chrome
Comprehensive Chrome DevTools development system with native Chrome capabilities for debugging, E2E testing, performance analysis, and browser automation
42
27%
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 ./.claude/skills/chrome/SKILL.mdQuality
Discovery
32%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 identifies the domain (Chrome DevTools) and lists broad capability categories but lacks specific concrete actions and entirely omits explicit trigger guidance ('Use when...'). The language reads more like a product tagline than a discriminating skill description, using terms like 'comprehensive' and 'native Chrome capabilities' that add little selection value.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks to debug a web page, run end-to-end browser tests, profile page performance, or automate Chrome interactions.'
Replace broad category labels with specific concrete actions, e.g., 'Set breakpoints, inspect DOM elements, capture network traces, run Lighthouse audits, automate page interactions via CDP.'
Include common user-facing trigger terms and file/tool references like 'inspect element', 'console errors', 'network requests', 'Puppeteer', 'headless Chrome', 'page load time'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Chrome DevTools) and lists several action areas (debugging, E2E testing, performance analysis, browser automation), but these are broad categories rather than specific concrete actions like 'set breakpoints', 'capture network traces', or 'run Lighthouse audits'. | 2 / 3 |
Completeness | Describes what the skill does at a high level but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' portion is also fairly vague, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Chrome DevTools', 'debugging', 'E2E testing', 'performance analysis', and 'browser automation', but misses common user variations like 'inspect element', 'console', 'network tab', 'Puppeteer', 'Playwright', 'page load speed', 'DOM', or 'headless browser'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Chrome DevTools' provides some distinctiveness, but terms like 'debugging', 'E2E testing', 'performance analysis', and 'browser automation' are broad enough to overlap with general testing skills, performance monitoring skills, or Selenium/Playwright-specific skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a feature overview or marketing document than actionable guidance for Claude. It lists many capabilities and tool names but never demonstrates how to actually use them with concrete, executable examples. The absence of real workflows, validation steps, and copy-paste ready code significantly limits its utility.
Suggestions
Add concrete, executable examples for each major action showing actual MCP tool calls with real parameters and expected outputs (e.g., a complete debugging workflow using mcp__chrome-devtools__evaluate_script with specific JavaScript)
Create step-by-step workflows for key use cases like E2E testing and performance analysis, including validation checkpoints (e.g., 'verify page loaded by checking screenshot before proceeding')
Remove the vague 'Key Features' section and replace it with worked examples that demonstrate the features in action
Add error handling guidance showing what to do when common operations fail (e.g., element not found during click, page not responding)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary padding like the 'AI-Driven Page Analysis' feature descriptions that are vague bullet points, and the context section adds little value. The tables are reasonably structured but the 'Key Features' section is mostly restating capabilities without adding actionable detail. | 2 / 3 |
Actionability | Despite listing many tool names and slash commands, there is no executable code, no concrete examples of actual MCP tool invocations, and no copy-paste ready workflows. The slash command syntax (/chrome analyze --full) appears to be a custom interface but no implementation or actual usage examples are shown. The tool names are listed but never demonstrated with real parameters or expected outputs. | 1 / 3 |
Workflow Clarity | There are no sequenced multi-step workflows, no validation checkpoints, and no feedback loops. Debugging, testing, and performance analysis are all multi-step processes that are only described at a feature-list level without any step-by-step guidance. For example, E2E testing mentions 'scenario execution' but never shows how to construct or run a test scenario. | 1 / 3 |
Progressive Disclosure | The content is organized into sections with headers and tables, which provides some structure. However, it's a monolithic file with no references to external documentation for advanced topics, and the 'Key Features' section duplicates information already covered in the tool priorities and actions tables without adding depth. | 2 / 3 |
Total | 6 / 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.
- Repository
- sc30gsw/claude-code-customes
- Commit
7aff694
- Reviewed
Table of Contents
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.