a11y-core
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules. Read by skills, never dispatched…
Reference data, not a reviewer. Per-file-type accessibility rules: semantic HTML, ARIA patterns, CSS, markdown, testing and terminology.
Claude Code
$ npx -y skills add Community-Access/accessibility-agents --skill kb-path-instructions --agent claude-code
Codex
$ npx skills add Community-Access/accessibility-agents --skill kb-path-instructions -a codex -y
Cursor
$ npx skills add Community-Access/accessibility-agents --skill kb-path-instructions -a cursor -y
Gemini CLI
$ npx skills add Community-Access/accessibility-agents --skill kb-path-instructions -a gemini-cli -y
GitHub Copilot
$ npx skills add Community-Access/accessibility-agents --skill kb-path-instructions -a github-copilot -y
OpenCode
$ npx skills add Community-Access/accessibility-agents --skill kb-path-instructions -a opencode -y
Windsurf
$ npx skills add Community-Access/accessibility-agents --skill kb-path-instructions -a windsurf -y
name: kb-path-instructions description: "Reference data, not a reviewer. Per-file-type accessibility rules: semantic HTML, ARIA patterns, CSS, markdown, testing and terminology." license: MIT disable-model-invocation: true user-invocable: false metadata: tier: reference domain: cross-cutting output: none effort: low title: Path Instructions
Rules that apply to a particular kind of file. These were path-scoped instruction files before 7.0; each one still says which files it governs.
Open the one reference that matches what you are working on. Reading all ten costs more than the rules are worth on any single task.
| Read | When you are working on | |---|---| | `references/agent-terminology.md` | files matching `**/*.{md,agent.md}` | | `references/aria-patterns.md` | files matching `**/*.{html,jsx,tsx,vue,svelte,astro}` | | `references/css-accessibility.md` | files matching `**/*.{css,scss,less}` | | `references/document-generation.md` | files matching `**/*.{py,js,ts,mjs,cjs}` | | `references/markdown-accessibility.md` | files matching `**/*.md` | | `references/multi-agent-reliability.md` | files matching `**/*.{md,agent.md}` | | `references/powershell-terminal-ops.md` | files matching `**` | | `references/semantic-html.md` | files matching `**/*.{html,jsx,tsx,vue,svelte,astro}` | | `references/testing-accessibility.md` | files matching `**/*.{test,spec}.{js,ts,jsx,tsx}` | | `references/web-accessibility-baseline.md` | files matching `**/*.{html,jsx,tsx,vue,svelte,astro}` |
WCAG 2.2 AA enforcement for agentic coding, as a set of Agent Skills. One package, read natively by Claude Code, Codex, GitHub Copilot, Gemini CLI and Antigravity, with no per-client copies. Models forget accessibility while generating code.
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules. Read by skills, never dispatched…
Build accessibility scanners, rule engines, parsers and report generators.
Web UI accessibility lead. Use before writing or changing HTML, JSX, TSX, Vue, Svelte, CSS or templates. Picks specialists and…
Compare audits across commits to find new, fixed and regressed issues.
Generate a W3C or EU model accessibility statement from audit results.
GitHub Actions: workflow runs, logs, re-runs and CI failure triage.
Produce the "Playwright 1.xx API Review" artifact for a range of commits - the public API additions and the breaking or behavior…
Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions,…
DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent,…