agentleFS
Sign inStart free
podopodo/design-agent-skills/skills/accessibility-agents/SKILL.md

accessibility-agents

Skill32 starsChanged 6 months agoMITView on GitHub

WCAG 2.2 AA enforcement as a package of Agent Skills: router skills for web UI, full-site audits, Office/PDF/ePub documents, markdown, desktop and Python tooling, and GitHub workflows dispatch specialist, helper and reference skills by name.

The file

Create a free account to mount
Files
SKILL.md

accessibility-agents

Catalogue stub — full package: Community-Access/accessibility-agents

<!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block -->

Decision tree

  1. Is the full skill already installed? This package installs 108 skills (accessibility-lead, web-accessibility-wizard, document-accessibility-wizard, markdown-a11y-assistant, developer-hub, github-hub, a11y-core, a11y-tool-builder, accessibility-regression-detector, accessibility-statement, actions-manager, alt-text-headings, analytics, aria-specialist, ci-accessibility, cognitive-accessibility, compliance-mapping, contrast-master, contributions-hub, cross-document-analyzer, cross-page-analyzer, daily-briefing, data-visualization-accessibility, design-system-auditor, desktop-a11y-specialist, desktop-a11y-testing-coach, document-csv-reporter, document-inventory, email-accessibility, epub-accessibility, epub-scan-config, excel-accessibility, forms-specialist, i18n-accessibility, insiders-a11y-tracker, issue-tracker, kb-accessibility-rules, kb-ci-integration, kb-cognitive-accessibility, kb-data-visualization-accessibility, kb-design-system, kb-document-scanning, kb-email-accessibility, kb-framework-accessibility, kb-github-a11y-scanner, kb-github-analytics-scoring, kb-github-scanning, kb-github-shared-instructions, kb-github-workflow-standards, kb-help-url-reference, kb-legal-compliance-mapping, kb-lighthouse-scanner, kb-markdown-accessibility, kb-media-accessibility, kb-mobile-accessibility, kb-office-remediation, kb-path-instructions, kb-playwright-testing, kb-python-development, kb-report-generation, kb-severity-mapping, kb-testing-strategy, kb-web-scanning, kb-web-severity-scoring, keyboard-navigator, lighthouse-bridge, link-checker, live-region-controller, markdown-csv-reporter, markdown-fixer, markdown-scanner, media-accessibility, mobile-accessibility, modal-specialist, notifications-manager, nvda-addon-specialist, office-remediator, office-scan-config, pdf-accessibility, pdf-remediator, pdf-scan-config, performance-accessibility, playwright-scanner, playwright-verifier, powerpoint-accessibility, pr-review, projects-manager, python-specialist, release-manager, repo-admin, repo-manager, scanner-bridge, screen-reader-lab, security-dashboard, tables-data-specialist, team-manager, template-builder, testing-coach, text-quality-reviewer, wcag-aaa, wcag-guide, wcag3-preview, web-component-specialist, web-csv-reporter, web-issue-fixer, wiki-manager, word-accessibility, wxpython-specialist); checking the first.
    • Global: f=~/.agents/skills/accessibility-lead/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • Project: f=.agents/skills/accessibility-lead/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • installed → the skill is installed as accessibility-lead, invoke it and proceed
    • pointer → go to step 2

  2. Detect scope, then install:

    [ -e ~/.agents/skills/accessibility-agents ] && echo "global" || echo "project"

    Global:

    npx skills add Community-Access/accessibility-agents -g -y

    Project:

    npx skills add Community-Access/accessibility-agents -y

    Claude Code: send a command as a chat message starting with ! to run it without leaving the conversation.

Claude Code plugin route:

/plugin marketplace add Community-Access/accessibility-agents
/plugin install accessibility-agents@community-access

Heads-up

  • License: MIT
<!-- das:install:end -->

Invoke after install

Describe the problem; six router skills pick the specialists and hand work to them by name, so install the whole package, not single skills.

  • Skill name: accessibility-lead — before writing or changing HTML, JSX, TSX, Vue, Svelte, CSS or templates
  • Skill name: web-accessibility-wizard — a full site or app audit rather than one change
  • Skill name: document-accessibility-wizard — Word, Excel, PowerPoint, PDF or ePub files
  • Skill name: markdown-a11y-assistant — markdown documentation
  • Skill name: developer-hub — Python, wxPython, desktop apps, NVDA add-ons, accessibility tooling
  • Skill name: github-hub — issues, pull requests, releases, projects, actions, security, teams, wikis
  • Trigger phrases: "accessibility agents", "Community Access", "PDF accessibility", "document accessibility", "accessibility lead"

What it does

Models forget accessibility while generating code; this package routes the work to the right specialist and merges the findings. The six routers dispatch many specialist, helper and reference skills (ARIA, keyboard, focus, forms, contrast, modals, live regions, tables, cognitive load, i18n, mobile, email, data visualisation, Office/PDF/ePub scanning, markdown audits) by name. Reports are rendered from structured findings rather than from memory.

npx skills add installs the skills only. Upstream's extras (hooks that block edits to user-facing files until the accessibility lead has reviewed, plus an MCP server that supplies the scanners) come with the Claude Code plugin route or upstream's own node scripts/install.mjs.

When NOT to use

  • Single-file audits where a lighter tool suffices — use fixing-accessibility
  • Quick contrast check only — use color-expert
  • A single WCAG 2.2 audit pass without the router and specialist machinery — use wcag-audit-patterns

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