- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add JetBrains/thinkrail --skill librarian -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add JetBrains/thinkrail --skill librarian -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add JetBrains/thinkrail --skill librarian -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add JetBrains/thinkrail --skill librarian -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/JetBrains/thinkrail/tree/HEAD/thinkrail-extensions/web-access/skills/librarian来自发布者
Answer questions about open-source libraries by finding evidence with GitHub permalinks. Every claim backed by actual code.
Pi runs the independent tool calls of one turn concurrently, and batching them saves LLM round-trips (~5-10s each). Use these patterns:
Before doing anything, classify the request to pick the right research strategy.
Batch these in one turn:
"library-name topic" for recent articles and discussionsSynthesize web results + repo docs. Cite official documentation and link to relevant source files.
The core workflow -- clone, find, permalink:
Repository cloned to: <path>; that path is the clone, use it for every step belowgrep -rn "function_name", find . -name "*.ts"cd <clone path> && git rev-parse HEADhttps://github.com/owner/repo/blob/<sha>/path/to/file#L10-L20Batch the initial calls: fetch_content (clone) + web_search (recent discussions) in one turn. Then dig into the clone with grep/read once it's available.
Use git operations on the cloned repo:
cd <clone path>
# Recent changes to a specific file
git log --oneline -n 20 -- path/to/file.ts
# Who changed what and when
git blame -L 10,30 path/to/file.ts
# Full diff for a specific commit
git show <sha> -- path/to/file.ts
# Search commit messages
git log --oneline --grep="keyword" -n 10
For issues and PRs, use bash:
# Search issues
gh search issues "keyword" --repo owner/repo --state all --limit 10
# Search merged PRs
gh search prs "keyword" --repo owner/repo --state merged --limit 10
# View specific issue/PR with comments
gh issue view <number> --repo owner/repo --comments
gh pr view <number> --repo owner/repo --comments
# Release notes
gh api repos/owner/repo/releases --jq '.[0:5] | .[].tag_name'
Combine everything. Batch these in one turn:
gh search issues "keyword" --repo owner/repo --limit 10 & gh search prs "keyword" --repo owner/repo --state merged --limit 10 & waitThen dig into the clone with grep, read, git blame, git log as needed.
Permalinks are the whole point. They make your answers citable and verifiable.
https://github.com/<owner>/<repo>/blob/<commit-sha>/<filepath>#L<start>-L<end>
Getting the SHA from a cloned repo:
cd <clone path> && git rev-parse HEAD
Getting the SHA from a tag:
gh api repos/owner/repo/git/refs/tags/v1.0.0 --jq '.object.sha'
Always use full commit SHAs, not branch names. Branch links break when code changes. Permalinks don't.
Every code-related claim needs a permalink. Format:
The stale time check happens in [`notifyManager.ts`](https://github.com/TanStack/query/blob/abc123/packages/query-core/src/notifyManager.ts#L42-L50):
\`\`\`typescript
function isStale(query: Query, staleTime: number): boolean {
return query.state.dataUpdatedAt + staleTime < Date.now()
}
\`\`\`
For conceptual answers, link to official docs and relevant source files. For implementation answers, every function/class reference should have a permalink.
For questions about video tutorials, conference talks, or screen recordings:
// Full extraction (transcript + visual descriptions)
fetch_content({ url: "https://youtube.com/watch?v=abc" })
// Ask a specific question about a video
fetch_content({ url: "https://youtube.com/watch?v=abc", prompt: "What libraries are imported in this tutorial?" })
// Single frame at a known moment
fetch_content({ url: "https://youtube.com/watch?v=abc", timestamp: "23:41" })
// Range scan for visual discovery
fetch_content({ url: "https://youtube.com/watch?v=abc", timestamp: "23:41-25:00" })
// Custom density across a range
fetch_content({ url: "https://youtube.com/watch?v=abc", timestamp: "23:41-25:00", frames: 3 })
// Whole-video sampling
fetch_content({ url: "https://youtube.com/watch?v=abc", frames: 6 })
// Analyze a local recording
fetch_content({ url: "/path/to/demo.mp4", prompt: "What error message appears on screen?" })
// Batch multiple videos with the same question
fetch_content({
urls: ["https://youtube.com/watch?v=abc", "https://youtube.com/watch?v=def"],
prompt: "What packages are installed?"
})
Use single timestamps for known moments, ranges for visual scanning, and frames-alone for a quick overview of the whole video.
The prompt parameter applies to video content (YouTube URLs and local video files); for other URLs it is used only with mode: "answer".
fetch_content("https://github.com/owner/repo/tree/v1.0.0")Research open-source libraries with evidence-backed answers and GitHub permalinks. Use when the user asks about library internals, needs implementation details with source code references, wants to un
---name: librariandescription: Research open-source libraries with evidence-backed answers and GitHub permalinks. Use when the user asks…---# thinkrail-extensions/web-access/skills/librarian/SKILL.md概览
Research open-source libraries with evidence-backed answers and GitHub permalinks. Use when the user asks about library internals, needs implementation details with source code references, wants to understand why something was changed, or needs authoritative answers backed by actual code. Excels at navigating large open-source repos and providing citations to exact lines of code.
常见问题
从发布者处下载 thinkrail-extensions/web-access/skills/librarian/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/JetBrains/thinkrail。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。