菜单
Use this skill when working with Google NotebookLM — creating/querying notebooks, managing sources, or running research workflows via the notebooklm-mcp MCP server.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | notebooklm |
| description | Use this skill when working with Google NotebookLM — creating/querying notebooks, managing sources, or running research workflows via the notebooklm-mcp MCP server. |
MCP server: notebooklm-mcp (11 tools). Script: ~/.claude/notebooklm_mcp_lite.py.
Full 35-tool server available at /path/to/works/for/you/.local/bin/notebooklm-mcp.
Auth: run nlm login. Refresh mid-session: refresh_auth.
| Tool | Notes |
|---|---|
notebook_list | List all notebooks |
notebook_get | Get notebook details, including sources list |
notebook_create | Create a new notebook |
notebook_delete | Requires confirm=True after user approval |
source_add | Add url / text / drive / file (PDFs via file_path) |
source_delete | Requires confirm=True; accepts source_id or source_ids |
notebook_query | Query existing sources only |
refresh_auth | Re-authenticate mid-session |
research_start | Start web or Drive search for new sources |
research_status | Poll research job; use compact=False to review hits |
research_import | Import after complete; use source_indices to pick a subset |
Query an existing notebook:
notebook_list → notebook_query(notebook_id=..., query=...)
Add a source:
notebook_get to confirm notebook ID → source_add(notebook_id=..., url=...)
Research workflow (find and import new sources):
research_start(notebook_id=..., query=..., source_type="web")research_status(job_id=..., compact=False) — poll until complete, review hitsresearch_import(job_id=..., source_indices=[0, 2, 4]) — import chosen subsetDestructive operations: always require confirm=True; ask user before calling.
Calibrate the Claude Code statusline against the real /usage numbers. Use when the user shares a screenshot of the in-app `/usage` panel (or the claude.ai Settings → Usage page) and wants the statusline's "time left", session %, and weekly % to match what Claude actually reports. Fixes ccusage block-drift, where the local 5-hour clock starts from the first transcript message instead of the real server-side reset.
Dispatch a review task to Gemini CLI (large-context review — plans, docs, large file corpora) or Codex CLI (code review — diffs, PRs, implementation quality). Routes based on the nature of the artifact being reviewed. Use from achieve-goal, literature-survey skills, or any skill that needs a CLI-based review gate. This is a headless CLI review gate over a concrete artifact (code, diff, or doc corpus); for an interactive second opinion or a side-by-side model comparison via MCP chat, use consult-llm instead.
Use when the user wants a second opinion from Gemini or OpenAI/ChatGPT, asks to "consult" another model, or wants to compare responses across models. This is the interactive MCP chat path for a second opinion or model comparison; to run a structured review gate over code, diffs, plans, or large doc corpora through a headless CLI, use cli-review instead.
Use this skill when deciding whether and how to update the knowledge base at /path/to/works/for/you/knowledge_base/ after completing a task. This is the post-task "does this work belong in the KB, and where" decision path; to turn a pasted LLM conversation transcript into a KB note use kb-from-conversation instead.
Periodic review of the memory system at ~/.claude/memory/ for duplicates, redundancies, conflicts, and stale entries. Use when the user asks to audit, clean up, or review memory. Presents findings with enforcement trade-off context — never retires anything without user confirmation. Scoped to the agent memory files under ~/.claude/memory/; for the same kind of duplicate/stale/conflict audit over the knowledge base at /path/to/works/for/you/knowledge_base/ use kb-sweep instead.
Use this skill when the user wants to "promote", "move", "upgrade", or "migrate" a project-level skill, agent, or rule (e.g. a Cursor rule, a project-local AI rule, or any .md skill/agent file) into a global Claude scope. By default always promotes to global (~/.claude/skills/, ~/.claude/agents/, ~/.claude/CLAUDE.md) unless the user explicitly says "project-level". Moves the file so it is shared across all projects and symlinks it back so the original project is not broken. This keeps the skill private to your global ~/.claude scope; to publish skills to the public agent_skills GitHub repo, use publish-skills instead.