CtrlK
BlogDocsLog inGet started
Tessl Logo

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

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

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 security boundaries. Its main weakness is length — it tries to cover too many sub-topics (UI debugging, network issues, performance, accessibility, security, test plans) in a single file without progressive disclosure, and includes some verbose sections like the rationalizations table and overview paragraph that don't add value for Claude. The security guidance is well-justified and appropriately detailed given the risk profile of browser interaction.

Suggestions

Trim the 'Overview' paragraph, 'Common Rationalizations' table, and 'When to Use' list — Claude can infer when to use browser DevTools from the skill description and context.

Split detailed sub-workflows (accessibility verification, console analysis patterns, test plan template) into separate referenced files to reduce the token footprint of the main SKILL.md.

DimensionReasoningScore

Conciseness

The skill is well-organized but includes some unnecessary verbosity. The 'When to Use' / 'When NOT to use' section, the 'Common Rationalizations' table, and the 'Overview' paragraph explain things Claude already understands. The Available Tools table describes obvious tool purposes. The content boundary ASCII art box is unnecessary. However, the security boundaries section earns its place given the safety-critical nature of browser interaction.

2 / 3

Actionability

The skill provides concrete, executable guidance throughout: a copy-paste ready MCP configuration JSON, structured debugging workflows with specific steps, a detailed test plan example with exact expected outcomes, and specific console analysis patterns. The workflows are specific enough to follow directly.

3 / 3

Workflow Clarity

Multi-step workflows are clearly sequenced with explicit validation checkpoints. The UI bug workflow includes a VERIFY step with screenshot comparison and console checks. The network issue workflow includes diagnosis decision trees. The performance workflow includes baseline/measure comparison. Each workflow has clear feedback loops (fix → verify → confirm).

3 / 3

Progressive Disclosure

The content is well-structured with clear headers and sections, but it's a monolithic document (~250 lines) with no references to external files. Several sections (the detailed test plan example, the accessibility verification checklist, the console analysis patterns) could be split into separate reference files. For a skill of this complexity, the lack of any bundle files or external references means everything is loaded into context at once.

2 / 3

Total

10

/

12

Passed

Description

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 articulates specific capabilities (DOM inspection, console error capture, network analysis, performance profiling, visual verification), provides explicit trigger guidance with two 'Use when' clauses, and is distinctly scoped to browser-based testing via Chrome DevTools MCP. The description is concise, uses third person voice, and includes natural keywords users would employ when needing this functionality.

DimensionReasoningScore

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 common variations of what users would mention when needing browser debugging.

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 the specific MCP server requirement. Unlikely to conflict with generic testing or non-browser debugging skills.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
addyosmani/agent-skills
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.