troubleshooting
Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails.
87
83%
Does it follow best practices?
Impact
95%
1.58xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 well-crafted description with excellent trigger terms and completeness. It clearly defines both what the skill does and when to use it with specific function names as triggers. The main weakness is that the 'what' portion could be more specific about the concrete troubleshooting actions performed.
Suggestions
Add 2-3 specific troubleshooting actions to improve specificity, e.g., 'diagnose port conflicts, verify Chrome launch flags, reset stale connections'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Chrome DevTools MCP troubleshooting) and some actions (troubleshoot connection and target issues), but doesn't list multiple specific concrete actions like 'restart server', 'check port availability', 'verify Chrome flags'. | 2 / 3 |
Completeness | Clearly answers both what ('troubleshoot connection and target issues' with Chrome DevTools MCP) and when ('when list_pages, new_page, or navigate_page fail, or when the server initialization fails') with explicit trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes highly specific and natural trigger terms: 'list_pages', 'new_page', 'navigate_page', 'server initialization fails', 'Chrome DevTools MCP'. These are exactly the terms a user or Claude would encounter when hitting these errors. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Chrome DevTools MCP troubleshooting with distinct function names as triggers. Extremely unlikely to conflict with other skills given the specificity of the error conditions mentioned. | 3 / 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 strong troubleshooting skill with excellent workflow clarity and actionability. The step-by-step diagnostic process is well-sequenced with clear validation checkpoints and feedback loops, and the concrete commands and URLs make it immediately executable. The main weakness is that it's somewhat verbose for a skill file and could benefit from splitting detailed error patterns into a separate reference document.
Suggestions
Consider moving the detailed error pattern descriptions (Step 2 sub-sections) into a separate `troubleshooting-errors.md` reference file, keeping only a brief summary table in the main skill.
Remove the persona framing sentence ('You are acting as a troubleshooting wizard...') and the parenthetical trigger explanation, as these duplicate the skill's YAML metadata purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary verbosity, such as the detailed persona framing ('You are acting as a troubleshooting wizard') and some explanatory sentences that could be tightened. However, it largely avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides highly specific, concrete guidance: exact file paths to check, specific CLI commands to run (e.g., `npx chrome-devtools-mcp@latest --help`, `gh issue list ...`), exact URLs to navigate to (`chrome://inspect/#remote-debugging`), and specific flag names and values. The instructions are directly executable. | 3 / 3 |
Workflow Clarity | The 6-step diagnostic process is clearly sequenced with explicit validation checkpoints. Step 2's DevToolsActivePort sub-workflow has a particularly strong feedback loop: verify Chrome running → enable debugging → call list_pages to validate → escalate only if still failing. Each step has clear conditions for proceeding. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sub-sections, but it's a fairly long monolithic document (~100 lines of substantive content). Some sections like the detailed error patterns or the configuration formulation guidance could be split into referenced files. However, the external references to GitHub docs and issues are well-signaled. | 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
- ChromeDevTools/chrome-devtools-mcp
- Commit
1b857c9
- 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.