a11y-core
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules. Read by skills, never dispatched on its own.
Reference data, not a reviewer. Format accessibility audit reports with severity scoring (0-100, A-F grades), scorecard computation, and compliance exports including VPAT/ACR and remediation priorities.
$ npx -y skills add Community-Access/accessibility-agents --skill kb-report-generation --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/kb-report-generationContext preview
The summary Claude sees to decide when to auto-load this skill.
Reference data, not a reviewer. Format accessibility audit reports with severity scoring (0-100, A-F grades), scorecard computation, and compliance exports including VPAT/ACR and remediation priorities.
name: kb-report-generation description: Reference data, not a reviewer. Format accessibility audit reports with severity scoring (0-100, A-F grades), scorecard computation, and compliance exports including VPAT/ACR and remediation priorities. license: MIT disable-model-invocation: true user-invocable: false metadata: tier: reference domain: cross-cutting output: none effort: low title: Report Generation
Default output: `DOCUMENT-ACCESSIBILITY-AUDIT.md` in the project root.
Every audit report MUST include these sections:
1. **Audit Information** - date, auditor, profile, scope, counts 2. **Executive Summary** - totals, pass rate, most common issue, effort estimate 3. **Cross-Document Patterns** - recurring issues, systemic failures 4. **Findings by File** - per-document issues with rule ID, severity, location, WCAG, impact, remediation 5. **Findings by Rule (Cross-Reference)** - rule-level aggregation across files 6. **What Passed** - acknowledge clean documents and categories 7. **Remediation Priority** - ordered by impact (Immediate / Soon / When Possible) 8. **Accessibility Scorecard** - per-document scores and grades 9. **Metadata Dashboard** - document properties health 10. **Confidence Summary** - breakdown by confidence level
Document Score = 100 - (sum of weighted findings) Weights: Error (high confidence): -10 points Error (medium confidence): -7 points Error (low confidence): -3 points Warning (high confidence): -3 points Warning (medium confidence):-2 points Warning (low confidence): -1 point Tips: 0 points Floor: 0 (minimum score)
Each score, with its grade and meaning.
| Score | Grade | Meaning | |-------|-------|---------| | 90-100 | A | Excellent - minor or no issues | | 75-89 | B | Good - some warnings, few errors | | 50-74 | C | Needs Work - multiple errors | | 25-49 | D | Poor - significant accessibility barriers | | 0-24 | F | Failing - critical barriers, likely unusable with AT |
Each mode, with description and best for.
| Mode | Description | Best For | |------|-------------|----------| | By file | Group all issues under each document | Small batches (< 10 files) | | By issue type | Group all instances of each rule across documents | Seeing patterns | | By severity | Critical first, then serious, moderate, minor | Prioritizing fixes |
Each level, with its criteria.
| Level | Criteria | |-------|----------| | Supports | No findings for this WCAG criterion across any document | | Partially Supports | Some documents pass, some fail | | Does Not Support | All or most documents fail | | Not Applicable | Criterion does not apply to scanned document types |
When comparing against a baseline audit report:
| Status | Meaning | |--------|---------| | Fixed | Issue was in previous report but is now resolved | | New | Issue was not in previous report but appears now | | Persistent | Issue remains from previous report | | Regressed | Issue was previously fixed but has returned |
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 on its own.
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 merges their findings.
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.