
+        second_capture["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    second_result = middleware.wrap_model_call(_make_model_request([activation_msg, hidden_context, user_msg]), second_handler)
+
+    assert isinstance(second_result, AIMessage)
+    assert second_capture["messages"] == [activation_msg, hidden_context, user_msg]
+    assert sum(is_slash_skill_activation_reminder(message) for message in second_capture["messages"]) == 1
+
+
+def test_skill_activation_middleware_dedupes_immediately_previous_activation_without_target_id(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    legacy_activation_msg = SkillActivationMiddleware._make_activation_message(
+        HumanMessage(content="/data-analysis analyze uploads/foo.csv"),
+        "existing activation context",
+    )
+    target = HumanMessage(content="/data-analysis analyze uploads/foo.csv", id="msg-1")
+    captured = {}
+
+    def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(_make_model_request([legacy_activation_msg, target]), handler)
+
+    assert isinstance(result, AIMessage)
+    assert captured["messages"] == [legacy_activation_msg, target]
+    assert sum(is_slash_skill_activation_reminder(message) for message in captured["messages"]) == 1
+
+
+def test_skill_activation_middleware_async_injects_hidden_human_context_for_model_call(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis analyze uploads/foo.csv", id="msg-1")
+    request = _make_model_request([original])
+    captured = {}
+
+    async def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = asyncio.run(middleware.awrap_model_call(request, handler))
+
+    assert isinstance(result, AIMessage)
+    assert result.content == "ok"
+    activation_msg, user_msg = captured["messages"]
+    assert is_slash_skill_activation_reminder(activation_msg)
+    assert activation_msg.additional_kwargs["hide_from_ui"] is True
+    assert "Use pandas." in activation_msg.content
+    assert "<user_request>\nanalyze uploads/foo.csv\n</user_request>" in activation_msg.content
+    assert user_msg.content == original.content
+    assert request.state["messages"] == [original]
+
+
+def test_skill_activation_middleware_uses_fallback_when_task_text_is_empty(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis", id="msg-1")
+    captured = {}
+
+    def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(_make_model_request([original]), handler)
+
+    assert isinstance(result, AIMessage)
+    activation_msg = captured["messages"][0]
+    assert "No additional task text was provided after the slash skill command." in activation_msg.content
+
+
+def test_skill_activation_middleware_uses_original_user_content_when_uploads_are_injected(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(
+        content="<uploaded_files>\n- report.pdf\n</uploaded_files>\n\n/data-analysis 分析这个文档",
+        id="msg-1",
+        additional_kwargs={ORIGINAL_USER_CONTENT_KEY: "/data-analysis 分析这个文档"},
+    )
+    captured = {}
+
+    def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(_make_model_request([original]), handler)
+
+    assert isinstance(result, AIMessage)
+    assert result.content == "ok"
+    activation_msg, user_msg = captured["messages"]
+    assert is_slash_skill_activation_reminder(activation_msg)
+    assert "Use pandas." in activation_msg.content
+    assert "<user_request>\n分析这个文档\n</user_request>" in activation_msg.content
+    assert user_msg.content == original.content
+    assert user_msg.additional_kwargs[ORIGINAL_USER_CONTENT_KEY] == "/data-analysis 分析这个文档"
+
+
+def test_skill_activation_middleware_activates_from_list_content(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content=[{"type": "text", "text": "/data-analysis analyze uploads/foo.csv"}], id="msg-1")
+    captured = {}
+
+    def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(_make_model_request([original]), handler)
+
+    assert isinstance(result, AIMessage)
+    activation_msg, user_msg = captured["messages"]
+    assert is_slash_skill_activation_reminder(activation_msg)
+    assert "<user_request>\nanalyze uploads/foo.csv\n</user_request>" in activation_msg.content
+    assert user_msg.content == original.content
+
+
+def test_skill_activation_middleware_records_activation_audit_event(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    recorded = []
+    journal = SimpleNamespace(record_middleware=lambda *args, **kwargs: recorded.append((args, kwargs)))
+    runtime = SimpleNamespace(context={"__run_journal": journal})
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis analyze uploads/foo.csv", id="msg-1")
+
+    def handler(model_request: ModelRequest):
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(_make_model_request([original], runtime=runtime), handler)
+
+    assert isinstance(result, AIMessage)
+    assert len(recorded) == 1
+    args, kwargs = recorded[0]
+    assert args == ("skill_activation",)
+    assert kwargs["name"] == "SkillActivationMiddleware"
+    assert kwargs["hook"] == "wrap_model_call"
+    assert kwargs["action"] == "activate"
+    assert kwargs["changes"] == {
+        "skill_name": "data-analysis",
+        "category": "custom",
+        "path": "/mnt/skills/custom/data-analysis/SKILL.md",
+        "content_hash": hashlib.sha256(b"# Data Analysis\nUse pandas.").hexdigest(),
+    }
+
+
+def test_skill_activation_middleware_async_records_activation_audit_event(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    recorded = []
+    journal = SimpleNamespace(record_middleware=lambda *args, **kwargs: recorded.append((args, kwargs)))
+    runtime = SimpleNamespace(context={"__run_journal": journal})
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis analyze uploads/foo.csv", id="msg-1")
+
+    async def handler(model_request: ModelRequest):
+        return AIMessage(content="ok")
+
+    result = asyncio.run(middleware.awrap_model_call(_make_model_request([original], runtime=runtime), handler))
+
+    assert isinstance(result, AIMessage)
+    assert len(recorded) == 1
+    args, kwargs = recorded[0]
+    assert args == ("skill_activation",)
+    assert kwargs["hook"] == "awrap_model_call"
+    assert kwargs["changes"]["skill_name"] == "data-analysis"
+    assert kwargs["changes"]["content_hash"] == hashlib.sha256(b"# Data Analysis\nUse pandas.").hexdigest()
+
+
+def test_skill_activation_middleware_ignores_activation_audit_errors(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    journal = SimpleNamespace(record_middleware=lambda *args, **kwargs: (_ for _ in ()).throw(RuntimeError("db down")))
+    runtime = SimpleNamespace(context={"__run_journal": journal})
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis analyze uploads/foo.csv", id="msg-1")
+
+    def handler(model_request: ModelRequest):
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(_make_model_request([original], runtime=runtime), handler)
+
+    assert isinstance(result, AIMessage)
