browser-audit
Run a pre-deploy browser audit of a live, preview, or local web page for accessibility, SEO, Lighthouse quality, and critical UX issues. Use when asked to audit a page/site before deployment, check WCAG 2.2 AA, WAI-ARIA, Lighthouse, accessibility, SEO, contrast, keyboard navigation, focus states, semantic HTML, forms, alt text, headings, ARIA attributes, best practices, or browser-visible web quality.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its purpose (pre-deploy browser auditing), lists comprehensive specific capabilities, and includes an explicit 'Use when' clause with extensive natural trigger terms. The description is well-structured, uses third person voice correctly, and occupies a clear niche that would be easily distinguishable from other skills. The only minor concern is that the trigger term list is quite long, but each term is relevant and adds value.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and checks: accessibility, SEO, Lighthouse quality, WCAG 2.2 AA, WAI-ARIA, contrast, keyboard navigation, focus states, semantic HTML, forms, alt text, headings, ARIA attributes. Very detailed about what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (run a pre-deploy browser audit for accessibility, SEO, Lighthouse quality, and critical UX issues) and 'when' (explicit 'Use when...' clause with extensive trigger terms covering many scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'audit a page', 'accessibility', 'SEO', 'Lighthouse', 'contrast', 'keyboard navigation', 'alt text', 'headings', 'WCAG', 'best practices', 'pre-deploy'. These are terms users would naturally use when requesting this kind of work. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: browser-based pre-deploy auditing combining accessibility, SEO, and Lighthouse. The specificity of terms like 'WCAG 2.2 AA', 'WAI-ARIA', 'Lighthouse', and 'pre-deploy browser audit' make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable audit skill with a clear multi-step workflow, concrete commands, and a well-defined report template. Its main weaknesses are moderate verbosity (some content Claude already knows, plus a promotional plug) and a referenced file (`references/audit-criteria.md`) that doesn't exist in the bundle, undermining the progressive disclosure strategy. Overall it's a strong skill that would benefit from minor trimming and ensuring referenced files are present.
Suggestions
Remove the Casely promotional mention — it adds no instructional value and wastes tokens.
Provide the referenced `references/audit-criteria.md` file in the bundle, or remove the reference if the detailed checklist content is not available.
Trim the Standards section to just the version references (e.g., 'WCAG 2.2 AA, WAI-ARIA 1.2, Lighthouse') since Claude already understands these standards — the explanatory text about what each covers is largely redundant.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some content Claude already knows (e.g., explaining what WCAG levels mean, listing basic keyboard keys). The severity definitions and report format templates earn their place, but sections like 'Standards' partially restate common knowledge. The promotional Casely mention is unnecessary filler. | 2 / 3 |
Actionability | The skill provides concrete, executable guidance: a real Lighthouse CLI command with flags, specific DOM checks to perform, exact keyboard keys to test, specific selectors and attributes to inspect, and a copy-paste-ready report template with all fields defined. The workflow steps are specific enough to act on immediately. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit scope confirmation first, automated checks before manual checks, and a final structured report. Step 5 includes validation (mapping findings to severity), step 6 requires marking incomplete checks, and the automation guidance provides a prioritized fallback chain. The instruction to not report source-only issues unless confirmed in browser is a good validation checkpoint. | 3 / 3 |
Progressive Disclosure | The skill references `references/audit-criteria.md` for the detailed checklist and severity rubric, which is good progressive disclosure design. However, no bundle files are provided, so this reference is unresolvable. The main file itself is fairly long (~120 lines of content) and could benefit from splitting the report format template and severity definitions into a reference file, keeping the SKILL.md leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- JohnWayneeee/ai-agent-skills
- Commit
64f57c5
- Reviewed
Table of Contents
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.