a11y-self-check

Included with Lifetime

$97 forever

Proactively validates Claude Code's own generated HTML/JSX/TSX output for accessibility before presenting to users. Use this skill automatically when generating UI code to ensure WCAG 2.1 AA compliance.

Design

What this skill does


# A11y Self-Check for Claude Code

This skill enables Claude Code to validate its own generated HTML/JSX/TSX output for accessibility issues before presenting code to users.

## When to Use

Proactively run self-check when you (Claude Code):

1. **Generate new HTML/JSX/TSX files** - Validate before suggesting to user
2. **Write UI components** - Check before completing the task
3. **Modify existing templates** - Verify changes don't introduce issues
4. **Create forms, modals, navigation** - High-risk accessibility areas

## Self-Check Workflow

### Step 1: Write Code to Temporary File

When generating HTML/JSX/TSX code, write it to a temporary file:

```bash
# For generated HTML
cat > /tmp/claude-generated.html << 'EOF'
[your generated HTML here]
EOF

# For JSX/TSX
cat > /tmp/claude-generated.tsx << 'EOF'
[your generated JSX/TSX here]
EOF
```

### Step 2: Run A11y Lint

Execute the lint script on the temporary file:

```bash
bash ${CLAUDE_PLUGIN_ROOT}/skills/html-lint-runner/scripts/lint-html.sh /tmp/claude-generated.html
```

### Step 3: Analyze Results

Check the JSON output for issues:

```json
{
  "summary": {
    "axe_violations": 0,
    "markuplint_problems": 0,
    "total_issues": 0
  }
}
```

- If `total_issues` is 0: Code is ready to present
- If `total_issues` > 0: Fix issues before presenting

### Step 4: Fix and Re-validate

If issues found:
1. Look up WCAG/ARIA reference: `${CLAUDE_PLUGIN_ROOT}/skills/wcag-aria-lookup/`
2. Apply fixes to your generated code
3. Re-run lint to confirm resolution
4. Present corrected code to user

## Quick Checks (No Tool Required)

Before running lint tools, perform mental checks:

### Images
- [ ] All `<img>` have `alt` attribute
- [ ] Decorative images use `alt=""`
- [ ] Complex images have `aria-describedby`

### Forms
- [ ] All inputs have associated `<label>`
- [ ] Required fields have `aria-required="true"`
- [ ] Error states use `aria-invalid` and `aria-describedby`

### Interactive Elements
- [ ] Buttons have accessible names
- [ ] Links have descriptive text (not "click here")
- [ ] Custom controls have proper ARIA roles

### Structure
- [ ] Headings follow logical order (h1 → h2 → h3)
- [ ] Landmarks are used (`<main>`, `<nav>`, `<aside>`)
- [ ] Language is set on `<html lang="...">`

### Color & Contrast
- [ ] Text contrast ≥ 4.5:1 (normal), ≥ 3:1 (large)
- [ ] Information not conveyed by color alone

## Integration with /a11y-audit

For comprehensive validation, use the `/a11y-audit` command:

```
/a11y-audit /tmp/claude-generated.html
```

This spawns the `a11y-fixer` agent for detailed analysis with WCAG references.

## Example: Self-Validated Component Generation

```
User: "Create a login form component"

Claude Code (internal process):
1. Generate LoginForm.tsx
2. Write to /tmp/claude-generated.tsx
3. Run: bash ${CLAUDE_PLUGIN_ROOT}/skills/html-lint-runner/scripts/lint-html.sh /tmp/claude-generated.tsx
4. Results show: missing label association
5. Fix: Add htmlFor and id attributes
6. Re-run lint: 0 issues
7. Present validated code to user
```

## Proactive Quality Assurance

This skill transforms Claude Code from generating "potentially accessible" code to generating "validated accessible" code by:

1. **Pre-flight checks** - Mental validation before writing
2. **Automated validation** - Tool-based verification after writing
3. **Reference lookup** - WCAG/ARIA guidance for fixes
4. **Iteration** - Fix → Validate → Confirm cycle

Users receive code that has already passed accessibility checks.

Files: 1

Size: 3.7 KB

Complexity: 7/100

Category: Design

Source: https://github.com/naporin0624/claude-web-audit-plugins/tree/main/skills/a11y-self-check

Related in Design

contribute

Included

Local-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".

Designscripts

architectural-analysis

Included

User-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).

Designscripts

mcp

Included

Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.

Designscripts

react-native-skia

Included

Design, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.

Designscripts

plaid

Included

Product Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".

Designscripts

nextjs-framer-motion-animations

Included

Adds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.

Designscripts