+    assert result.content == "ok"
+
+
+def test_skill_activation_middleware_activates_only_latest_real_user_message(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    old_slash = HumanMessage(content="/data-analysis old request", id="msg-1")
+    latest_user = HumanMessage(content="continue normally", id="msg-2")
+    request = _make_model_request([old_slash, AIMessage(content="done"), latest_user])
+    captured = {}
+
+    def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(request, handler)
+
+    assert isinstance(result, AIMessage)
+    assert captured["messages"] == request.messages
+    assert not any(is_slash_skill_activation_reminder(message) for message in captured["messages"])
+
+
+def test_skill_activation_middleware_ignores_hidden_and_summary_user_messages(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis", content="# Data Analysis\nUse pandas.")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    real_user = HumanMessage(content="continue normally", id="msg-1")
+    hidden_slash = HumanMessage(content="/data-analysis hidden request", id="msg-2", additional_kwargs={"hide_from_ui": True})
+    summary_slash = HumanMessage(content="/data-analysis summary request", id="msg-3", name="summary")
+    request = _make_model_request([real_user, hidden_slash, summary_slash])
+    captured = {}
+
+    def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(request, handler)
+
+    assert isinstance(result, AIMessage)
+    assert captured["messages"] == request.messages
+    assert not any(is_slash_skill_activation_reminder(message) for message in captured["messages"])
+
+
+def test_skill_activation_middleware_returns_clear_error_for_disallowed_skill(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware(available_skills={"frontend-design"})
+    original = HumanMessage(content="/data-analysis run")
+
+    def handler(model_request: ModelRequest):
+        raise AssertionError("handler should not be called for invalid slash skills")
+
+    result = middleware.wrap_model_call(_make_model_request([original]), handler)
+
+    assert isinstance(result, AIMessage)
+    assert "not available for this agent" in result.content
+
+
+def test_skill_activation_middleware_returns_clear_error_for_missing_skill(monkeypatch, tmp_path):
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, []))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis run")
+
+    def handler(model_request: ModelRequest):
+        raise AssertionError("handler should not be called for missing slash skills")
+
+    result = middleware.wrap_model_call(_make_model_request([original]), handler)
+
+    assert isinstance(result, AIMessage)
+    assert "not installed" in result.content
+
+
+def test_skill_activation_middleware_returns_clear_error_for_disabled_skill(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis")
+    skill.enabled = False
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis run")
+
+    def handler(model_request: ModelRequest):
+        raise AssertionError("handler should not be called for disabled slash skills")
+
+    result = middleware.wrap_model_call(_make_model_request([original]), handler)
+
+    assert isinstance(result, AIMessage)
+    assert "installed but disabled" in result.content
+
+
+def test_skill_activation_middleware_escapes_activation_content(monkeypatch, tmp_path):
+    skill = _make_skill(
+        tmp_path,
+        "data-analysis",
+        content="# Data Analysis\nUse <xml> & avoid </skill> collisions.\n----- END SKILL.md -----",
+    )
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+    original = HumanMessage(content="/data-analysis analyze </user_request>")
+    captured = {}
+
+    def handler(model_request: ModelRequest):
+        captured["messages"] = model_request.messages
+        return AIMessage(content="ok")
+
+    result = middleware.wrap_model_call(_make_model_request([original]), handler)
+
+    assert isinstance(result, AIMessage)
+    activation_msg = captured["messages"][0]
+    assert '<skill_content encoding="xml-escaped">' in activation_msg.content
+    assert "analyze &lt;/user_request&gt;" in activation_msg.content
+    assert "Use &lt;xml&gt; &amp; avoid &lt;/skill&gt; collisions." in activation_msg.content
+    assert "----- BEGIN SKILL.md -----" not in activation_msg.content
+
+
+def test_skill_activation_middleware_rejects_skill_file_outside_skills_root(monkeypatch, tmp_path):
+    skills_root = tmp_path / "skills"
+    skill_dir = skills_root / "custom" / "data-analysis"
+    skill_dir.mkdir(parents=True)
+    outside_dir = tmp_path / "outside"
+    outside_dir.mkdir()
+    outside_file = outside_dir / "SKILL.md"
+    outside_file.write_text("# Leaked\nDo not read me.", encoding="utf-8")
+    (skill_dir / "SKILL.md").symlink_to(outside_file)
+    skill = Skill(
+        name="data-analysis",
+        description="Description for data-analysis",
+        license="MIT",
+        skill_dir=skill_dir,
+        skill_file=skill_dir / "SKILL.md",
+        relative_path=Path("data-analysis"),
+        category=SkillCategory.CUSTOM,
+        enabled=True,
+    )
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(skills_root, [skill]))
+
+    middleware = SkillActivationMiddleware()
+
+    def handler(model_request: ModelRequest):
+        raise AssertionError("handler should not be called when SKILL.md fails safety checks")
+
+    result = middleware.wrap_model_call(_make_model_request([HumanMessage(content="/data-analysis run")]), handler)
+
+    assert isinstance(result, AIMessage)
+    assert "could not be loaded safely" in result.content
+
+
+def test_skill_activation_middleware_reports_missing_skill_file_safely(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis")
+    skill.skill_file.unlink()
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+
+    def handler(model_request: ModelRequest):
+        raise AssertionError("handler should not be called when SKILL.md is missing")
+
+    result = middleware.wrap_model_call(_make_model_request([HumanMessage(content="/data-analysis run")]), handler)
+
+    assert isinstance(result, AIMessage)
+    assert "could not be loaded safely" in result.content
+
+
+def test_skill_activation_middleware_reports_invalid_utf8_skill_file_safely(monkeypatch, tmp_path):
+    skill = _make_skill(tmp_path, "data-analysis")
+    skill.skill_file.write_bytes(b"\xff\xfe\x00")
+    monkeypatch.setattr(middleware_module, "get_or_new_skill_storage", lambda **kwargs: _make_storage(tmp_path, [skill]))
+
+    middleware = SkillActivationMiddleware()
+
+    def handler(model_request: ModelRequest):
+        raise AssertionError("handler should not be called when SKILL.md is not valid UTF-8")
+
+    result = middleware.wrap_model_call(_make_model_request([HumanMessage(content="/data-analysis run")]), handler)
+
+    assert isinstance(result, AIMessage)
+    assert "could not be loaded safely" in result.content

