Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query and manage Google NotebookLM notebooks with persistent profile auth, source sync, batch/multi queries, and structured exports. Use when user asks to query NotebookLM, 'ask my notebook', shares NotebookLM notebook URLs, wants to list/create notebooks, manage sources, do bulk folder sync, dedupe, or audit exports.
.claude/skills/sanjay3290-notebooklm/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 239% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -15% | 0% |
Query NotebookLM notebooks and manage notebooks/sources via Playwright browser automation.
All commands run from the skill directory. All scripts output JSON to stdout and exit 1 on error. Use --help on any script for full flag reference.
python scripts/auth_manager.py setup --profile <name>python scripts/notebook_manager.py add --url <url> --name <name> --description <desc> --topics <topics>python scripts/ask_question.py --question "..." --notebook-id <id>python scripts/remote_manager.py add-source|sync-sources ...--show-browser for debugging only.~/.config/claude/notebooklm-skill/ (override with NOTEBOOKLM_DATA_DIR).--dry-run available on all destructive/bulk operations (create, add-source, delete-source, sync-sources).--retries N retries transient browser failures with screenshot/HTML artifact capture.--questions "q1||q2||q3") and multi-notebook comparison (--compare-notebook-ids) supported.--export-format markdown --save-notes.bash# Auth python scripts/auth_manager.py setup --profile work python scripts/auth_manager.py status --profile work # Library python scripts/notebook_manager.py add --url "..." --name "..." --description "..." --topics "..." python scripts/notebook_manager.py list # Ask python scripts/ask_question.py --question "..." --notebook-id <id> python scripts/ask_question.py --questions "q1||q2" --notebook-id <id> # Sources python scripts/remote_manager.py add-source --notebook-id <id> --dir ./docs --recursive python scripts/remote_manager.py sync-sources --notebook-id <id> --dir ./docs --recursive --delete-missing --dry-run
For full command reference with all flags and examples, see references/commands.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 12,916 | 21,818 | +69% | 1 | 1 | 0% | 2,368 | 831 | -65% | 0 | 0 | — |
case-02 | fail→pass | 5,739 | 1,571 | -73% | 1 | 1 | 0% | 254 | 860 | +239% | 0 | 0 | — |
case-03 | fail→fail | 4,075 | 5,036 | +24% | 1 | 1 | 0% | 675 | 796 | +18% | 0 | 0 | — |
case-04 | fail→fail | 8,817 | 9,411 | +7% | 1 | 1 | 0% | 1,641 | 835 | -49% | 0 | 0 | — |
case-05 | fail→fail | 4,050 | 4,978 | +23% | 1 | 1 | 0% | 603 | 707 | +17% | 0 | 0 | — |
case-06 | fail→fail | 4,173 | 3,356 | -20% | 1 | 1 | 0% | 669 | 700 | +5% | 0 | 0 | — |
case-07 | fail→fail | 2,469 | 4,855 | +97% | 1 | 1 | 0% | 358 | 931 | +160% | 0 | 0 | — |
case-08 | fail→pass | 10,078 | 3,067 | -70% | 1 | 1 | 0% | 1,742 | 1,093 | -37% | 0 | 0 | — |
case-09 | fail→fail | 8,370 | 5,778 | -31% | 1 | 1 | 0% | 1,388 | 869 | -37% | 0 | 0 | — |
case-10 | fail→fail | 17,049 | 4,631 | -73% | 1 | 1 | 0% | 2,090 | 783 | -63% | 0 | 0 | — |
case-11 | fail→pass | 10,831 | 1,296 | -88% | 1 | 1 | 0% | 1,993 | 776 | -61% | 0 | 0 | — |
case-12 | fail→fail | 12,061 | 5,011 | -58% | 1 | 1 | 0% | 2,051 | 803 | -61% | 0 | 0 | — |
case-13 | fail→pass | 8,150 | 1,481 | -82% | 1 | 1 | 0% | 1,498 | 792 | -47% | 0 | 0 | — |
case-14 | fail→fail | 7,585 | 4,952 | -35% | 1 | 1 | 0% | 1,426 | 891 | -38% | 0 | 0 | — |
case-15 | pass→pass | 7,392 | 1,645 | -78% | 1 | 1 | 0% | 1,211 | 814 | -33% | 0 | 0 | — |
case-16 | pass→pass | 12,233 | 3,306 | -73% | 1 | 1 | 0% | 2,094 | 1,055 | -50% | 0 | 0 | — |
case-17 | fail→pass | 8,075 | 3,371 | -58% | 1 | 1 | 0% | 1,193 | 1,010 | -15% | 0 | 0 | — |
case-18 | pass→pass | 6,280 | 2,661 | -58% | 1 | 1 | 0% | 1,194 | 1,037 | -13% | 0 | 0 | — |
case-19 | fail→pass | 22,397 | 27,274 | +22% | 1 | 1 | 0% | 4,330 | 1,459 | -66% | 0 | 0 | — |
case-20 | pass→pass | 9,162 | 5,297 | -42% | 1 | 1 | 0% | 1,589 | 1,525 | -4% | 0 | 0 | — |
case-21 | pass→pass | 6,590 | 5,300 | -20% | 1 | 1 | 0% | 1,206 | 1,486 | +23% | 0 | 0 | — |
case-22 | pass→pass | 6,612 | 4,548 | -31% | 1 | 1 | 0% | 1,196 | 1,365 | +14% | 0 | 0 | — |
case-23 | pass→pass | 6,197 | 3,951 | -36% | 1 | 1 | 0% | 1,076 | 1,120 | +4% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 13 counted toward the lift figure. The other 10 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +26 percentage points is the difference between those two pass rates over the 13 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.