Guide for creating optimized Claude Code agents. Use to design a new specialized agent, a swarm sub-agent, or a multi-agent workflow. Follows the Skill → Agent (preloaded skills) → Skill orchestration pattern.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Update documentation after code changes. Scans git diff to find affected docs and updates them for consistency.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
This skill activates for:
/update-docsRead .claude/roles/documentalist.md — adopt this profile and follow all its rules.
# Default: last 5 commits. The user can specify a range.
git diff --name-only HEAD~5
Filter relevant files (ignore: tests, configs, lock files).
Two strategies, in this order:
Strategy A — Frontmatter related (priority):
# Read the frontmatter of each doc
Glob docs/**/*.md
# Look for modified files in the `related` field
Strategy B — Keyword search (fallback):
mcpServerStdio.ts changed, search for "mcp", "server", "stdio" in docsFor each potentially affected doc:
| Question | If Yes |
|---|---|
| Has the documented behavior changed? | Update required |
| Has a documented API/interface changed? | Update required |
| Only internal implementation changed? | No update needed |
| Has a new concept appeared? | Suggest /create-doc |
For each doc to modify:
last-updated in the frontmatterrelated entries are up to date (add new files if needed)If a doc has no YAML frontmatter, add it following the template from PERSONA.md.
This is a progressive migration — no need to do everything at once.
List the modifications made:
## Docs Updated
| File | Changes | Reason |
|------|---------|--------|
| docs/MCP-TOOLS-REFERENCE.md | Updated tool parameters | mcpServerStdio.ts changed |
| docs/ARCHITECTURE.md | No update needed | Internal refactor only |
/audit-docs first아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Guide for creating optimized Claude Code agents. Use to design a new specialized agent, a swarm sub-agent, or a multi-agent workflow. Follows the Skill → Agent (preloaded skills) → Skill orchestration pattern.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Anti-overengineering guide based on YAGNI. Use before adding an architectural pattern, during code review, or to challenge an overly complex implementation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Clean Architecture (Uncle Bob) guide for this project. Use when creating modules, entities, use cases, presenters, controllers, gateways, guards, services. Contains tactical patterns and structure conventions.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit documentation for duplication, staleness, language issues, and verbosity. Read-only — produces an actionable report.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Local auto-review of modified code (no GitLab/GitHub). Runs 5 sequential audits and generates a local report. Ideal for validating code before creating a MR/PR.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Clean Code (Robert C. Martin) guide to produce and challenge code that is readable, durable, simple, and consistent. Covers naming, functions, comments, smells, and refactor heuristics. Complements `/solid` (SOLID principles) and `/anti-overengineering` (YAGNI/KISS). Activate during the REFACTOR phase of the TDD cycle and during implementation self-review.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.