agentleFS
Sign inStart free
phoenixvnphoenixvn/claude-code-agency/.claude/skills/qa/SKILL.md

qa

Skill0 starsChanged 7 months agoMITView on GitHub

Multi-dimensional quality assessment: functional, performance, accessibility, security. "Which quality dimensions?" (multiSelect) - Functional Testing - Performance (Core Web Vitals) - Accessibility (WCAG 2.1) - Security (OWASP) - All performance-analyst: - Lighthouse audit (Performance, Best Practices, SEO scores) - Core Web Vitals: LCP < 2.5s, FID < 100ms, CLS < 0.1 - Bundle size analysis - Image optimization check accessibility-specialist: - WCAG 2.1 AA compliance audit - Keyboard-only navigation test - Screen reader compatibility - Color contrast verification (4.5:1 minimum) -…

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write test cases from acceptance criteria or requirements

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/qa — Full QA Pipeline

Multi-dimensional quality assessment: functional, performance, accessibility, security.

Instructions

Phase 1: Scope

Use AskUserQuestion: "What to test?"

  • Full site/application
  • Specific feature (specify)
  • Specific page (specify)

"Which quality dimensions?" (multiSelect)

  • Functional Testing
  • Performance (Core Web Vitals)
  • Accessibility (WCAG 2.1)
  • Security (OWASP)
  • All

Phase 2: Test Planning

Spawn qa-lead to:

  • Define test strategy based on project type and scope
  • Write test cases from acceptance criteria or requirements
  • Prioritize: critical user paths first, then edge cases

Phase 3: Functional Testing

Spawn qa-tester to:

  • Execute test cases against acceptance criteria
  • Cross-browser check (Chrome, Firefox, Safari, Edge)
  • Responsive testing (mobile 375px, tablet 768px, desktop 1440px)
  • Form validation (valid/invalid inputs, required fields)
  • Error handling (network errors, 404s, edge cases)
  • Navigation flows (all links work, breadcrumbs correct)

Phase 4: Non-functional Testing (parallel)

Spawn selected specialists:

performance-analyst:

  • Lighthouse audit (Performance, Best Practices, SEO scores)
  • Core Web Vitals: LCP < 2.5s, FID < 100ms, CLS < 0.1
  • Bundle size analysis
  • Image optimization check

accessibility-specialist:

  • WCAG 2.1 AA compliance audit
  • Keyboard-only navigation test
  • Screen reader compatibility
  • Color contrast verification (4.5:1 minimum)
  • Focus management and skip links

security-auditor:

  • OWASP Top 10 quick assessment
  • Security headers check (CSP, HSTS, X-Frame-Options)
  • Authentication/authorization review
  • Dependency vulnerability scan (npm audit)

Phase 5: Bug Report

Compile findings with severity:

  • Critical: Blocks usage, data loss, security vulnerability
  • Major: Significant UX issue, broken feature
  • Minor: Cosmetic issue, edge case
  • Enhancement: Improvement suggestion

Each bug: Severity | Description | Steps to Reproduce | Expected vs Actual | Location

Phase 6: Quality Score

Calculate readiness:

  • 0 Critical + 0 Major = Ready to launch
  • 0 Critical + some Major = Ready after fixes
  • Any Critical = Not ready

Save to deliverables/docs/qa-report-[date].md.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free