Implement skill self-evolution and skill_manage flow (#1874)

* chore: ignore .worktrees directory

* Add skill_manage self-evolution flow

* Fix CI regressions for skill_manage

* Address PR review feedback for skill evolution

* fix(skill-evolution): preserve history on delete

* fix(skill-evolution): tighten scanner fallbacks

* docs: add skill_manage e2e evidence screenshot

* fix(skill-manage): avoid blocking fs ops in session runtime

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

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

@@ -55,7 +55,7 @@ def load_skills(skills_path: Path | None = None, use_config: bool = True, enable
     if not skills_path.exists():
         return []
 
-    skills = []
+    skills_by_name: dict[str, Skill] = {}
 
     # Scan public and custom directories
     for category in ["public", "custom"]:
@@ -74,7 +74,9 @@ def load_skills(skills_path: Path | None = None, use_config: bool = True, enable
 
             skill = parse_skill_file(skill_file, category=category, relative_path=relative_path)
             if skill:
-                skills.append(skill)
+                skills_by_name[skill.name] = skill
+
+    skills = list(skills_by_name.values())
 
     # Load skills state configuration and update enabled status
     # NOTE: We use ExtensionsConfig.from_file() instead of get_extensions_config()