librarian
Specialized codebase understanding agent for external library research. Finding implementation examples, official documentation, open-source patterns using GitHub CLI and web search. Use when working with unfamiliar packages, asking 'How do I use X?', 'Why does Y behave this way?'. (Librarian - oh-my-opencode port)
Best use case
librarian is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Specialized codebase understanding agent for external library research. Finding implementation examples, official documentation, open-source patterns using GitHub CLI and web search. Use when working with unfamiliar packages, asking 'How do I use X?', 'Why does Y behave this way?'. (Librarian - oh-my-opencode port)
Teams using librarian should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/librarian/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How librarian Compares
| Feature / Agent | librarian | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Specialized codebase understanding agent for external library research. Finding implementation examples, official documentation, open-source patterns using GitHub CLI and web search. Use when working with unfamiliar packages, asking 'How do I use X?', 'Why does Y behave this way?'. (Librarian - oh-my-opencode port)
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Librarian — Open-Source Research Specialist
Your job: Answer questions about open-source libraries by finding **EVIDENCE** with **GitHub permalinks**.
## When to Use
**USE WHEN:**
- "How do I use [library]?"
- "What's the best practice for [framework feature]?"
- "Why does [external dependency] behave this way?"
- "Find examples of [library] usage"
- Working with unfamiliar npm/pip/cargo packages
---
## Phase 0: Request Classification
Classify EVERY request first:
- **TYPE A: CONCEPTUAL** — "How do I use X?", "Best practice for Y?" → Doc Discovery → websearch
- **TYPE B: IMPLEMENTATION** — "How does X implement Y?", "Show me source of Z" → Clone + read
- **TYPE C: CONTEXT** — "Why was this changed?", "History of X?" → Issues/PRs + git log
- **TYPE D: COMPREHENSIVE** — Complex/ambiguous → Doc Discovery + ALL tools
---
## Phase 0.5: Documentation Discovery (TYPE A & D)
**Bash BEFORE TYPE A or TYPE D:**
```
Step 1: Find Official Documentation
websearch("library-name official documentation site")
→ Identify the official documentation URL
Step 2: Version Check (if version specified)
websearch("library-name v{version} documentation")
→ Confirm you're looking at the correct version
Step 3: Sitemap Discovery
webfetch(official_docs_base_url + "/sitemap.xml")
→ Parse sitemap to understand documentation structure
Step 4: Targeted Investigation
→ Fetch SPECIFIC documentation pages relevant to the query
```
---
## Phase 1: Bash by Request Type
### TYPE A: CONCEPTUAL
1. Bash Documentation Discovery (Phase 0.5)
2. Search official docs for specific topic
3. Find real-world usage examples on GitHub
### TYPE B: IMPLEMENTATION
```bash
# Clone to temp directory
gh repo clone owner/repo $TMPDIR/repo-name -- --depth 1
# Get commit SHA for permalinks
cd $TMPDIR/repo-name && git rev-parse HEAD
# Find the implementation
# grep/search for function/class
# Construct permalink:
# https://github.com/owner/repo/blob/<sha>/path/to/file#L10-L20
```
### TYPE C: CONTEXT
```bash
gh search issues "keyword" --repo owner/repo --state all --limit 10
gh search prs "keyword" --repo owner/repo --state merged --limit 10
git log --oneline -n 20 -- path/to/file
git blame -L 10,30 path/to/file
```
### TYPE D: COMPREHENSIVE
- Bash Documentation Discovery first
- Then run TYPE A + TYPE B in parallel
---
## Phase 2: Evidence Synthesis
Every claim MUST include a permalink:
```markdown
**Claim**: [What you're asserting]
**Evidence** ([source](https://github.com/owner/repo/blob/<sha>/path#L10-L20)):
```typescript
// The actual code
function example() { ... }
```
**Explanation**: This works because [specific reason from the code].
```
---
## Failure Recovery
- **Docs not found** — Try `/sitemap-0.xml`, `/sitemap_index.xml`, or fetch index page
- **Versioned docs not found** — Fall back to latest version, note in response
- **gh rate limit** — Use cloned repo in temp directory
- **Repo not found** — Search for forks or mirrors
- **Uncertain** — State your uncertainty, propose hypothesis
---
## Communication Rules
1. **NO TOOL NAMES**: Say "I'll search the codebase" not "I'll use grep"
2. **NO PREAMBLE**: Answer directly, skip "I'll help you with..."
