troubleshooting

Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails.

1.08x

Quality

82%

Does it follow best practices?

Impact

89%

1.08x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

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.

A well-engineered diagnostic playbook: the triage section maps specific errors to exact remediation sequences, and every step carries executable commands, flags, or URLs. Weaknesses are minor — a few wordy framing sentences, inline version-number dependencies, and missing re-verification checkpoints after Steps 4-6 produce a fix.

Dimension	Reasoning	Score
Conciseness	The body is dense and instructional with exact flags, URLs, and commands, but carries minor trimmable elements ('You are acting as a troubleshooting wizard...', asides like 'This is the simplest and safest way...') and inline version numbers (Chrome 144+, 'Chrome before 149') that anchor it below the lean efficiency of a 5 and clearly above the noticeable verbosity of a 3.	4 / 5
Actionability	Fully executable throughout: exact config filenames (.mcp.json, .vscode/launch.json), the precise URL chrome://inspect/#remote-debugging, copy-paste flags (--browser-url=http://127.0.0.1:9222, --logFile, startup_timeout_ms 20000), and runnable commands (npx chrome-devtools-mcp@latest --help, DEBUG=* ... --logFile=/tmp/cdm-test.log, gh issue list ... --search).	5 / 5
Workflow Clarity	Six clearly sequenced steps with a genuine feedback loop in the DevToolsActivePort branch (confirm Chrome running, confirm remote debugging, verify via list_pages, then escalate), but Steps 4-6 (formulate config, run diagnostics, search GitHub) end without an explicit re-verification of the original failure, so it does not fully match anchor 5's checkpoints throughout.	4 / 5
Progressive Disclosure	No bundle files exist, so the single-file structure is judged on its own organization: clear step-based sections with well-signaled external references (GitHub troubleshooting doc, issues, discussions). It is not a 5 because the ~93-line body inlines the full error-triage catalog that could be split into reference files, and it exceeds the under-50-lines simple-skill exception.	4 / 5
	Total	17 / 20 Passed

Description

82%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 with an explicit 'Trigger this skill when...' clause anchored to concrete tool-failure symptoms, making both purpose and activation conditions unambiguous. The main gap is breadth: the capability statement covers only one action ('troubleshoot connection and target issues') and trigger coverage omits common user phrasings like 'won't connect' or 'server won't start'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Chrome DevTools MCP') and a concrete action ('troubleshoot connection and target issues'), but only 1-2 actions rather than the several specific actions of anchor 4; it is above anchor 2 because the actions and domain are concrete, not generic.	3 / 5
Completeness	Explicitly answers both: what ('Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues') and when ('Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails') with concrete trigger phrases, matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Triggers ('list_pages, new_page, or navigate_page fail', 'server initialization fails') are phrases users would genuinely paste from failing output, giving good coverage; not a 5 because common natural variations like 'won't connect' or 'Chrome won't start' are absent, and not a 3 because the listed terms are specific and naturally said rather than generic.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Chrome DevTools MCP connection troubleshooting) with distinct, tool-name-specific triggers that are unlikely to fire for other skills; no meaningful overlap risk.	5 / 5
	Total	17 / 20 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
Path: skills/troubleshooting/SKILL.md
Commit: 02c0112

Reviewed: 1 day 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.