← All skills
notebooklm
85 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
By b-open-io/prompts (GitHub) · coding · 15 stars · scanned at commit f4b302a
This skill should be used when the user asks to "query my NotebookLM notebook", "ask NotebookLM about these sources", "get a citation-backed answer from my documents", or "search my NotebookLM library". Provides browser automation, library management, and persistent auth for querying Google NotebookLM notebooks directly from Claude Code, returning source-grounded answers from Gemini instead of general knowledge.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this. Expected for a coding skill.
Found in 25 places.
Show 17 more
- modules/research/skills/notebooklm/SKILL.md, line 66
python scripts/run.py notebook_manager.py list - modules/research/skills/notebooklm/SKILL.md, line 89
python scripts/run.py ask_question.py --question "Your question here" - modules/research/skills/notebooklm/SKILL.md, line 147
python scripts/run.py auth_manager.py status - modules/research/skills/notebooklm/references/api_reference.md, line 160
result = subprocess.run([ - modules/research/skills/notebooklm/references/api_reference.md, line 216
result = subprocess.run([ - modules/research/skills/notebooklm/references/api_reference.md, line 228
subprocess.run(["python", "scripts/run.py", "auth_manager.py", "setup"]) - modules/research/skills/notebooklm/references/api_reference.md, line 249
result = subprocess.run([ - modules/research/skills/notebooklm/references/api_reference.md, line 271
result = subprocess.run([ - modules/research/skills/notebooklm/references/troubleshooting.md, line 132
subprocess.run(["python", "scripts/run.py", "auth_manager.py", "reauth"]) - modules/research/skills/notebooklm/references/usage_patterns.md, line 177
result = subprocess.run([ - modules/research/skills/notebooklm/references/usage_patterns.md, line 210
result = subprocess.run([ - modules/research/skills/notebooklm/references/usage_patterns.md, line 219
follow_up = subprocess.run([ - modules/research/skills/notebooklm/scripts/__init__.py, line 53
subprocess.run( - modules/research/skills/notebooklm/scripts/__init__.py, line 65
subprocess.run( - modules/research/skills/notebooklm/scripts/run.py, line 38
result = subprocess.run([sys.executable, str(setup_script)]) - modules/research/skills/notebooklm/scripts/run.py, line 91
result = subprocess.run(cmd) - modules/research/skills/notebooklm/scripts/setup_environment.py, line 54
subprocess.run(
and 5 more places
Changes files outside its own folder
The author does not mention this.
Found in 5 places.
Show 2 more
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'notebooklm' ] || [ -L ~/.agents/skills/'notebooklm' ]; then echo 'A skill folder named notebooklm already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/b-open-io/prompts' "$d" && git -C "$d" checkout --quiet 'f4b302aadb0c99023b03e1f1b38ffed3697fbedf' -- 'modules/research/skills/notebooklm' && mkdir -p ~/.agents/skills && cp -R "$d"/'modules/research/skills/notebooklm' ~/.agents/skills/'notebooklm' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'notebooklm' ~/.claude/skills/'notebooklm' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for b-open-io/prompts shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/b-open-io/prompts/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | f4b302a | 85 |
| 2026-11-06 | f4b302a | 85 |