notebooklm

Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/notebooklm/SKILL.md

Quality

Content

67%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 highly actionable with a clear sequenced workflow and good progressive-disclosure structure pointing to real reference files. Its main weakness is conciseness: several sections duplicate commands and restate what the run.py wrapper already automates.

Suggestions

Remove the verbatim re-statement of the description at the top and consolidate the Script Reference section so each command appears once (Core Workflow or reference, not both).

Move the Environment Management and Data Storage detail into references/usage_patterns.md, keeping only the 'always use run.py' rule and data path inline.

Add an explicit validate-then-confirm feedback loop for destructive operations (notebook_manager.py remove and cleanup_manager.py --confirm), e.g. preview output, confirm, then re-run list/stats to verify.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-organized but includes unnecessary duplication: the description is restated verbatim, the Smart Add / manual add and script-reference sections repeat commands already shown in Core Workflow, and Environment/Data Storage sections restate what run.py automates. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Provides concrete, copy-paste-ready bash commands for every script and subcommand, plus a decision-flow diagram and a troubleshooting table. It is not a 5 because several examples use placeholder URLs/IDs and the follow-up mechanism is procedural rather than a fully worked executable example.	4 / 5
Workflow Clarity	Presents a clear multi-step sequence (auth, add, activate, ask, follow-up, synthesize) with a decision-flow diagram and most checkpoints present (ask before guessing metadata, preview cleanup before --confirm, follow-up until complete). Minor validation gaps on destructive remove/cleanup keep it just below a 5; the cap-at-3 rule does not apply because preview-before-confirm and ask-before-guess checks are present.	4 / 5
Progressive Disclosure	SKILL.md serves as an overview with bulk detail split into three real, one-level-deep reference files (api_reference.md, troubleshooting.md, usage_patterns.md) and separate scripts, all clearly signaled in the Resources section. It is not a 5 because some inline content (duplicated script reference, environment management) could be moved into the reference files.	4 / 5
	Total	15 / 20 Passed

Description

75%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 specific and clearly distinct, naming concrete actions and a well-defined niche, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a 'Use when...' clause would lift the strongest remaining weakness.

Suggestions

Append a 'Use when...' clause naming concrete triggers (e.g., 'Use when the user mentions NotebookLM, shares a notebooklm.google.com URL, or asks to query their uploaded documentation').

Fold one or two natural trigger phrases such as 'ask my NotebookLM' or 'check my docs' into the description to improve trigger-term coverage.

Keep the existing concrete action list but consider trimming the session-lifecycle detail ('opens a fresh browser session... and closes') to preserve conciseness once a trigger clause is added.

Dimension	Reasoning	Score
Specificity	Names the domain (Google NotebookLM) and multiple concrete actions: query documentation with Gemini's source-grounded answers, open a fresh browser session, retrieve answers exclusively from uploaded documents, and close. This matches the anchor for comprehensive coverage of specific concrete actions.	5 / 5
Completeness	The description clearly answers 'what' (interact with NotebookLM for source-grounded documentation queries) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes the key natural term 'Google NotebookLM' and the natural phrase 'query documentation', giving good keyword coverage. It is not a 5 because broader natural variations ('ask my NotebookLM', 'check my docs') and any extension/synonym coverage live in the body rather than the description itself.	4 / 5
Distinctiveness Conflict Risk	The pairing of 'Google NotebookLM' with 'Gemini's source-grounded answers' carves a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/notebooklm/SKILL.md
Commit: fbdfd63

Reviewed: about 17 hours 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.