chrome-devtools

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

85%

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

A highly actionable, well-structured skill body with clear workflows, validation checkpoints, and exemplary one-level-deep reference disclosure; its main weakness is redundancy that inflates token usage without adding capability.

Suggestions

Consolidate the repeated 'Always check pwd before running scripts' warning and working-directory protocol into a single Execution Protocol section, removing the duplicate CRITICAL callouts in Quick Start and Available Scripts.

Trim the Troubleshooting section to a concise error-to-fix mapping and remove details already covered in the Installation steps (e.g., the libnss3 apt-get command duplicates install-deps.sh guidance).

Consider moving the long Troubleshooting block into a ./references/troubleshooting.md file so the main SKILL.md stays a lean overview while keeping the detail one level deep.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and operational, but repeats the 'Always check pwd' warning (lines 13 and 68) and restates working-directory verification across Quick Start, Available Scripts, and Execution Protocol, while the verbose Troubleshooting section overlaps the Install section — matching the 'could be tightened' anchor rather than the every-token-earns-its-place profile of a 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands such as 'node screenshot.js --url https://example.com --output page.png --max-size 3' and jq pipelines over JSON output, with concrete flags and examples matching the score-3 anchor.	3 / 3
Workflow Clarity	The Execution Protocol gives a numbered Working Directory Verification, an Output Validation checkpoint ('ls -lh', Read tool, 'success:true' check), and an Error Recovery feedback loop (selector fails -> snapshot.js -> retry XPath), plus a Common Mistakes checklist — clear sequence with explicit validation and feedback loops.	3 / 3
Progressive Disclosure	A 'Reference Documentation' section signals three one-level-deep references (cdp-domains.md, puppeteer-reference.md, performance-guide.md, all verified to exist) with descriptions, and points to ./scripts/README.md for complete options; deep material is appropriately externalized, matching the clear-overview-with-signaled-references anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%

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

A strong, well-structured description: third-person voice, concrete capability list, and an explicit 'Use for' trigger clause that jointly answer what and when with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging' — matching the multiple-specific-actions anchor rather than the partial coverage of a 2.	3 / 3
Completeness	The first sentence states what it does and the explicit 'Use for ...' clause supplies when to invoke it, answering both what and when; it is not a 2 because the trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	Uses natural terms users would actually say ('screenshots', 'web scraping', 'form automation', 'network traffic', 'JavaScript debugging', 'browser automation'), giving good coverage rather than the missing-variations profile of a 2.	3 / 3
Distinctiveness Conflict Risk	The 'using Puppeteer CLI scripts' scoping plus browser-specific triggers carve a clear niche unlikely to conflict with non-browser skills, matching the distinct-trigger anchor rather than the overlapping profile of a 2.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mrgoonie/claudekit-skills
Path: .claude/skills/chrome-devtools/SKILL.md
Commit: 80113d8

Reviewed: about 9 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.