frontend-quality-auditor
Skill136 starsChanged 5 months agoMITView on GitHub
Audit launch readiness; report ship/no-ship.
In this repository80 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-audit-websitesSkill
- accessibility-performance-polishSkill
- agent-evaluation-operationsSkill
- agent-memory-provenanceSkill
- agent-orchestration-architectureSkill
- animation-easing-languageSkill
- animation-jank-qaSkill
- animation-tool-routerSkill
- anti-generic-website-reviewSkill
- brand-voice-to-ui-copySkill
- browser-inspection-workflowSkill
- code-change-safety-checkpointSkill
- code-change-undo-revertSkill
- color-material-lighting-directionSkill
- content-pruning-reviewSkill
- content-structure-information-architectureSkill
- conversion-forms-checkout-polishSkill
- creativitySkill
- critical-thinkingSkill
- cross-browser-qaSkill
- css-grid-editorial-systemsSkill
- cta-language-systemsSkill
- deep-researchSkill
- design-motion-principlesSkill
- editorial-typography-systemsSkill
- evidence-reconciliationSkill
- final-client-handoffSkill
- frontend-tooling-trust-gateSkill
- gsap-performanceSkill
- hero-image-art-directionSkill
- image-crop-responsive-qaSkill
- image-video-loading-qaSkill
- logical-thinkingSkill
- mobile-responsive-qaSkill
- modern-site-engineeringSkill
- motion-language-directorSkill
- motion-performance-qaSkill
- motion-react-layout-transitionsSkill
- motion-react-microinteractionsSkill
- motion-react-page-transitionsSkill
- motion-react-patternsSkill
- nextjs-app-router-routingSkill
- nextjs-server-client-boundariesSkill
- nextjs-site-architectureSkill
- non-generic-web-copySkill
- performance-audit-websitesSkill
- performance-budget-labSkill
- premium-visual-reference-librarySkill
- premium-web-build-gateSkill
- radix-accessible-primitivesSkill
- react-accessible-componentsSkill
- react-component-compositionSkill
- react-component-craftSkill
- react-error-loading-empty-statesSkill
- react-form-patternsSkill
- react-responsive-componentsSkill
- react-state-and-effects-disciplineSkill
- reduced-motion-designSkill
- responsive-visual-polish-qaSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill to decide whether a frontend is ready to ship and what should be fixed first.
- Very specific: line 19
Check the launch-critical surfaces: hero or first screen, navigation, primary CTA, forms, media, interactive states, footer, …
- Distinctive: line 54
Use this structure unless the user asks for something else:
- Very specific: line 63
Read references/audit-checklist.md for the full checklist when performing a complete launch-readiness review.
- Very specific: line 67
Add insufficient evidence / not assessed when source-only or sampled evidence cannot support readiness.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Frontend Quality Auditor
Use this skill to decide whether a frontend is ready to ship and what should be fixed first.
Core Contract
Produce a concise, evidence-based quality report. Do not redesign the product unless the user explicitly asks for fixes. The default output is an audit, not a rebuild.
Audit Workflow
- Identify the project type, framework, entry routes, styling system, scripts, and available preview or deployment URL.
- Inspect source structure first, then inspect rendered output when a browser or screenshot workflow is available.
- Review desktop and mobile breakpoints before judging visual quality.
- Check the launch-critical surfaces: hero or first screen, navigation, primary CTA, forms, media, interactive states, footer, error/loading/empty states, and any checkout, booking, pricing, or dashboard flows.
- Classify issues by severity:
- Blocker: likely broken, inaccessible, misleading, unusable, or launch-damaging.
- High: visibly unprofessional, confusing, slow, fragile, or trust-reducing.
- Medium: polish, consistency, or resilience issue worth fixing soon.
- Low: minor refinement that should not block launch.
- Recommend the smallest useful next action for each meaningful issue.
- End with a clear Ship, Ship after fixes, or Do not ship yet judgment.
Review Areas
- Visual polish: hierarchy, spacing, typography, alignment, density, color, contrast, icon use, media treatment, empty space, and generic AI-looking patterns.
- Responsive behavior: mobile composition, tablet layout, overflow, touch targets, nav behavior, media crops, and text wrapping.
- Accessibility: semantic structure, headings, labels, focus states, keyboard paths, alt text, contrast, reduced motion, ARIA misuse, and modal/menu behavior.
- Performance: image and video weight, layout shift risk, font loading, animation cost, bundle hints, third-party scripts, and Core Web Vitals concerns.
- SEO and sharing basics: title, description, canonical, Open Graph, heading order, crawlable content, image alt text, sitemap/robots signals when relevant.
- Interaction quality: hover, focus, active, disabled, loading, error, success, offline, retry, and empty states.
- Content and trust: vague claims, placeholder copy, weak CTAs, unsupported proof, unclear pricing or contact flows, missing legal or support signals where expected.
Use Specialist Skills When Available
Route deep follow-up work to focused skills instead of bloating this audit:
browser-inspection-workflowfor rendered browser inspection and evidence capture.visual-polish-qaorresponsive-visual-polish-qafor visual fixes.mobile-responsive-qafor phone and tablet layout issues.accessibility-audit-websitesfor detailed accessibility remediation.performance-audit-websitesorperformance-budget-labfor speed and Core Web Vitals.seo-technical-qafor launch SEO checks.cross-browser-qafor browser compatibility.anti-generic-website-reviewfor generic AI output and weak design patterns.content-pruning-review,non-generic-web-copy, orcta-language-systemsfor copy and conversion clarity.
Output Format
Use this structure unless the user asks for something else:
- Verdict: Ship, ship after fixes, or do not ship yet.
- Top Risks: The material issues most likely to affect users or trust, if any; do not invent a minimum count.
- Findings: Severity, location, evidence, impact, and recommended fix.
- Quick Wins: Small improvements with high visible payoff.
- Specialist Follow-Ups: Which focused skills or checks should be run next.
- Verification Notes: Commands, URLs, viewports, screenshots, and checks actually performed.
Read references/audit-checklist.md for the full checklist when performing a complete launch-readiness review.
Scope and evidence
Add insufficient evidence / not assessed when source-only or sampled evidence cannot support readiness. Qualify every verdict by surface and claimed stage. Recommendations remain recommendations in an analysis-only audit.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

