accessibility-auditor
Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions,…
This document defines the standard output contract for background agents spawned by the meta-orchestrator or any plugin skill.
> /plugin marketplace add heymegabyte/claude-skillsHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
This document defines the standard output contract for background agents spawned by the meta-orchestrator or any plugin skill.
This document defines the standard output contract for background agents spawned by the meta-orchestrator or any plugin skill.
Every background agent MUST write its final output as a Markdown file to:
$CLAUDE_PLUGIN_DATA/agent-output/<agent-name>-<iso-timestamp>.md
Each output file follows this structure:
# <agent-name> — <iso-timestamp> ## Task One-line description of what was requested. ## Summary 2–5 sentences covering what was done, key findings, and any blockers. ## Results - **Result 1**: description with evidence - **Result 2**: description with evidence - ... ## Artifacts - `<path/to/generated/file>` — purpose of the file - `<pull-request-url>` — if a PR was created ## Recommendations Optional list of follow-up actions or suggestions for the main thread. ## Status PASS | FAIL | PARTIAL
The SessionStart hook MUST check for unread output files:
1. List `$CLAUDE_PLUGIN_DATA/agent-output/*.md` sorted by modification time (newest first). 2. For any file not yet read (tracked via a `.read_stamp` file or `$CLAUDE_PLUGIN_DATA/agent-output/.read-stamp`), prepend a system reminder:
> Unread agent output available: `<path>`
3. The user or main thread reads the file on demand.
# deploy-verifier — 2026-06-28T143022Z ## Task Verify example.com after deploy. ## Summary All checks passed. Site loads in 1.2s, axe reports 0 violations, all 6 breakpoints clean. ## Results - Page loads: 200 OK in 1.2s - Console errors: 0 - Visual: clean at 375/390/768/1024/1280/1920 - Accessibility: 0 axe violations - SEO: title (58 chars), meta (142 chars), OG tags present, canonical set - Performance: LCP 1.4s, CLS 0.03, INP 48ms ## Artifacts - `e2e/screenshots/deploy-verifier/2026-06-28/` — all breakpoint screenshots ## Status PASS
14-category autonomous product-building OS for 32+ AI coding tools. One-line prompts → deployed products.
Repo: heymegabyte/claude-skills
Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions,…
Pre-implementation architecture agent. Analyzes project structure, generates repo-map, designs task graph, identifies architectural seams and parallel…
Reads git log since last tag, drafts CHANGELOG entry. Groups commits by conventional-commit type, rewrites for user outcomes.
Auto-generates changelogs from conventional commits. Parses git log since last tag, groups by type, writes user-outcome-focused CHANGELOG.md entries.
Simplifies code for clarity, consistency, and maintainability. Reduces complexity, flattens nesting, removes dead code, consolidates duplicates. Focuses on…
Post-implementation verification agent. Runs Feature Completeness Engine, Zero Recommendations Gate, and visual verification. Only declares DONE when genuinely…