Enhance MCP development features and introduce skills management

- Added configuration options for requiring human approval before applying LLM-generated MCP patches.
- Updated Docker setup to include skills directory.
- Integrated skills management into the backend, allowing for procedural guides and skill matching.
- Refactored database initialization to apply Alembic migrations.
- Enhanced task approval process to handle MCP patch applications with optional approval.
- Introduced new schemas for skills and updated existing APIs to support skills functionality.

This commit lays the groundwork for improved agent capabilities and better management of MCP development processes.

backend/app/schemas.py

@@ -313,3 +313,34 @@ class TroubleshootingRulesOut(BaseModel):
     yaml: str
     parsed: dict[str, Any]
     path_hint: str
+
+
+# ---- Agent skills -----------------------------------------------------
+class SkillSummaryOut(BaseModel):
+    id: str
+    name: str
+    description: str
+    priority: int
+    rule_ids: list[str]
+    match: dict[str, Any]
+    path_hint: str
+
+
+class SkillsListOut(BaseModel):
+    skills: list[SkillSummaryOut]
+    path_hint: str
+
+
+class SkillOut(BaseModel):
+    id: str
+    name: str
+    description: str
+    priority: int
+    rule_ids: list[str]
+    match: dict[str, Any]
+    markdown: str
+    path_hint: str
+
+
+class SkillUpdate(BaseModel):
+    markdown: str