backend/tests/test_uploads_middleware_core_logic.py

@@ -14,6 +14,7 @@ from langchain_core.messages import AIMessage, HumanMessage
 
 from deerflow.agents.middlewares.uploads_middleware import UploadsMiddleware
 from deerflow.config.paths import Paths
+from deerflow.utils.messages import ORIGINAL_USER_CONTENT_KEY
 
 THREAD_ID = "thread-abc123"
 
@@ -263,6 +264,22 @@ class TestBeforeAgent:
         assert "<uploaded_files>" in combined_text
         assert "analyse this" in combined_text
 
+    def test_list_content_preserves_original_slash_skill_text(self, tmp_path):
+        mw = _middleware(tmp_path)
+        uploads_dir = _uploads_dir(tmp_path)
+        (uploads_dir / "data.csv").write_bytes(b"a,b")
+
+        msg = _human(
+            [{"type": "text", "text": "/data-analysis analyze data.csv"}],
+            files=[{"filename": "data.csv", "size": 3, "path": "/mnt/user-data/uploads/data.csv"}],
+        )
+        result = mw.before_agent(self._state(msg), _runtime())
+
+        assert result is not None
+        updated_msg = result["messages"][-1]
+        assert isinstance(updated_msg.content, list)
+        assert updated_msg.additional_kwargs[ORIGINAL_USER_CONTENT_KEY] == "/data-analysis analyze data.csv"
+
     def test_preserves_additional_kwargs_on_updated_message(self, tmp_path):
         mw = _middleware(tmp_path)
         uploads_dir = _uploads_dir(tmp_path)
@@ -278,6 +295,37 @@ class TestBeforeAgent:
         assert updated_kwargs.get("files") == files_meta
         assert updated_kwargs.get("element") == "task"
 
