♻️ refactor: migrate AI Rules to Claude Code Skills (#11737)

♻️ refactor: migrate AI Rules to Claude Code Skills system

Migrate all AI Rules from .cursor/rules/ to .agents/skills/ directory:
- Move 23 skills to .agents/skills/ (main directory)
- Update symlinks: .claude/skills, .cursor/skills, .codex/skills
- Create project-overview skill from project documentation
- Add references/ subdirectories for complex skills
- Remove LobeChat references from skill descriptions
- Delete obsolete .cursor/rules/ and .claude/commands/prompts/ directories

Skills structure enables better portability and maintainability across AI tools.

CLAUDE.md

@@ -1,65 +1,68 @@
 # CLAUDE.md
 
-This document serves as a shared guideline for all team members when using Claude Code in this opensource lobe-chat(also known as lobehub) repository.
+Guidelines for using Claude Code in this LobeChat repository.
 
 ## Tech Stack
 
-read @.cursor/rules/project-introduce.mdc
+- Next.js 16 + React 19 + TypeScript
+- SPA inside Next.js with `react-router-dom`
+- `@lobehub/ui`, antd for components; antd-style for CSS-in-JS
+- react-i18next for i18n; zustand for state management
+- SWR for data fetching; TRPC for type-safe backend
+- Drizzle ORM with PostgreSQL; Vitest for testing
 
-## Directory Structure
+## Project Structure
 
-read @.cursor/rules/project-structure.mdc
+```
+lobe-chat/
+├── apps/desktop/           # Electron desktop app
+├── packages/               # Shared packages (@lobechat/*)
+│   ├── database/           # Database schemas, models, repositories
+│   ├── agent-runtime/      # Agent runtime
+│   └── ...
+├── src/
+│   ├── app/                # Next.js app router
+│   ├── store/              # Zustand stores
+│   ├── services/           # Client services
+│   ├── server/             # Server services and routers
+│   └── ...
+└── e2e/                    # E2E tests (Cucumber + Playwright)
+```
 
 ## Development
 
 ### Git Workflow
 
-- use rebase for git pull
-- git commit message should prefix with gitmoji
-- git branch name format template: <type>/<feature-name>
-- use .github/PULL_REQUEST_TEMPLATE.md to generate pull request description
-- PR titles starting with `✨ feat/` or `🐛 fix` will trigger the release workflow upon merge. Only use these prefixes for significant user-facing feature changes or bug fixes
+- Use rebase for `git pull`
+- Commit messages: prefix with gitmoji
+- Branch format: `<type>/<feature-name>`
+- PR titles with `✨ feat/` or `🐛 fix` trigger releases
 
 ### Package Management
 
-This repository adopts a monorepo structure.
-
-- Use `pnpm` as the primary package manager for dependency management
-- Use `bun` to run npm scripts
-- Use `bunx` to run executable npm packages
-
-### TypeScript Code Style Guide
-
-see @.cursor/rules/typescript.mdc
-
-### Code Comments
-
-- **Avoid meaningless comments**: Do not write comments that merely restate what the code does. Comments should explain _why_ something is done, not _what_ is being done. The code itself should be self-explanatory.
+- `pnpm` for dependency management
+- `bun` to run npm scripts
+- `bunx` for executable npm packages
 
 ### Testing
 
-- **Required Rule**: read `.cursor/rules/testing-guide/testing-guide.mdc` before writing tests
-- **Command**:
-  - web: `bunx vitest run --silent='passed-only' '[file-path-pattern]'`
-  - packages(eg: database): `cd packages/database && bunx vitest run --silent='passed-only' '[file-path-pattern]'`
+```bash
+# Run specific test (NEVER run `bun run test` - takes ~10 minutes)
+bunx vitest run --silent='passed-only' '[file-path]'
 
-**Important**:
+# Database package
+cd packages/database && bunx vitest run --silent='passed-only' '[file]'
+```
 
-- wrap the file path in single quotes to avoid shell expansion
-- Never run `bun run test` etc to run tests, this will run all tests and cost about 10mins
-- If trying to fix the same test twice, but still failed, stop and ask for help.
-- **Prefer `vi.spyOn` over `vi.mock`**: When mocking modules or functions, prefer using `vi.spyOn` to mock specific functions rather than `vi.mock` to mock entire modules. This approach is more targeted, easier to maintain, and allows for better control over mock behavior in individual tests.
-- **Tests must pass type check**: After writing or modifying tests, run `bun run type-check` to ensure there are no type errors. Tests should pass both runtime execution and TypeScript type checking.
-
-### Typecheck
-
-- use `bun run type-check` to check type errors.
+- Prefer `vi.spyOn` over `vi.mock`
+- Tests must pass type check: `bun run type-check`
+- After 2 failed fix attempts, stop and ask for help
 
 ### i18n
 
-- **Keys**: Add to `src/locales/default/namespace.ts`
-- **Dev**: Translate `locales/zh-CN/namespace.json` and `locales/en-US/namespace.json` locales file only for dev preview
-- DON'T run `pnpm i18n`, let CI auto handle it
+- Add keys to `src/locales/default/namespace.ts`
+- For dev preview: translate `locales/zh-CN/` and `locales/en-US/`
+- Don't run `pnpm i18n` - CI handles it
 
 ## Linear Issue Management
 
@@ -72,9 +75,9 @@ see @.cursor/rules/typescript.mdc
 **Workflow:**
 
 1. Use `ToolSearch` to confirm `linear-server` MCP exists (search `linear` or `mcp__linear-server__`)
-2. If found, read `.cursor/rules/linear.mdc` and follow the workflow
+2. If found, read `.agents/skills/linear/SKILL.md` and follow the workflow
 3. If not found, skip Linear integration (treat as not installed)
 
-## Rules Index
+## Skills (Auto-loaded by Claude)
 
-Some useful project rules are listed in @.cursor/rules/rules-index.mdc
+Claude Code automatically loads relevant skills from `.agents/skills/`.