browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 what the skill does (browser testing and debugging via Chrome DevTools) and when to use it (building or debugging browser-based applications). It lists multiple specific capabilities as trigger terms and is well-scoped to avoid conflicts with other skills. The prerequisite mention of the chrome-devtools MCP server adds helpful context.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: inspect the DOM, capture console errors, analyze network requests, profile performance, verify visual output with real runtime data. | 3 / 3 |
Completeness | Clearly answers both what (tests in real browsers, inspect DOM, capture console errors, analyze network requests, profile performance, verify visual output) and when ('Use when building or debugging anything that runs in a browser'). Includes explicit 'Use when' clauses. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'browser', 'DOM', 'console errors', 'network requests', 'performance', 'visual output', 'Chrome DevTools'. These cover a good range of how users would describe browser debugging needs. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to browser-based testing via Chrome DevTools MCP, with distinct triggers like DOM inspection, console errors, network requests, and performance profiling. The mention of the specific MCP server requirement further narrows its niche and reduces conflict risk. | 3 / 3 |
Total | 12 / 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, actionable skill with excellent workflow clarity and thorough coverage of browser debugging scenarios. Its main weakness is length — at ~250 lines with no bundle files, it tries to be both overview and comprehensive reference, which hurts conciseness and progressive disclosure. The security boundaries section is valuable but could be more concise, and motivational content like the 'Common Rationalizations' table adds tokens without adding actionable guidance.
Suggestions
Extract the detailed security boundaries, test plan template, and accessibility verification guide into separate referenced files (e.g., SECURITY.md, TEST_PLAN_TEMPLATE.md, ACCESSIBILITY.md) to improve progressive disclosure and reduce the main file's token footprint.
Remove or significantly trim the 'Common Rationalizations' table — it's motivational rather than instructional and Claude doesn't need persuasion to follow its own skill instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-organized but includes some unnecessary content that Claude already knows — the 'Common Rationalizations' table is motivational rather than instructional, the 'When to Use / When NOT to use' section is somewhat obvious, and the overview paragraph restates what the description already conveys. The security boundaries section, while important, is verbose and could be tightened. However, most content does earn its place. | 2 / 3 |
Actionability | The skill provides concrete, structured workflows with specific steps, a detailed test plan example with exact expected outcomes, clear tool descriptions with use cases, and specific patterns for console analysis and accessibility verification. The installation config is copy-paste ready, and the debugging workflows give precise decision trees (e.g., 4xx → client error, 5xx → server error). | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit validation checkpoints throughout — the UI bug workflow has a dedicated VERIFY step with screenshot comparison and console checks, the network workflow includes diagnosis decision trees, and the performance workflow includes baseline/measure comparison. The test plan example demonstrates feedback loops with expected outcomes at each step and a final verification checklist. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a monolithic document (~250 lines) with no references to external files. The detailed test plan example, the full security boundaries section, and the accessibility verification guide could be split into separate referenced files. For a skill of this complexity, some content should be offloaded to keep the main SKILL.md as an overview. | 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
- addyosmani/agent-skills
- Commit
f17c6e8
- 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.