CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

88

1.24x
Quality

Does it follow best practices?

Impact

66%

1.24x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable body with clear sequenced workflows and explicit verification steps. The main weakness is mild redundancy around the extension flag and an inline config block that slightly inflate the token budget.

Suggestions

De-duplicate the `--categoryExtensions` guidance: state the flag once in Core Concepts and have the Testing-an-extension section reference it rather than repeat the MCP JSON config.

Move the full `mcpServers` JSON config and the extension-testing details into a references file (e.g. references/extensions.md) and link to it from the body to keep SKILL.md a lean overview.

Tighten the Troubleshooting section by collapsing the two DevTools doc links and the troubleshooting.md link into a single one-line pointer.

DimensionReasoningScore

Conciseness

Mostly efficient and tool-name-driven, but the extension-testing block repeats the `--categoryExtensions` flag already given in Core Concepts and embeds a full `mcpServers` JSON config that pads the overview. It could be tightened to earn the score-3 'every token earns its place' bar.

2 / 3

Actionability

Provides executable, copy-paste-ready guidance: named tools, concrete parameters (`filePath`, `pageIdx`, `pageSize`, `includeSnapshot: false`), CLI flags, and a complete `mcpServers` JSON config, plus a numbered procedure mapping each step to a specific tool.

3 / 3

Workflow Clarity

Sequences are explicit (navigate → wait → snapshot → interact) and the extension procedure includes explicit verification checkpoints (verify service worker, verify page behavior) plus a retry loop when an element is not found.

3 / 3

Progressive Disclosure

No bundle files exist and none are referenced; the skill is a self-contained, cleanly sectioned overview (Core Concepts, Workflow Patterns, Troubleshooting), which is appropriate for its scope and avoids nested references.

3 / 3

Total

11

/

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.

A concise, well-targeted description that answers both what the skill does and when to use it with natural trigger terms and a clear disambiguating scope note. It is clearly distinguishable from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "debugging, troubleshooting and browser automation" and "debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests" — rather than vague language. It exceeds the score-2 bar of naming only some actions.

3 / 3

Completeness

Explicitly states what it does ("Uses Chrome DevTools via MCP for efficient debugging...") and when to use it via a clear "Use when..." clause, plus a scope exclusion for `--slim` mode. The explicit trigger means it is not capped at 2.

3 / 3

Trigger Term Quality

Covers natural user terms — "debugging web pages", "automating browser interactions", "analyzing performance", "inspecting network requests" — the phrases a user would actually say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

The "Chrome DevTools via MCP" niche with distinct triggers (web debugging, performance, network inspection) and the `--slim` exclusion make it unlikely to fire for the wrong skill.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ChromeDevTools/chrome-devtools-mcp
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.