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).
89
87%
Does it follow best practices?
Impact
89%
2.28xAverage 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 weakness is that the capability descriptions could be more granular—listing specific concrete actions rather than broad categories like 'debugging' and 'troubleshooting'.
Suggestions
Add more specific concrete actions such as 'set breakpoints, capture screenshots, inspect DOM elements, monitor console logs, profile page load times' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Chrome DevTools, browser automation, debugging) and mentions several action areas (debugging, troubleshooting, performance analysis, network inspection), but doesn't list multiple concrete granular actions like 'set breakpoints, capture screenshots, modify DOM elements'. | 2 / 3 |
Completeness | Clearly answers both 'what' (Chrome DevTools via MCP for debugging, troubleshooting, browser automation) and 'when' with an explicit 'Use when...' clause covering debugging, automating, performance analysis, and network inspection. Also includes a helpful exclusion note about slim mode. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'debugging web pages', 'browser automation', 'performance', 'network requests', 'Chrome DevTools', 'browser interactions'. These cover the main ways users would phrase requests in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | 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 testing skills. | 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 main strength is clear workflow sequencing and token efficiency. Its primary weakness is the lack of concrete, executable tool call examples — showing at least one complete tool invocation with parameters would significantly improve actionability.
Suggestions
Add one concrete, complete tool call example (e.g., a full navigate → wait → snapshot → click sequence with actual parameter values) to improve actionability.
Include a brief example showing the `filePath` parameter usage or `includeSnapshot: false` in context, since these are non-obvious optimization tips that benefit from concrete illustration.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude knows what Chrome DevTools, MCP, accessibility trees, and UIDs are. Every section delivers information Claude wouldn't already know (tool-specific parameters, workflow ordering, troubleshooting links) without padding. | 3 / 3 |
Actionability | The guidance is concrete in terms of tool names, parameter names, and workflow ordering, but lacks executable code examples or copy-paste ready tool call examples. The instructions reference tools like `take_snapshot`, `click`, `fill` but never show a concrete invocation with parameters. | 2 / 3 |
Workflow Clarity | The 'Before interacting with a page' workflow is clearly sequenced (navigate → wait → snapshot → interact) with explicit ordering constraints. The parallel execution section reinforces correct ordering. The troubleshooting section provides fallback paths. For this type of tool-orchestration skill, the workflow is unambiguous. | 3 / 3 |
Progressive Disclosure | The content is well-organized into logical sections (Core Concepts, Workflow Patterns, Troubleshooting) with clear navigation. External references (troubleshooting docs, DevTools docs) are one level deep and clearly signaled. The skill is appropriately concise for a single SKILL.md without needing additional files. | 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
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.