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.
81
84%
Does it follow best practices?
Impact
57%
2.00xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
92%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 description that clearly identifies the tool (Puppeteer), lists specific capabilities, and provides explicit trigger guidance. The main weakness is that some trigger terms like 'JavaScript debugging' and 'performance analysis' are broad enough to potentially conflict with other skills. The phrasing 'or encountering JavaScript debugging, browser automation errors' is slightly awkward grammatically but still conveys the intent.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: screenshots, performance analysis, network monitoring, web scraping, form automation, and JavaScript debugging/browser automation errors. | 3 / 3 |
Completeness | Clearly answers 'what' (browser automation with Puppeteer CLI scripts) and 'when' with explicit triggers ('Use for screenshots, performance analysis, network monitoring, web scraping, form automation, or encountering JavaScript debugging, browser automation errors'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'screenshots', 'web scraping', 'form automation', 'Puppeteer', 'browser automation', 'network monitoring', 'performance analysis', 'JavaScript debugging'. These cover a good range of terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | While 'Puppeteer' and 'browser automation' are fairly distinct, terms like 'web scraping', 'JavaScript debugging', and 'performance analysis' could overlap with other skills focused on general web development, debugging, or performance tooling. The scope is somewhat broad which increases conflict risk. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with clear workflows and validation steps. Its main weakness is verbosity—the compression details, multi-OS installation instructions, and repeated pwd warnings inflate the token count beyond what's necessary. The progressive disclosure could be improved by moving installation and troubleshooting to separate reference files.
Suggestions
Move the detailed installation instructions (multi-OS support, ImageMagick setup) to a separate INSTALL.md and reference it from the Quick Start section
Consolidate the compression behavior details into the scripts README.md rather than inlining all format-specific compression logic
Remove the repeated 'CRITICAL: Always check pwd' warnings—state it once prominently in the Execution Protocol section
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary detail. The extensive compression behavior section with all format-specific details and the verbose installation steps (including OS-specific instructions Claude could infer) add bulk. The repeated 'CRITICAL: Always check pwd' appears multiple times. | 2 / 3 |
Actionability | Highly actionable with concrete, executable commands throughout. Every script has real usage examples with actual flags, selectors, and expected JSON output. The chaining pattern, jq parsing, and error recovery examples are all copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit validation checkpoints. The Execution Protocol section includes working directory verification before execution, output validation after operations (verify file, check JSON success), and error recovery with a discover-then-retry feedback loop using snapshot.js. | 3 / 3 |
Progressive Disclosure | References the scripts README.md for detailed usage, which is good. However, the compression behavior details, full installation instructions for multiple OSes, and troubleshooting could be split into separate files. The inline content is somewhat heavy for an overview skill file. | 2 / 3 |
Total | 10 / 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
88da5ff
- 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.