+    def test_preserves_original_user_content_before_upload_context(self, tmp_path):
+        mw = _middleware(tmp_path)
+        uploads_dir = _uploads_dir(tmp_path)
+        (uploads_dir / "report.pdf").write_bytes(b"pdf")
+
+        msg = _human(
+            "/data-analysis 分析这个文档",
+            files=[{"filename": "report.pdf", "size": 3, "path": "/mnt/user-data/uploads/report.pdf"}],
+        )
+        result = mw.before_agent(self._state(msg), _runtime())
+
+        assert result is not None
+        updated_msg = result["messages"][-1]
+        assert updated_msg.content.startswith("<uploaded_files>")
+        assert updated_msg.additional_kwargs[ORIGINAL_USER_CONTENT_KEY] == "/data-analysis 分析这个文档"
+
+    def test_preserves_existing_original_user_content_marker(self, tmp_path):
+        mw = _middleware(tmp_path)
+        uploads_dir = _uploads_dir(tmp_path)
+        (uploads_dir / "report.pdf").write_bytes(b"pdf")
+
+        msg = _human(
+            "<uploaded_files>\nold\n</uploaded_files>\n\n/data-analysis run",
+            files=[{"filename": "report.pdf", "size": 3, "path": "/mnt/user-data/uploads/report.pdf"}],
+            **{ORIGINAL_USER_CONTENT_KEY: "/data-analysis run"},
+        )
+        result = mw.before_agent(self._state(msg), _runtime())
+
+        assert result is not None
+        assert result["messages"][-1].additional_kwargs[ORIGINAL_USER_CONTENT_KEY] == "/data-analysis run"
+
     def test_uploaded_files_returned_in_state_update(self, tmp_path):
         mw = _middleware(tmp_path)
         uploads_dir = _uploads_dir(tmp_path)

frontend/eslint.config.js

@@ -9,6 +9,8 @@ export default tseslint.config(
   {
     ignores: [
       ".next",
+      "playwright-report",
+      "test-results",
       "src/components/ui/**",
       "src/components/ai-elements/**",
       "*.js",

frontend/src/components/ai-elements/prompt-input.tsx

@@ -881,6 +881,7 @@ export type PromptInputTextareaProps = ComponentProps<
 
 export const PromptInputTextarea = ({
   onChange,
+  onKeyDown,
   className,
   placeholder = "What would you like to know?",
   ...props
@@ -891,6 +892,10 @@ export const PromptInputTextarea = ({
   const [isComposing, setIsComposing] = useState(false);
 
   const handleKeyDown: KeyboardEventHandler<HTMLTextAreaElement> = (e) => {
+    onKeyDown?.(e);
+    if (e.defaultPrevented) {
+      return;
+    }
     if (e.key === "Enter") {
       if (isIMEComposing(e, isComposing)) {
         return;

frontend/src/components/workspace/input-box.tsx

@@ -20,6 +20,7 @@ import {
   useRef,
   useState,
   type ComponentProps,
+  type KeyboardEvent,
 } from "react";
 
 import {
@@ -59,6 +60,8 @@ import { fetch } from "@/core/api/fetcher";
 import { getBackendBaseURL } from "@/core/config";
 import { useI18n } from "@/core/i18n/hooks";
 import { useModels } from "@/core/models/hooks";
+import type { Skill } from "@/core/skills";
+import { useSkills } from "@/core/skills/hooks";
 import type { AgentThreadContext } from "@/core/threads";
 import { textOfMessage } from "@/core/threads/utils";
 import { cn } from "@/lib/utils";
@@ -86,6 +89,48 @@ import { Tooltip } from "./tooltip";
 
 type InputMode = "flash" | "thinking" | "pro" | "ultra";
 
+const MAX_SKILL_SUGGESTIONS = 6;
+
+function getLeadingSlashSkillQuery(value: string): string | null {
+  if (!value.startsWith("/")) {
+    return null;
+  }
+
+  const query = value.slice(1);
+  if (query.includes("/") || /\s/.test(query)) {
+    return null;
+  }
+
+  return query;
+}
+
+function getMatchingSkillSuggestions(skills: Skill[], query: string): Skill[] {
+  const normalizedQuery = query.toLowerCase();
+
+  return skills
+    .map((skill, index) => ({
+      skill,
+      index,
+      name: skill.name.toLowerCase(),
+    }))
+    .filter(({ skill, name }) => {
+      if (!skill.enabled) {
+        return false;
+      }
+      return !normalizedQuery || name.includes(normalizedQuery);
+    })
+    .sort((a, b) => {
+      const aStartsWith = a.name.startsWith(normalizedQuery);
+      const bStartsWith = b.name.startsWith(normalizedQuery);
+      if (aStartsWith !== bStartsWith) {
+        return aStartsWith ? -1 : 1;
+      }
+      return a.index - b.index;
+    })
+    .slice(0, MAX_SKILL_SUGGESTIONS)
+    .map(({ skill }) => skill);
+}
+
 function getResolvedMode(
   mode: InputMode | undefined,
   supportsThinking: boolean,
@@ -153,11 +198,17 @@ export function InputBox({
   const { models } = useModels();
   const { thread, isMock } = useThread();
   const { textInput } = usePromptInputController();
+  const { skills } = useSkills();
   const promptRootRef = useRef<HTMLDivElement | null>(null);
+  const textareaRef = useRef<HTMLTextAreaElement | null>(null);
 
   const [followups, setFollowups] = useState<string[]>([]);
   const [followupsHidden, setFollowupsHidden] = useState(false);
   const [followupsLoading, setFollowupsLoading] = useState(false);
+  const [textareaFocused, setTextareaFocused] = useState(false);
+  const [skillSuggestionIndex, setSkillSuggestionIndex] = useState(0);
+  const [dismissedSkillSuggestionValue, setDismissedSkillSuggestionValue] =
+    useState<string | null>(null);
   const lastGeneratedForAiIdRef = useRef<string | null>(null);
   const wasStreamingRef = useRef(false);
   const messagesRef = useRef(thread.messages);
@@ -347,9 +398,98 @@ export function InputBox({
     setTimeout(() => requestFormSubmit(), 0);
   }, [pendingSuggestion, requestFormSubmit, textInput]);
 
