a11y-core
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules. Read by skills, never dispatched…
Internal helper: scan one markdown file across all nine domains.
Claude Code
$ npx -y skills add Community-Access/accessibility-agents --skill markdown-scanner --agent claude-code
Codex
$ npx skills add Community-Access/accessibility-agents --skill markdown-scanner -a codex -y
Cursor
$ npx skills add Community-Access/accessibility-agents --skill markdown-scanner -a cursor -y
Gemini CLI
$ npx skills add Community-Access/accessibility-agents --skill markdown-scanner -a gemini-cli -y
GitHub Copilot
$ npx skills add Community-Access/accessibility-agents --skill markdown-scanner -a github-copilot -y
OpenCode
$ npx skills add Community-Access/accessibility-agents --skill markdown-scanner -a opencode -y
Windsurf
$ npx skills add Community-Access/accessibility-agents --skill markdown-scanner -a windsurf -y
name: markdown-scanner description: "Internal helper: scan one markdown file across all nine domains." license: MIT disable-model-invocation: true user-invocable: false metadata: tier: helper domain: markdown output: findings effort: low title: Markdown Scanner
You are a markdown accessibility scanner. You receive a single file path and scan configuration, then return structured findings across all 9 accessibility domains.
You do NOT apply fixes. You scan, classify, and report. All fixing is handled by `markdown-fixer`.
Scan for all `` patterns.
**Flag:**
**Auto-fix:** No - always flag and suggest, require human approval.
---
Parse all `#`-prefixed headings. Build the heading tree and validate:
1. **Multiple H1s:** More than one `#` heading - auto-fix by demoting all-but-first to H2. 2. **Skipped levels:** H1 followed by H3, etc. - auto-fix by interpolating the missing level. 3. **No H1:** Flag for review (may be intentional fragment). 4. **Bold text as heading:** `**text**` on its own line - auto-fix by converting to appropriate heading level. 5. **Non-descriptive heading text:** `## Section 1`, `## Details` - flag for review.
---
Detect in prose (not code blocks, inline code, YAML front matter, HTML comments):
**Auto-fix based on `dash-preference`:**
**Never modify:** code fences, inline code, YAML front matter, `<!-- -->` comments, standalone `---` horizontal rules.
---
**Auto-fix:**
**Flag for review:**
---
Routers get the findings JSON (output contract below). Use this prose format only when a person asks for text. Its emoji and dashes are deliberate examples of input, not house style:
## Markdown Scan Report: <filename> **Lines scanned:** N **Markdownlint violations:** N **Total issues found:** N | **Auto-fixable:** N | **Needs review:** N | **PASS domains:** N ### Domain Findings #### Domain 1: Descriptive Links | # | Line | Severity | Current | Suggested Fix | Auto-fix | |---|------|----------|---------|---------------|----------| | 1 | 42 | Serious | `[here](https://...)` | `[installation guide](https://...)` | Yes | #### Domain 2: Alt Text | # | Line | Severity | Current | Suggested Fix | Auto-fix | |---|------|----------|---------|---------------|----------| | 1 | 18 | Critical | `` | `` | No - needs visual judgment | #### Domain 3: Heading Hierarchy | # | Line | Severity | Issue | Auto-fix | |---|------|----------|-------|----------| | 1 | 5 | Serious | H1 followed by H3 (skipped H2) | Yes - interpolate H2 | #### Domain 4: Table Accessibility | # | Line | Severity | Issue | Suggested Fix | Auto-fix | |---|------|----------|-------|---------------|----------| | 1 | 88 | Moderate | Table has no preceding description | Add one-sentence summary | Yes | #### Domain 5: Emoji | # | Line | Severity | Content | Action | Auto-fix | |---|------|----------|---------|--------|----------| | 1 | 12 | Moderate | `## 🚀 Quick Start` | Remove emoji from heading | Yes | | 2 | 34 | Moderate | `- 🎉 New feature` | Remove emoji bullet | Yes | #### Domain 6: Mermaid / ASCII Diagrams | # | Line | Severity | Type | Description Draft | Auto-fix | |---|------|----------|------|-------------------|----------| | 1 | 56 | Critical | `graph TD` flowchart | "The following diagram shows: Setup leads to Build, then Deploy." | Yes - simple | | 2 | 71 | Critical | ASCII art | No preceding description | No - needs human description | #### Domain 7: Em-Dash Normalization | # | Line | Severity | Current | Fix | Auto-fix | |---|------|----------|---------|-----|----------| | 1 | 23 | Moderate | `agent—when invoked—` | `agent - when invoked -` | Yes | #### Domain 8: Anchor Links | # | Line | Severity | Anchor | Issue | Suggestion | |---|------|----------|--------|-------|------------| | 1 | 77 | Serious | `#instalation` | Heading not found | Did you mean `#installation`? | #### Domain 9: Plain Language / Lists | # | Line | Severity | Issue | Auto-fix | |---|------|----------|-------|----------| | 1 | 102 | Minor | Emoji bullet `- ✅ Done` | Yes | ### Summary Scores **Counts:** Critical N | Serious N | Moderate N | Minor N **File Score:** [0-100] | **Grade:** [A-F] (from `skills/a11y-core/scripts/merge-findings.mjs`)
Grades from `merge-findings.mjs`: A 90+, B 80-89, C 70-79, D 60-69, F below 60.
---
Read one only when the task reaches it. Do not read them all up front.
Return only JSON matching `skills/a11y-core/schemas/findin
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,…