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.

1.52x

Quality

—

Does it follow best practices?

Impact

90%

1.52x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

The content is highly actionable and clearly sequenced with concrete commands and verification loops. The main weakness is progressive disclosure: the guide is a single inline document rather than an overview with clearly signaled, one-level-deep reference files, and it carries minor verbosity.

Suggestions

Split the per-symptom/error reference detail (DevToolsActivePort, empty profile, missing tools, extensions) into a separate reference file (e.g., ERROR-REFERENCE.md) and keep SKILL.md as a concise overview that links to it.

Trim softening prose such as 'This is the simplest and safest way to verify' and 'your primary goal is to guide the user' so every token earns its place.

Proofread for typos like '--autoBronnect' and 'in configured' to keep the executable guidance reliable.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes competence, listing concrete errors, flags, commands, and URLs without explaining basic concepts, but a few softening sentences ('This is the simplest and safest way to verify', 'your primary goal is to guide the user') and minor typos could be tightened, placing it between the level-2 and level-3 anchors.	2.5 / 3
Actionability	It provides fully executable, copy-paste-ready guidance — specific flags (--autoConnect, --browserUrl, --categoryExtensions, --slim, --logFile), an exact URL to navigate (chrome://inspect/#remote-debugging), and concrete commands (npx chrome-devtools-mcp@latest --help, DEBUG=* ... --logFile=/tmp/cdm-test.log, gh issue list ...) — matching the level-3 anchor.	3 / 3
Workflow Clarity	It presents a clear six-step sequence with explicit gating checkpoints and recovery loops ('Once the user confirms both steps, your only next action should be to call list_pages'; 'If list_pages succeeds, the problem is resolved. If it still fails ... then you can proceed'), matching the level-3 anchor for clear sequencing with feedback loops.	3 / 3
Progressive Disclosure	The body is well-organized into labeled sections (Step N, Error:/Symptom:) and so is not a monolithic wall, but at ~95 lines it exceeds the under-50-line leniency and keeps all per-symptom detail inline with only an external doc URL rather than well-signaled one-level-deep reference files, matching the level-2 anchor where content that could be separate is inline.	2 / 3
	Total	10.5 / 12 Passed

Description

82%

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 is strong on completeness and distinctiveness, with an explicit trigger clause and a clearly scoped niche. Specificity is moderate because 'troubleshoot' bundles several actions rather than enumerating them, and trigger terms, while concrete, are somewhat technical.

Suggestions

Replace the broad verb 'troubleshoot' with a short list of concrete actions (e.g., 'diagnose connection failures, fix flag misconfiguration, and resolve missing-tool errors').

Add a few natural-language trigger variations users might say (e.g., 'when Chrome DevTools tools are missing' or 'when the browser won't connect') alongside the tool-name triggers.

Dimension	Reasoning	Score
Specificity	The description names the domain and a general action ('troubleshoot connection and target issues') but does not enumerate multiple distinct concrete actions, matching the level-2 anchor 'Names domain and some actions, but not comprehensive'; it falls short of level 3 which requires listing several specific actions.	2 / 3
Completeness	It clearly answers both 'what' ('Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues') and 'when' via an explicit 'Trigger this skill when ...' clause, matching the level-3 anchor with explicit trigger guidance.	3 / 3
Trigger Term Quality	It provides concrete, relevant triggers ('list_pages, new_page, or navigate_page fail', 'server initialization fails') that a user in a failure state would naturally surface, exceeding the level-2 'some relevant keywords' anchor, but they lean tool-internal and technical rather than offering broad natural-language variations, stopping short of comprehensive level-3 coverage.	2.5 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to Chrome DevTools MCP with triggers tied to specific tool failures, making it unlikely to fire for unrelated skills, matching the level-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10.5 / 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.