+  const slashSkillQuery = useMemo(
+    () => getLeadingSlashSkillQuery(textInput.value ?? ""),
+    [textInput.value],
+  );
+  const skillSuggestions = useMemo(
+    () =>
+      slashSkillQuery === null
+        ? []
+        : getMatchingSkillSuggestions(skills, slashSkillQuery),
+    [skills, slashSkillQuery],
+  );
+  const showSkillSuggestions =
+    !disabled &&
+    textareaFocused &&
+    slashSkillQuery !== null &&
+    skillSuggestions.length > 0 &&
+    dismissedSkillSuggestionValue !== textInput.value;
+
+  useEffect(() => {
+    setSkillSuggestionIndex(0);
+  }, [slashSkillQuery, skillSuggestions.length]);
+
+  const applySkillSuggestion = useCallback(
+    (skill: Skill) => {
+      const nextValue = `/${skill.name} `;
+      textInput.setInput(nextValue);
+      setDismissedSkillSuggestionValue(nextValue);
+      requestAnimationFrame(() => {
+        const textarea = textareaRef.current;
+        if (!textarea) {
+          return;
+        }
+        textarea.focus();
+        textarea.setSelectionRange(nextValue.length, nextValue.length);
+      });
+    },
+    [textInput],
+  );
+
+  const handleSkillSuggestionKeyDown = useCallback(
+    (event: KeyboardEvent<HTMLTextAreaElement>) => {
+      if (!showSkillSuggestions) {
+        return;
+      }
+
+      if (event.key === "ArrowDown") {
+        event.preventDefault();
+        setSkillSuggestionIndex(
+          (index) => (index + 1) % skillSuggestions.length,
+        );
+        return;
+      }
+
+      if (event.key === "ArrowUp") {
+        event.preventDefault();
+        setSkillSuggestionIndex(
+          (index) =>
+            (index - 1 + skillSuggestions.length) % skillSuggestions.length,
+        );
+        return;
+      }
+
+      if (event.key === "Enter" || event.key === "Tab") {
+        if (event.shiftKey) {
+          return;
+        }
+        event.preventDefault();
+        const selectedSkill = skillSuggestions[skillSuggestionIndex];
+        if (selectedSkill) {
+          applySkillSuggestion(selectedSkill);
+        }
+        return;
+      }
+
+      if (event.key === "Escape") {
+        event.preventDefault();
+        setDismissedSkillSuggestionValue(textInput.value);
+      }
+    },
+    [
+      applySkillSuggestion,
+      showSkillSuggestions,
+      skillSuggestionIndex,
+      skillSuggestions,
+      textInput.value,
+    ],
+  );
+
   const showFollowups =
     !disabled &&
     !isWelcomeMode &&
+    !showSkillSuggestions &&
     !followupsHidden &&
     (followupsLoading || followups.length > 0);
 
@@ -478,6 +618,48 @@ export function InputBox({
           </div>
         </div>
       )}
+      {showSkillSuggestions && (
+        <div className="absolute right-0 bottom-full left-0 z-40 mb-2 px-1">
+          <div
+            aria-label="Skill suggestions"
+            className="bg-popover/95 text-popover-foreground border-border max-h-72 overflow-y-auto rounded-xl border p-1 shadow-lg backdrop-blur-sm"
+            role="listbox"
+          >
+            {skillSuggestions.map((skill, index) => {
+              const selected = index === skillSuggestionIndex;
+              return (
+                <button
+                  aria-selected={selected}
+                  className={cn(
+                    "flex min-h-12 w-full min-w-0 cursor-pointer items-center gap-3 rounded-lg px-3 py-2 text-left transition-colors",
+                    selected
+                      ? "bg-accent text-accent-foreground"
+                      : "text-popover-foreground hover:bg-accent/70 hover:text-accent-foreground",
+                  )}
+                  key={skill.name}
+                  onClick={() => applySkillSuggestion(skill)}
+                  onMouseDown={(event) => event.preventDefault()}
+                  onMouseEnter={() => setSkillSuggestionIndex(index)}
+                  role="option"
+                  type="button"
+                >
+                  <SparklesIcon className="text-muted-foreground size-4 shrink-0" />
+                  <span className="min-w-0 flex-1">
+                    <span className="block truncate text-sm font-medium">
+                      /{skill.name}
+                    </span>
+                    {skill.description && (
+                      <span className="text-muted-foreground block truncate text-xs">
+                        {skill.description}
+                      </span>
+                    )}
+                  </span>
+                </button>
+              );
+            })}
+          </div>
+        </div>
+      )}
       <PromptInput
         className={cn(
           "bg-background/85 rounded-2xl backdrop-blur-sm transition-all duration-300 ease-out *:data-[slot='input-group']:rounded-2xl",
@@ -506,6 +688,10 @@ export function InputBox({
             placeholder={t.inputBox.placeholder}
             autoFocus={autoFocus}
             defaultValue={initialValue}
+            onBlur={() => setTextareaFocused(false)}
+            onFocus={() => setTextareaFocused(true)}
+            onKeyDown={handleSkillSuggestionKeyDown}
+            ref={textareaRef}
           />
         </PromptInputBody>
         <PromptInputFooter className="flex">
@@ -860,11 +1046,13 @@ export function InputBox({
         )}
       </PromptInput>
 