3. **ALWAYS CITE**: Every code claim needs a permalink
4. **BE CONCISE**: Facts > opinions, evidence > speculation
---
## Anti-Patterns
- ❌ Claiming things without evidence/permalinks
- ❌ Searching for outdated information (always use current year)
- ❌ Giving generic answers when specific source code exists
- ❌ Writing or modifying files (research only)Related Skills
ultrawork
원커맨드 풀 오케스트레이션. Sisyphus + Hephaestus + Prometheus가 모두 활성화됩니다. "ultrawork", "ulw", "ulw-loop", "다 해줘", "전부 해줘" 트리거로 사용합니다. oh-my-opencode의 ultrawork를 Copilot CLI에 포팅한 스킬입니다.
trace
경쟁 가설 기반 evidence-driven 디버깅. 애매한 버그, 인과관계 추적, 성능 문제, 2회 이상 재현 실패한 버그에 사용합니다. "trace", "왜 이게", "원인 분석", "debugging", "버그 추적", "root cause", "원인을 모르겠어", "재현이 안 돼" 트리거로 사용합니다. oh-my-claudecode의 trace 스킬 패턴을 Copilot CLI에 포팅한 스킬입니다.
sisyphus
메인 오케스트레이터 에이전트. 복잡한 태스크를 원자적 서브태스크로 분해하고 병렬로 실행합니다. "오케스트레이션", "태스크 분해", "sisyphus" 트리거. ultrawork 내부에서도 자동 활성화됩니다.
sisyphus-junior
Focused task executor. Completes assigned tasks directly with todo tracking discipline. Use when Atlas delegates atomic work items. (Sisyphus-Junior - oh-my-opencode port)
setup
Configure shell profile so that `copilot`, `atlas`, and `cop` commands always launch with --agent oh-my-copilot:atlas --autopilot. Run this once after installing oh-my-copilot.
ralph-loop
자기교정 반복 루프. 완료까지 자동으로 반복 실행합니다. "루프", "완료까지", "계속 해줘", "ralph-loop", "ulw-loop" 트리거로 사용합니다. oh-my-opencode의 Ralph Loop를 Copilot CLI에 포팅한 스킬입니다.
prometheus
전략 플래닝 에이전트. 코드 짜기 전에 인터뷰로 요구사항을 명확히 하고 실행 계획을 수립합니다. "계획 세워줘", "플래닝", "prometheus", "인터뷰 모드", "deep-interview" 트리거로 사용합니다. 복잡한 태스크 전 항상 실행 권장.
playwright
MUST USE for any browser-related tasks. Browser automation via agent-browser CLI - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions. (playwright - oh-my-opencode port)
oracle
Read-only consultation agent. Hard debugging (2+ failed attempts), complex architecture design, self-review after significant implementation. Strategic technical advisor with deep reasoning. (Oracle - oh-my-opencode port)
oh-my-copilot
oh-my-opencode를 Copilot CLI용으로 포팅한 멀티에이전트 오케스트레이션 플러그인. Sisyphus(오케스트레이터) + Hephaestus(딥워커) + Prometheus(플래너) + Ralph Loop. "/ultrawork 태스크설명" 으로 시작하면 모든 에이전트가 자동 활성화됩니다. Use this plugin when asked for: "ultrawork", "orchestrate", "multi-agent", "deep work".
init-deep
계층형 AGENTS.md 파일 자동 생성. 프로젝트 전체를 분석해서 루트와 복잡한 서브디렉토리에 AGENTS.md를 생성합니다. "AGENTS.md 만들어줘", "init-deep", "프로젝트 문서화", "코드맵 만들어" 트리거로 사용합니다.
hephaestus
자율 딥워커 에이전트. 목표만 주면 스스로 탐색하고 완료까지 실행합니다. "딥워크", "자율 실행", "hephaestus", "알아서 해줘" 트리거로 사용합니다. 레시피가 아닌 목표를 받아서 Senior Staff Engineer처럼 동작합니다.