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).

87

1.08x
Quality

80%

Does it follow best practices?

Impact

100%

1.08x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

The body is a well-structured, highly actionable MCP tool guide: concrete tool names, parameters, flags, and a copy-paste config, with clear ordered workflows and verification steps in the extension testing flow. Weaknesses are minor — a couple of trimmable phrases, a typo, and no failure-handling guidance after verification steps.

DimensionReasoningScore

Conciseness

The body is dense and tool-focused with almost no explanation of concepts Claude already knows (e.g., "Use `take_snapshot` to get page structure with element `uid`s"). A few phrases could be trimmed ("Treat the output as authoritative and complete.") and there is a typo ("Addional"), so it is efficient with minor instances of over-explanation rather than the lean anchor 5.

4 / 5

Actionability

Fully executable guidance for an MCP-tool skill: exact tool names and parameters (`pageId`, `filePath`, `includeSnapshot: false`, `pageIdx`/`pageSize`), CLI flags (`--categoryExtensions`, `--memoryDebugging`), a copy-paste JSON server config, and specific service-worker evaluation instructions. As an instruction-only skill, the guidance is concrete and covers the common cases, matching anchor 5.

5 / 5

Workflow Clarity

Clear sequences with explicit ordering ("navigate → wait → snapshot → interact") and a 5-step extension workflow that includes verification steps ("Verify Service Worker", "Verify Page Behavior") plus an error-recovery hint ("If an element isn't found, take a fresh snapshot"). Below anchor 5 because there is no guidance on what to do when a verification step fails; above anchor 3 because checkpoints are present and explicit.

4 / 5

Progressive Disclosure

No bundle files exist, and the body (~70 lines) is well-organized into Core Concepts, Workflow Patterns, and Troubleshooting with external links clearly signaled and grouped in Troubleshooting. All inline content belongs inline, but the body slightly exceeds the under-50-line threshold where good sections alone earn a 5, so anchor 4's 'good structure, minor organization gaps' is the closest fit.

4 / 5

Total

17

/

20

Passed

Description

78%Weight 40%Scale 1-5

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 strong description: third-person, explicit 'Use when' triggers, and a clear MCP-scoped niche. Its main weakness is that the stated capabilities are generic verbs (debugging, troubleshooting) rather than concrete operations, and a few natural trigger synonyms are missing.

Suggestions

Replace generic verbs with concrete operations, e.g. "take page snapshots, click/fill elements by uid, capture screenshots and network traces" instead of "efficient debugging, troubleshooting and browser automation".

Add common user phrasings to the trigger clause, such as 'screenshots of a page', 'scraping page content', or 'testing a Chrome extension'.

DimensionReasoningScore

Specificity

Names the domain ("Chrome DevTools via MCP") and several capability areas ("debugging, troubleshooting and browser automation"), but the actions are generic high-level verbs rather than concrete operations like 'take snapshots' or 'fill forms'. Fits anchor 3 (domain plus actions, not comprehensive) better than anchor 4, which expects several specific concrete actions; it is above anchor 2 because the domain is clearly named with multiple capability areas.

3 / 5

Completeness

Explicitly answers both: what ("Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation") and when ("Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests") with concrete trigger phrases. Matches anchor 5 exactly; anchor 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

"Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests" provides good natural phrases users would say. Missing a few common variations and synonyms (e.g., 'screenshots', 'scraping', 'testing an extension'), so it does not reach anchor 5's comprehensive synonym coverage; it clearly exceeds anchor 3's partial keyword coverage.

4 / 5

Distinctiveness Conflict Risk

"Uses Chrome DevTools via MCP" carves out a clear niche with tool-specific triggers, and the "--slim" mode boundary note further scopes it. Minor overlap risk remains with generic web-debugging or automation skills ("debugging web pages" alone is broad), keeping it below anchor 5.

4 / 5

Total

16

/

20

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 — 16 / 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.