chrome-devtools
Browser automation with Puppeteer CLI scripts. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, or encountering JavaScript debugging, browser automation errors.
86
92%
Does it follow best practices?
Impact
57%
2.00xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
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.
This is a strong skill description that clearly communicates capabilities and usage triggers. It lists specific actions (screenshots, scraping, form automation), includes natural trigger terms users would say, and explicitly states when to use it. The mention of 'Puppeteer CLI' provides clear distinctiveness from other automation tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'screenshots, performance analysis, network monitoring, web scraping, form automation' and mentions specific debugging scenarios. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Browser automation with Puppeteer CLI scripts') and when ('Use for screenshots, performance analysis, network monitoring, web scraping, form automation, or encountering JavaScript debugging, browser automation errors'). Has explicit 'Use for' trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'screenshots', 'web scraping', 'form automation', 'browser automation', 'Puppeteer', 'JavaScript debugging'. Good coverage of terms a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche with 'Puppeteer CLI scripts' and browser-specific triggers like 'browser automation errors'. Distinct from general web development or testing skills due to specific tool mention and automation focus. | 3 / 3 |
Total | 12 / 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 strong skill document with excellent actionability and workflow clarity. The content provides fully executable commands, clear validation steps, and good error recovery guidance. The main weakness is some redundancy in the pwd warnings and minor verbosity in explanations that could be tightened.
Suggestions
Consolidate the repeated 'CRITICAL: Always check pwd' warnings into a single prominent note at the top, rather than repeating throughout the document
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy - 'CRITICAL: Always check pwd' is repeated multiple times, and some explanations could be tighter. The installation section is appropriately detailed for setup but the repeated pwd warnings add unnecessary tokens. | 2 / 3 |
Actionability | Excellent executable guidance throughout - all commands are copy-paste ready with concrete examples, real selectors, actual JSON output samples, and specific file paths. The chain commands example and error recovery section provide fully actionable workflows. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit validation checkpoints. The Execution Protocol section includes working directory verification, output validation steps (ls -lh, Read tool), and error recovery with concrete fallback strategies (CSS → snapshot → XPath). | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from Quick Start to Available Scripts to Usage Patterns to Troubleshooting. References to external files (scripts/README.md) are one level deep and clearly signaled. Content is appropriately split between overview and detailed script documentation. | 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.
- Repository
- secondsky/claude-skills
- Commit
90d6bd7
- 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.