devtools-verification

MANDATORY: Activate this skill ANY TIME you need to build the project, run tests, or verify code health in DevTools. You MUST use this skill before executing commands like npm test, npm run build, autoninja, or linters, as it contains critical, repository-specific instructions on how to correctly format these commands, filter test runs, and interpret failures.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 body is concise and highly actionable with concrete, executable repo-specific commands well-organized into clear sections. Its main weakness is workflow clarity: it lists commands but lacks explicit sequencing and validation checkpoints for the build/test/verify cycle it describes.

Suggestions

Add a short verification workflow that sequences the steps, e.g. lint -> build -> run affected tests -> git cl presubmit, so Claude knows the order of operations.

Include an explicit validation checkpoint for build/test runs (e.g. 'Only proceed if tests pass; if autoninja reports errors, fix them before continuing') to add a feedback loop.

Clarify how to interpret failures (the description promises this) with a brief pointer on reading test/build output rather than leaving it implied.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient - short bullet points with concrete commands and no explanation of concepts Claude already knows; every line carries actionable information about repo-specific commands.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands like `npm run test -- <FILEPATH>`, `autoninja -C out/Default`, `npm run lint -- <PATH>`, and `git cl presubmit -u` with concrete path conventions and examples.	3 / 3
Workflow Clarity	Sections are clearly organized by task (Testing, Building, Linting, Best practices) but there are no validation checkpoints or feedback loops - e.g. it lists running tests and builds but does not sequence how to verify changes or recover from failures, which the guidelines call out for verification workflows.	2 / 3
Progressive Disclosure	For a simple skill under 50 lines with no external references needed, the content is well-organized into clear sections covering each verification task, which the simple-skills scoring note allows to score 3.	3 / 3
	Total	11 / 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 specificity and completeness, clearly stating both capabilities and explicit trigger conditions. It is weakened by verbose imperative framing ('MANDATORY', 'You MUST') that inflates token count without adding trigger coverage, and its triggers are somewhat generic across build/test tasks.

Suggestions

Trim imperative fluff like 'MANDATORY:', 'ANY TIME', and 'You MUST use this skill' to reduce verbosity; the trigger conditions stand on their own.

Add more natural user-spoken trigger variations (e.g. 'run the linter', 'check my build', 'run a specific test') to broaden trigger-term coverage.

Sharpen distinctiveness by foregrounding the DevTools-specific tooling (autoninja, git cl presubmit) earlier so it reads as a DevTools-only skill rather than a generic build/test helper.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions - 'build the project, run tests, or verify code health' and 'format these commands, filter test runs, and interpret failures' - matching the top anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers what it does (repository-specific instructions on formatting commands, filtering test runs, interpreting failures) and when to use it ('ANY TIME you need to build the project, run tests, or verify code health') with explicit triggers.	3 / 3
Trigger Term Quality	Includes natural terms users would say ('build the project', 'run tests', 'npm test', 'npm run build') but is padded with imperative directives ('MANDATORY', 'ANY TIME', 'You MUST') rather than covering common natural variations of triggers.	2 / 3
Distinctiveness Conflict Risk	Scoped to DevTools with repository-specific commands like 'autoninja' and 'git cl presubmit', but 'build the project, run tests, verify code health' is generic enough that it could overlap with other generic build/test skills in different repos.	2 / 3
	Total	10 / 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/devtools-frontend
Path: .agents/skills/devtools-verification/SKILL.md
Commit: 184a74d

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.