Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
79
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./SKILL.mdQuality
Discovery
57%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 effectively identifies a unique niche (Google NotebookLM integration) with good distinctiveness, but suffers from incomplete trigger guidance and a mix of features/benefits rather than clear user actions. The lack of an explicit 'Use when...' clause and missing natural user trigger terms limit Claude's ability to reliably select this skill.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'research my notes', 'check my sources', 'NotebookLM', 'find citations'
Replace feature-focused language ('browser automation', 'persistent auth') with user-facing actions like 'search notebooks', 'retrieve cited passages', 'query uploaded documents'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google NotebookLM) and some actions ('query notebooks', 'browser automation', 'library management', 'persistent auth'), but the actions are a mix of features and benefits rather than comprehensive concrete user-facing actions. | 2 / 3 |
Completeness | Has a 'what' (query NotebookLM for citation-backed answers) but lacks an explicit 'Use when...' clause. The opening 'Use this skill to' partially addresses when, but doesn't provide explicit trigger guidance for Claude's skill selection. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Google NotebookLM', 'notebooks', 'Gemini', 'citation', 'source-grounded', but misses common variations users might say like 'research', 'notes', 'sources', or 'references'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Google NotebookLM integration with clear product-specific terminology. Unlikely to conflict with other skills due to the unique combination of NotebookLM, Gemini, and citation-backed responses. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with clear workflows and good progressive disclosure. The main weakness is some redundancy between sections (wrapper warning repeated, workflow duplicated in decision flow). The follow-up mechanism and smart discovery patterns show thoughtful design for complex multi-step operations.
Suggestions
Consolidate the 'Critical: Always Use run.py Wrapper' section with the first mention in Core Workflow to reduce redundancy
Remove the Decision Flow diagram or merge it with Core Workflow since it largely duplicates the step-by-step instructions above it
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some redundancy - the 'Critical: Always Use run.py Wrapper' section repeats information, and there's overlap between the Core Workflow and Script Reference sections. The decision flow diagram duplicates earlier content. However, it avoids explaining basic concepts Claude knows. | 2 / 3 |
Actionability | Excellent executable guidance with copy-paste ready bash commands throughout. Every operation has concrete, complete command examples with all required flags shown. The troubleshooting table provides specific solutions. | 3 / 3 |
Workflow Clarity | Clear sequential workflow with explicit steps (1-4), validation checkpoints (check auth status first, check library before adding), and a decision flow diagram. The follow-up mechanism section provides explicit feedback loop for iterative querying. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from triggers to core workflow to reference. References to extended documentation (api_reference.md, troubleshooting.md, usage_patterns.md) are clearly signaled at the end. Content is appropriately split between quick reference and detailed docs. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
eea5cb2
Table of Contents
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.