-      {isWelcomeMode && searchParams.get("mode") !== "skill" && (
+      {isWelcomeMode &&
-        <div className="flex items-center justify-center pt-2">
+        searchParams.get("mode") !== "skill" &&
-          <SuggestionList />
+        !showSkillSuggestions && (
-        </div>
+          <div className="flex items-center justify-center pt-2">
-      )}
+            <SuggestionList />
+          </div>
+        )}
 
       <Dialog open={confirmOpen} onOpenChange={setConfirmOpen}>
         <DialogContent>

frontend/src/core/messages/utils.ts

@@ -469,10 +469,14 @@ export function findToolCallResult(toolCallId: string, messages: Message[]) {
 }
 
 export function isHiddenFromUIMessage(message: Message) {
+  const content = extractTextFromMessage(message);
   return (
     message.additional_kwargs?.hide_from_ui === true ||
     (typeof message.name === "string" &&
-      HIDDEN_CONTROL_MESSAGE_NAMES.has(message.name))
+      HIDDEN_CONTROL_MESSAGE_NAMES.has(message.name)) ||
+    (message.type === "human" &&
+      content.includes("<slash_skill_activation>") &&
+      stripUploadedFilesTag(content).length === 0)
   );
 }
 
@@ -488,12 +492,13 @@ export interface FileInMessage {
 }
 
 /**
- * Strip <uploaded_files> tag from message content.
+ * Strip backend-injected human context tags from message content.
- * Returns the content with the tag removed.
+ * Kept under its historical name because callers use it for uploaded-file
+ * display cleanup.
  */
 export function stripUploadedFilesTag(content: string): string {
   return content
-    .replace(/<uploaded_files>[\s\S]*?<\/uploaded_files>/g, "")
+    .replace(/<(uploaded_files|slash_skill_activation)>[\s\S]*?<\/\1>/g, "")
     .trim();
 }
 
@@ -504,6 +509,7 @@ export function stripUploadedFilesTag(content: string): string {
  * These markers are *not* user copy — they come from:
  *
  * - ``UploadsMiddleware`` → ``<uploaded_files>``
+ * - ``SkillActivationMiddleware`` → ``<slash_skill_activation>``
  * - ``DynamicContextMiddleware`` → ``<system-reminder>`` (carrying
  *   ``<memory>`` / ``<current_date>`` inside)
  * - ``TodoListMiddleware`` / ``LoopDetectionMiddleware`` style reminders
@@ -517,6 +523,7 @@ export function stripUploadedFilesTag(content: string): string {
  */
 export const INTERNAL_MARKER_TAGS = [
   "uploaded_files",
+  "slash_skill_activation",
   "system-reminder",
   "memory",
   "current_date",

frontend/tests/e2e/chat.spec.ts

@@ -24,6 +24,61 @@ test.describe("Chat workspace", () => {
     await expect(textarea).toHaveValue("Hello, DeerFlow!");
   });
 
+  test("suggests matching skills after a leading slash", async ({ page }) => {
+    await page.goto("/workspace/chats/new");
+
+    const textarea = page.getByPlaceholder(/how can i assist you/i);
+    await expect(textarea).toBeVisible({ timeout: 15_000 });
+
+    await textarea.fill("/dat");
+    await expect(
+      page.getByRole("option", { name: /data-analysis/i }),
+    ).toBeVisible();
+    await expect(
+      page.getByRole("option", { name: /disabled-skill/i }),
+    ).toBeHidden();
+
+    await textarea.press("Enter");
+
+    await expect(textarea).toHaveValue("/data-analysis ");
+  });
+
+  test("keeps Shift+Enter as newline while skill suggestions are visible", async ({
+    page,
+  }) => {
+    await page.goto("/workspace/chats/new");
+
+    const textarea = page.getByPlaceholder(/how can i assist you/i);
+    await expect(textarea).toBeVisible({ timeout: 15_000 });
+
+    await textarea.fill("/dat");
+    await expect(
+      page.getByRole("option", { name: /data-analysis/i }),
+    ).toBeVisible();
+
+    await textarea.press("Shift+Enter");
+
+    await expect(textarea).toHaveValue("/dat\n");
+    await expect(
+      page.getByRole("option", { name: /data-analysis/i }),
+    ).toBeHidden();
+  });
+
+  test("does not suggest skills for slash text away from the prompt start", async ({
+    page,
+  }) => {
+    await page.goto("/workspace/chats/new");
+
+    const textarea = page.getByPlaceholder(/how can i assist you/i);
+    await expect(textarea).toBeVisible({ timeout: 15_000 });
+
+    await textarea.fill("please /dat");
+
+    await expect(
+      page.getByRole("option", { name: /data-analysis/i }),
+    ).toBeHidden();
+  });
+
   test("sending a message triggers API call and shows response", async ({
     page,
   }) => {
@@ -49,6 +104,150 @@ test.describe("Chat workspace", () => {
     });
   });
 
