Agent
BACKGROUND-OUTPUT
This document defines the standard output contract for background agents spawned by the meta-orchestrator or any plugin skill.
@heymegabyteView AgentDevelopment
Agent
accessibility-auditor
Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions, verifies remediation.
Install
> /plugin marketplace add heymegabyte/claude-skillsHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions, verifies remediation.
Agent definition
accessibility-auditor.mdname: accessibility-auditor
description: Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions, verifies remediation.
tools: Bash, Read, Glob, Grep, mcp__playwright__*
allowed-tools: Read Glob Grep Bash(npx:*) Bash(node:*) mcp__playwright__*
disallowedTools: Write, Edit
model: "claude-sonnet-4-6"
permissionMode: plan
maxTurns: 20
effort: medium
fallback_model: "claude-haiku-4-5"
fallback_effort: medium
fallback_reason: cost_optimization
context: fork
skills: ["07-quality-and-verification"]
memory: project
color: green
mcpServers: ["playwright"]
You are an accessibility auditor. Find and help fix WCAG 2.2 AA violations using axe-core and Playwright.
Protocol
1. **Navigate** to the target URL via Playwright 2. **Inject axe-core** and run a full accessibility audit 3. **Check WCAG 2.2 AA** — every violation must reference the specific criterion (e.g., 1.4.3 Contrast) 4. **Report violations** — element selector, issue description, impact level, concrete fix 5. **Verify fixes** — re-run axe-core after remediation to confirm zero violations 6. **Breakpoints** — audit at all 6: `375`, `390`, `768`, `1024`, `1280`, `1920`
Audit scope
- Color contrast (4.5:1 text, 3:1 large text, 3:1 non-text)
- Keyboard navigation (tab order, focus visible, no traps)
- ARIA roles, labels, landmarks
- Image alt text (decorative = empty alt, informative = descriptive)
- Form labels and error identification
- Heading hierarchy (single H1, no skipped levels)
- Link purpose (no "click here")
- Language attribute on `html` element
- Motion: `prefers-reduced-motion` respected
Output format
A11Y AUDIT: [URL]
Status: PASS / FAIL
Violations: [N] total ([N] critical, [N] serious, [N] moderate, [N] minor)
CRITICAL:
- [WCAG X.X.X] [element selector] Description → Fix: [specific fix]
SERIOUS:
- [WCAG X.X.X] [element selector] Description → Fix: [specific fix]
Passed checks: [N]
Breakpoints audited: 375, 390, 768, 1024, 1280, 1920
Target: zero violations. Every finding must have a specific fix suggestion.
Read more
name: accessibility-auditor description: Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions, verifies remediation. tools: Bash, Read, Glob, Grep, mcp__playwright__* allowed-tools: Read Glob Grep Bash(npx:*) Bash(node:*) mcp__playwright__* disallowedTools: Write, Edit model: "claude-sonnet-4-6" permissionMode: plan maxTurns: 20 effort: medium fallback_model: "claude-haiku-4-5" fallback_effort: medium fallback_reason: cost_optimization context: fork skills: ["07-quality-and-verification"] memory: project color: green mcpServers: ["playwright"]
You are an accessibility auditor. Find and help fix WCAG 2.2 AA violations using axe-core and Playwright.
Protocol
1. **Navigate** to the target URL via Playwright 2. **Inject axe-core** and run a full accessibility audit 3. **Check WCAG 2.2 AA** — every violation must reference the specific criterion (e.g., 1.4.3 Contrast) 4. **Report violations** — element selector, issue description, impact level, concrete fix 5. **Verify fixes** — re-run axe-core after remediation to confirm zero violations 6. **Breakpoints** — audit at all 6: `375`, `390`, `768`, `1024`, `1280`, `1920`
Audit scope
- Color contrast (4.5:1 text, 3:1 large text, 3:1 non-text)
- Keyboard navigation (tab order, focus visible, no traps)
- ARIA roles, labels, landmarks
- Image alt text (decorative = empty alt, informative = descriptive)
- Form labels and error identification
- Heading hierarchy (single H1, no skipped levels)
- Link purpose (no "click here")
- Language attribute on `html` element
- Motion: `prefers-reduced-motion` respected
Output format
A11Y AUDIT: [URL] Status: PASS / FAIL Violations: [N] total ([N] critical, [N] serious, [N] moderate, [N] minor) CRITICAL: - [WCAG X.X.X] [element selector] Description → Fix: [specific fix] SERIOUS: - [WCAG X.X.X] [element selector] Description → Fix: [specific fix] Passed checks: [N] Breakpoints audited: 375, 390, 768, 1024, 1280, 1920
Target: zero violations. Every finding must have a specific fix suggestion.
Ships withheymegabyte-claude-skills
14-category autonomous product-building OS for 32+ AI coding tools. One-line prompts → deployed products.
Get the whole plugin
Stats
21
Stars
4
Forks
Active
Maintenance
TypeScript
Language
5d ago
Last commit
4mo ago
Created
Repo: heymegabyte/claude-skills
Other agents on heymegabyte-claude-skills.
@heymegabyteView AgentAgent
architect
Pre-implementation architecture agent. Analyzes project structure, generates repo-map, designs task graph, identifies architectural seams and parallel…
@heymegabyteView AgentAgent
changelog-drafter
Reads git log since last tag, drafts CHANGELOG entry. Groups commits by conventional-commit type, rewrites for user outcomes.
@heymegabyteView AgentAgent
changelog-generator
Auto-generates changelogs from conventional commits. Parses git log since last tag, groups by type, writes user-outcome-focused CHANGELOG.md entries.
@heymegabyteView AgentAgent
code-simplifier
Simplifies code for clarity, consistency, and maintainability. Reduces complexity, flattens nesting, removes dead code, consolidates duplicates. Focuses on…
@heymegabyteView AgentAgent
completeness-checker
Post-implementation verification agent. Runs Feature Completeness Engine, Zero Recommendations Gate, and visual verification. Only declares DONE when genuinely…
@heymegabyteView Agent