evaluate-ai-css-completion

Expose a temporary evaluation hook in DevTools and run a Puppeteer script to validate CSS code completion trigger rates.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/evaluate-ai-css-completion/SKILL.md

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 with executable code, clear sequencing, explicit checkpoints, and a properly referenced bundled script. The only weak spot is minor verbosity from the redundant introductory line and a few explanatory passages.

Suggestions

Remove or compress the opening restatement of the description so the body starts directly with the warning or Step 1.

Trim explanatory sentences that restate what the code already shows (e.g. 'The script will connect to the DevTools instance, trigger completions, and output the results').

Add an explicit 'verify the build succeeded before running the evaluation' checkpoint after the autoninja build in Step 3 to strengthen the validation gate.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with copy-paste code and commands earning their place, but the opening line restates the description ("This skill allows you to temporarily expose an evaluation hook...") and a few explanatory sentences could be tightened; not a 3 because of that redundancy.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: a complete TypeScript patch, an exact npm start command with flags, an autoninja build command, a node script command, and a git checkout revert command; matches the anchor for fully executable examples.	3 / 3
Workflow Clarity	Five steps are clearly sequenced with an explicit agent checklist requiring user confirmation in Step 2, a debugging/diagnostics feedback loop in Step 4, and a revert step in Step 5; it is above 2 because validation checkpoints and error-recovery guidance are explicit.	3 / 3
Progressive Disclosure	Well-organized into Steps 1–5 plus a debugging section, with a single one-level-deep reference to a real bundled script (scripts/evaluate.js, invoked at Step 4) and no nested references; matches the anchor for clear overview with well-signaled references.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 specific and clearly distinct, but it omits an explicit 'when to use' trigger clause, which caps completeness and leaves trigger-term coverage short of ideal. Adding consumer-facing trigger phrasing would raise the weaker dimensions.

Suggestions

Add a 'Use when...' clause stating when to invoke the skill (e.g. 'Use when you need to measure or test CSS code completion trigger rates in a local DevTools build').

Include more natural trigger terms users would actually say, such as 'test', 'measure', or 'benchmark' alongside 'validate'.

Soften technical jargon like 'evaluation hook' and 'trigger rates' with plainer phrasing to broaden natural-language matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person ("Expose a temporary evaluation hook in DevTools and run a Puppeteer script to validate CSS code completion trigger rates"), matching the anchor for listing several specific actions; it is above 2 because two distinct actions are named rather than a single vague one.	3 / 3
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent trigger guidance, so per the judging guideline completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	Domain keywords are present ("DevTools", "Puppeteer", "CSS code completion") but phrasing leans technical ("evaluation hook", "trigger rates") and lacks the common natural variations a user might say (e.g. "test", "measure"); not a 3 because coverage of natural trigger terms is incomplete.	2 / 3
Distinctiveness Conflict Risk	The niche is highly specific (measuring CSS code completion trigger rates in DevTools via Puppeteer), making it unlikely to trigger for the wrong skill; it clears the 2 anchor because the scope is unambiguous.	3 / 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/evaluate-ai-css-completion/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.