chrome-devtools-cli

Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.

1.22x

Quality

—

Does it follow best practices?

Impact

81%

1.22x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

The body is highly actionable with comprehensive executable command examples and a clear usage workflow, but it is weighed down by an exhaustive inline flag catalog that would be better as a reference file, and its workflow omits explicit result-verification steps.

Suggestions

Move the exhaustive per-command flag catalog into a references file (e.g. references/commands.md) and keep only the core workflow plus a few representative examples in SKILL.md.

Add an explicit verification step to the AI Workflow, e.g. re-snapshot after acting to confirm the page reached the expected state before proceeding.

Trim redundant flag-variant lines that duplicate --help output to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body avoids concept explanations and keeps lines tight, but it inlines an exhaustive enumeration of every command and flag variant (~100 lines) that Claude could largely obtain from --help and could be tightened or moved to a reference.	2 / 3
Actionability	It provides fully executable, copy-paste-ready `chrome-devtools` commands with concrete arguments and flags across all categories, plus a clear invocation pattern.	3 / 3
Workflow Clarity	The AI Workflow section gives a clear Execute → Inspect → Act sequence with a snapshot feedback mechanism, but it lacks explicit verification checkpoints confirming that an action produced the expected page state.	2 / 3
Progressive Disclosure	Installation is correctly split into a clearly signaled one-level reference, but the large command/flag catalog is kept inline in SKILL.md rather than moved to a separate API reference file.	2 / 3
	Total	9 / 12 Passed

Description

57%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly identifies a distinct niche (Chrome DevTools CLI browser automation) and names concrete actions, but it lacks an explicit trigger clause and omits common natural-language variations users would actually say. It is competent but not optimally discoverable.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when automating the browser, controlling Chrome from the command line, or interacting with page elements via DevTools."

Include user-facing terms like "browser automation", "control Chrome", or "interact with web pages" alongside the technical "Chrome DevTools via CLI" phrasing.

Replace the generic "automate tasks in the browser" with more concrete actions (e.g. click, fill forms, navigate, take snapshots) to raise specificity.

Dimension	Reasoning	Score
Specificity	It names the domain and several actions ("write shell scripts", "run shell commands", "use Chrome DevTools via CLI"), but "automate tasks in the browser" is generic filler rather than a comprehensive list of concrete actions.	2 / 3
Completeness	It states what the skill does but provides no explicit "Use when..." trigger clause, so the "when to use it" half is only implied, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Relevant keywords appear ("shell scripts", "browser", "Chrome DevTools", "CLI"), but common natural variations a user would say ("browser automation", "control Chrome", "scrape a page", "click a button") are missing.	2 / 3
Distinctiveness Conflict Risk	The Chrome DevTools CLI browser-automation niche is specific and clearly distinct from other skills, making wrong-skill triggering unlikely despite the generic "shell scripts" opening.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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
Commit: e5bd334

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.