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

91%

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

86%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.

A well-structured, highly actionable toolbox skill with copy-paste commands and clean progressive disclosure into reference files. Minor conciseness and workflow-validation gaps keep it just short of perfect.

Suggestions

Trim the troubleshooting section (e.g., the long manual apt-get line and repeated cd paths) by deferring full detail to ./scripts/README.md.

Add an explicit validation checkpoint to the form-automation workflow (e.g., snapshot the form and verify fields before clicking submit).

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of what Puppeteer or Core Web Vitals are), but the troubleshooting section and repeated `cd .claude/skills/chrome-devtools/scripts` paths could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready commands for every common case — navigate, screenshot, fill, click, evaluate, performance, network, console — plus jq parsing and chained-command patterns.	5 / 5
Workflow Clarity	Setup is clearly sequenced (install-deps → npm install → Test with expected output) and workflows are recipe-style, but the form-automation workflow lacks an explicit validate-before-submit checkpoint.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing to verified one-level-deep references (cdp-domains.md, puppeteer-reference.md, performance-guide.md) and ./scripts/README.md, each signaled with a description; detail is appropriately split out.	5 / 5
	Total	18 / 20 Passed

Description

96%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.

A strong description that pairs a concrete capability list with explicit 'Use for' trigger guidance and natural user phrasings. Only minor overlap risk with sibling browser skills prevents a perfect distinctiveness score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'taking screenshots', 'monitoring network traffic', 'web scraping', 'form automation', 'JavaScript debugging' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Browser automation, debugging, and performance analysis using Puppeteer CLI scripts') and 'when' ('Use for automating browsers, taking screenshots, ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Uses natural phrasings a user would actually say ('taking screenshots', 'web scraping', 'form automation', 'network traffic', 'performance analysis') rather than purely technical jargon.	5 / 5
Distinctiveness Conflict Risk	The 'Puppeteer CLI scripts' and DevTools/performance framing carves a clear niche, but generic triggers like 'taking screenshots' or 'automating browsers' could overlap with other browser skills.	4 / 5
	Total	19 / 20 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: einverne/dotfiles
Path: claude/skills/chrome-devtools/SKILL.md
Commit: 1446b2f

Reviewed: 1 day 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.