+  test("slash skill command is submitted as normal chat text", async ({
+    page,
+  }) => {
+    const slashCommand = "/data-analysis analyze uploads/foo.csv";
+    let submittedText: string | undefined;
+    await page.route("**/runs/stream", (route) => {
+      const body = route.request().postDataJSON() as {
+        input?: { messages?: Array<{ content?: unknown }> };
+      };
+      const content = body.input?.messages?.at(-1)?.content;
+      if (typeof content === "string") {
+        submittedText = content;
+      } else if (Array.isArray(content)) {
+        submittedText = content
+          .map((block) =>
+            typeof block === "object" &&
+            block !== null &&
+            "text" in block &&
+            typeof block.text === "string"
+              ? block.text
+              : "",
+          )
+          .join("");
+      }
+      return handleRunStream(route);
+    });
+
+    await page.goto("/workspace/chats/new");
+
+    const textarea = page.getByPlaceholder(/how can i assist you/i);
+    await expect(textarea).toBeVisible({ timeout: 15_000 });
+
+    await textarea.fill(slashCommand);
+    await textarea.press("Enter");
+
+    await expect
+      .poll(() => submittedText, { timeout: 10_000 })
+      .toBe(slashCommand);
+    await expect(page.getByText("Hello from DeerFlow!")).toBeVisible({
+      timeout: 10_000,
+    });
+  });
+
+  test("slash skill command with attachment preserves command text and file metadata", async ({
+    page,
+  }) => {
+    const slashCommand = "/data-analysis analyze report.docx";
+    let uploadCalled = false;
+    let submittedText: string | undefined;
+    let submittedFiles:
+      | Array<{ filename?: string; path?: string; status?: string }>
+      | undefined;
+
+    await page.route("**/api/threads/*/uploads", async (route) => {
+      uploadCalled = true;
+      return route.fulfill({
+        status: 200,
+        contentType: "application/json",
+        body: JSON.stringify({
+          success: true,
+          message: "Uploaded",
+          files: [
+            {
+              filename: "report.docx",
+              size: 12,
+              path: "report.docx",
+              virtual_path: "/mnt/user-data/uploads/report.docx",
+              artifact_url: "/api/threads/test/uploads/report.docx",
+              extension: ".docx",
+            },
+          ],
+        }),
+      });
+    });
+
+    await page.route("**/runs/stream", (route) => {
+      const body = route.request().postDataJSON() as {
+        input?: {
+          messages?: Array<{
+            content?: unknown;
+            additional_kwargs?: {
+              files?: Array<{
+                filename?: string;
+                path?: string;
+                status?: string;
+              }>;
+            };
+          }>;
+        };
+      };
+      const message = body.input?.messages?.at(-1);
+      const content = message?.content;
+      if (typeof content === "string") {
+        submittedText = content;
+      } else if (Array.isArray(content)) {
+        submittedText = content
+          .map((block) =>
+            typeof block === "object" &&
+            block !== null &&
+            "text" in block &&
+            typeof block.text === "string"
+              ? block.text
+              : "",
+          )
+          .join("");
+      }
+      submittedFiles = message?.additional_kwargs?.files;
+      return handleRunStream(route);
+    });
+
+    await page.goto("/workspace/chats/new");
+
+    const textarea = page.getByPlaceholder(/how can i assist you/i);
+    await expect(textarea).toBeVisible({ timeout: 15_000 });
+
+    await page.getByLabel("Upload files").setInputFiles({
+      name: "report.docx",
+      mimeType:
+        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+      buffer: Buffer.from("fake docx"),
+    });
+
+    await textarea.fill(slashCommand);
+    await textarea.press("Enter");
+
+    await expect.poll(() => uploadCalled, { timeout: 10_000 }).toBeTruthy();
+    await expect
+      .poll(() => submittedText, { timeout: 10_000 })
+      .toBe(slashCommand);
+    await expect
+      .poll(() => submittedFiles, { timeout: 10_000 })
+      .toEqual([
+        {
+          filename: "report.docx",
+          size: 12,
+          path: "/mnt/user-data/uploads/report.docx",
+          status: "uploaded",
+        },
+      ]);
+    await expect(page.getByText("Hello from DeerFlow!")).toBeVisible({
+      timeout: 10_000,
+    });
+  });
+
   test("keeps attachments visible while upload submit is pending", async ({
     page,
   }) => {

frontend/tests/e2e/utils/mock-api.ts

@@ -35,11 +35,41 @@ export type MockAgent = {
   system_prompt?: string;
 };
 
