blog-notebooklm

Query Google NotebookLM notebooks for source-grounded, citation-backed answers from user-uploaded documents. Manages notebook library, handles Google authentication, and supports smart discovery. Works standalone via /blog notebooklm or internally from blog-write and blog-researcher for source-grounded research context. Falls back gracefully when not configured. Use when user says "notebooklm", "notebook", "query notebook", "ask notebook", "notebook research", "source grounded research", "document query", "notebook library".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and highly actionable with concrete, executable commands and clear sequenced workflows including validation checkpoints and feedback loops. The main weaknesses are modest redundancy between the Quick Reference table and the detailed workflow sections, and missing explicit confirmation guidance for destructive library/auth operations.

Suggestions

Collapse the Quick Reference table into brief one-liners or defer full command detail to references/commands.md to remove duplication with the Query Workflow and Library Management sections.

Add an explicit user-confirmation checkpoint before destructive operations (e.g., 'Confirm with the user before running library remove or auth clear, since they delete data irreversibly').

Tighten the provenance prose in the intro (lines 29-33) into a short bulleted rule set so the citation guidance reads as instruction rather than narration.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with skill-specific provenance guidance that Claude would not already know, but the Quick Reference command table duplicates listings elaborated in the later Query/Library workflow sections, adding modest redundancy.	4 / 5
Actionability	Abundant copy-paste-ready bash commands covering ask, discover, library management, setup, status, and cleanup, with flag variants (--notebook-id, --notebook-url, --json, --show-browser) for the common cases.	5 / 5
Workflow Clarity	Query workflow is explicitly sequenced (Steps 1-4) with an auth gate checkpoint and a STOP/ANALYZE/SYNTHESIZE feedback loop, plus an error-recovery table; minor gap is the lack of explicit user-confirmation guidance for destructive ops like "library remove" and auth "clear".	4 / 5
Progressive Disclosure	Clear overview body with well-signaled one-level-deep references (references/commands.md, references/troubleshooting.md) marked "Load on-demand"; minor organization gap is partial duplication between the inline command examples and the separate commands.md reference.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person voice, concrete actions, explicit trigger guidance with natural synonyms, and a clearly delineated niche. It answers what, when, and how-it-integrates without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "Query Google NotebookLM notebooks for source-grounded, citation-backed answers", "Manages notebook library", "handles Google authentication", "supports smart discovery" — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (query, library management, auth, discovery) and when, with a concrete "Use when user says..." trigger clause listing natural phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms and the slash invocation: "notebooklm", "notebook", "query notebook", "ask notebook", "notebook research", "source grounded research", "document query", "notebook library".	5 / 5
Distinctiveness Conflict Risk	Clear niche (Google NotebookLM specifically) with distinct, product-specific triggers; minimal risk of firing for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AgriciDaniel/claude-blog
Path: skills/blog-notebooklm/SKILL.md
Commit: 84f7abf

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.