chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).
90
87%
Does it follow best practices?
Impact
94%
1.59xAverage 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 solid skill description that clearly communicates its purpose and when to use it. It has good trigger term coverage and explicit 'Use when' guidance with a helpful exclusion clause. The main area for improvement is adding more specific concrete actions beyond the high-level categories of debugging, automation, and performance analysis.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'capture screenshots, read console logs, click elements, evaluate JavaScript, monitor DOM changes' rather than just high-level categories.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Chrome DevTools, browser automation, debugging) and mentions several actions (debugging, troubleshooting, browser automation, analyzing performance, inspecting network requests), but these are somewhat high-level categories rather than multiple specific concrete actions like 'click elements, capture screenshots, read console logs, set breakpoints'. | 2 / 3 |
Completeness | Clearly answers both 'what' (uses Chrome DevTools via MCP for debugging, troubleshooting, and browser automation) and 'when' (explicit 'Use when' clause covering debugging web pages, automating browser interactions, analyzing performance, inspecting network requests). Also includes a helpful exclusion clause about slim mode. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'debugging', 'web pages', 'browser', 'performance', 'network requests', 'Chrome DevTools', 'browser automation', 'MCP'. These cover a good range of how users would naturally phrase requests involving browser debugging and automation. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Chrome DevTools via MCP, which is a distinct niche. The mention of MCP, Chrome DevTools, and browser-specific actions makes it unlikely to conflict with general coding or debugging skills. The exclusion of slim mode further sharpens its boundaries. | 3 / 3 |
Total | 11 / 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 well-structured, concise skill that efficiently communicates Chrome DevTools MCP usage patterns. Its strengths are excellent organization, clear workflow sequencing, and token efficiency. The main weakness is that it relies on tool name references rather than providing executable code examples or concrete input/output demonstrations, which slightly limits actionability.
Suggestions
Add a concrete example showing a complete interaction sequence with actual tool call parameters (e.g., a `take_snapshot` call followed by a `click` with a specific uid format) to improve actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows what Chrome DevTools, MCP, accessibility trees, and UIDs are. No unnecessary explanations of basic concepts. Every section delivers actionable information without padding. | 3 / 3 |
Actionability | The skill provides clear tool names and parameter references (e.g., `filePath`, `pageIdx`, `includeSnapshot: false`) and describes workflows with specific tool sequences, but lacks executable code examples or copy-paste ready commands. The guidance is concrete but stops short of fully executable examples. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced (navigate → wait → snapshot → interact) with explicit ordering constraints. The extension testing workflow has 5 clear steps. The troubleshooting section provides fallback paths. The 'take a fresh snapshot' guidance serves as an implicit validation/recovery step for element interaction. | 3 / 3 |
Progressive Disclosure | Content is well-organized into logical sections (Core Concepts, Workflow Patterns, Troubleshooting) with clear headers and subsections. External references are one level deep and clearly signaled (Chrome DevTools docs, troubleshooting guide). For a skill of this size with no bundle files, the structure is appropriate and easy to navigate. | 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
- ChromeDevTools/chrome-devtools-mcp
- Commit
2e039c0
- 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.