+export type MockSkill = {
+  name: string;
+  description: string;
+  category?: string;
+  license?: string | null;
+  enabled?: boolean;
+};
+
 export type MockAPIOptions = {
   threads?: MockThread[];
   agents?: MockAgent[];
+  skills?: MockSkill[];
 };
 
+const DEFAULT_SKILLS: MockSkill[] = [
+  {
+    name: "data-analysis",
+    description: "Analyze structured data and produce charts.",
+    category: "public",
+    enabled: true,
+  },
+  {
+    name: "frontend-design",
+    description: "Create polished frontend interfaces.",
+    category: "public",
+    enabled: true,
+  },
+  {
+    name: "disabled-skill",
+    description: "Hidden from slash autocomplete.",
+    category: "public",
+    enabled: false,
+  },
+];
+
 // ---------------------------------------------------------------------------
 // mockLangGraphAPI
 // ---------------------------------------------------------------------------
@@ -52,6 +82,7 @@ export type MockAPIOptions = {
 export function mockLangGraphAPI(page: Page, options?: MockAPIOptions) {
   const threads = options?.threads ?? [];
   const agents = options?.agents ?? [];
+  const skills = options?.skills ?? DEFAULT_SKILLS;
 
   // Thread search — sidebar thread list & chats list page
   void page.route("**/api/langgraph/threads/search", (route) => {
@@ -259,6 +290,18 @@ export function mockLangGraphAPI(page: Page, options?: MockAPIOptions) {
     return route.fallback();
   });
 
+  // Skills list — settings page and slash autocomplete
+  void page.route("**/api/skills", (route) => {
+    if (route.request().method() === "GET") {
+      return route.fulfill({
+        status: 200,
+        contentType: "application/json",
+        body: JSON.stringify({ skills }),
+      });
+    }
+    return route.fallback();
+  });
+
   // Follow-up suggestions — input box auto-suggest after AI response
   void page.route("**/api/threads/*/suggestions", (route) => {
     if (route.request().method() === "POST") {

frontend/tests/unit/core/messages/utils.test.ts

@@ -11,6 +11,7 @@ import {
   hasContent,
   hasReasoning,
   isAssistantMessageGroupStreaming,
+  stripUploadedFilesTag,
 } from "@/core/messages/utils";
 
 function aiMessage(content: string): Message {
@@ -173,6 +174,38 @@ describe("inline <think> tag splitting", () => {
   });
 });
 
+describe("human message internal context stripping", () => {
+  test("strips slash skill activation context from display content", () => {
+    const content =
+      "<slash_skill_activation>\n<skill_content># Secret SKILL.md</skill_content>\n</slash_skill_activation>\nreal user task";
+
+    expect(stripUploadedFilesTag(content)).toBe("real user task");
+  });
+
+  test("hides leaked slash skill activation messages with no user text", () => {
+    const messages = [
+      {
+        id: "slash-activation",
+        type: "human",
+        content:
+          "<slash_skill_activation>\n<skill_content># Secret SKILL.md</skill_content>\n</slash_skill_activation>",
+      },
+      {
+        id: "ai-1",
+        type: "ai",
+        content: "Public answer",
+      },
+    ] as Message[];
+
+    const groups = getMessageGroups(messages);
+
+    expect(groups.map((group) => group.type)).toEqual(["assistant"]);
+    expect(
+      groups.flatMap((group) => group.messages).map((message) => message.id),
+    ).toEqual(["ai-1"]);
+  });
+});
+
 test("hides internal todo reminder messages from message groups", () => {
   const messages = [
     {

frontend/tests/unit/core/threads/export.test.ts

@@ -260,6 +260,22 @@ describe("formatThreadAsJSON", () => {
     expect(raw).toContain("real user text");
   });
 
+  it("strips <slash_skill_activation> as defence in depth", () => {
+    // Slash activation normally rides in a hidden HumanMessage. If a replay
+    // or state merge loses the flag, export must still not leak full SKILL.md
+    // content into a user-visible transcript.
+    const leaky = human("real user task", {
+      id: "leak-slash-skill",
+      content:
+        "<slash_skill_activation>\n<skill_content># Secret SKILL.md\nUse internal source.</skill_content>\n</slash_skill_activation>\nreal user task",
+    } as unknown as Partial<Message>);
+    const raw = formatThreadAsJSON(makeThread(), [leaky]);
+    expect(raw).not.toContain("<slash_skill_activation>");
+    expect(raw).not.toContain("Secret SKILL.md");
+    expect(raw).not.toContain("internal source");
+    expect(raw).toContain("real user task");
+  });
+
   it("sanitises tool message content when includeToolMessages is true", () => {
     const message = {
       id: "t-leak",