notebooklm-integration
This skill should be used when the user asks to "ingest into NotebookLM", "query NotebookLM", "add sources to notebook", "cross-source synthesis", "check stale sources", or mentions NotebookLM, notebook integration, source ingestion, or knowledge consolidation.
- License 许可
- MIT
- 最近更新
- 2026-08-03
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- notebooklm-integration
- description
- This skill should be used when the user asks to "ingest into NotebookLM", "query NotebookLM", "add sources to notebook", "cross-source synthesis", "check stale sources", or mentions NotebookLM, notebook integration, source ingestion, or knowledge consolidation.
02 资源文件 10
- 参考文档_meta.json453 B
- 其他.gitignore24 B
- 参考文档README.md4.4 KB
- 参考文档references/api-reference.md13.7 KB
- 参考文档references/token-registry.md7.3 KB
- 参考文档SOURCE.md380 B
- 参考文档test/agent-test-cases.md3.2 KB
- 脚本test/full_skill_coverage_test.py6.5 KB
- 脚本test/run-all.ps1594 B
- 参考文档TRUST.auto.yaml2.2 KB
03 SKILL.md 正文
NotebookLM Integration
CLI Tool
Use notebooklm CLI only (teng-lin/notebooklm-py):
- Auth config at
$NOTEBOOKLM_HOME - One notebook per research DOMAIN, not per session
Commands
# Add a file or URL as a source
notebooklm source add <file-or-url>
# Add broad topic research
notebooklm source add-research "query"
# Query with citations
notebooklm ask "question" --citations
# Find outdated sources
notebooklm source stale
Consolidation Flow
- Agent writes findings to repo files (YAML provenance or markdown deep reviews)
- Consolidation step ingests into NotebookLM:
notebooklm source add <file> - Cross-source synthesis:
notebooklm ask --citations
Notebook Organization
| Domain | Notebook | Purpose |
|---|---|---|
| Research pipeline | research-pipeline | Source discovery, provenance, scoring |
| Multi-model review | autonomous-review | reviewd, consensus, debate integrity |
| Tool ecosystem | tool-ecosystem | mise, chezmoi, hk, devcontainer |
Rules
- Use
notebooklmCLI only — never build custom NotebookLM tooling - One notebook per domain — do not create per-session notebooks
- Always use
--citationswhen querying for synthesis - Check
notebooklm source staleperiodically to refresh outdated sources - Ingest YAML provenance records, not raw markdown notes
04 同仓库更多 Skills
next-workflow-step
Use this skill when the user wants to transition to the next workflow step, wrap up a session cleanly, prepare a handoff, or says things like "next step", "continue the workflow", "wrap up", "hand off", "move to the next phase", "what's next in embrace", or "prepare for /clear". Also triggers when the current octo:embrace phase appears complete and no explicit next action is set.
source-discovery
This skill should be used when the user asks to "find sources", "discover URLs", "catalog a source", "classify a URL", "search for libraries", "check what exists", or mentions source discovery, URL cataloging, source classification, or research source management.
review-synthesis
This skill should be used when the user asks to "summarize review findings", "prioritize fixes", "rank review issues", "combine reviewer feedback", "create action items from review", or mentions review synthesis, finding prioritization, severity ranking, or review result summarization.
research-scoring
This skill should be used when the user asks to "score research", "check research quality", "evaluate coverage", "measure improvement", "assess research completeness", or mentions research scoring, quality metrics, coverage gaps, improvement baseline, or research pipeline status.
evidence-synthesis
This skill should be used when the user asks to "synthesize findings", "combine research", "cross-reference sources", "summarize evidence", "write a deep review", or mentions evidence synthesis, finding consolidation, cross-source analysis, or research summarization.
debate-orchestration
This skill should be used when the user asks to "run a multi-model review", "debate code changes", "invoke reviewd", "get multiple model opinions", "run adversarial review", or mentions multi-model review, debate orchestration, reviewd CLI, codex review, gemini review, or adversarial code analysis.