Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.
79
71%
Does it follow best practices?
Impact
95%
1.06xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/accessibility-compliance/skills/wcag-audit-patterns/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope around WCAG 2.2 accessibility auditing, lists concrete actions, and includes an explicit 'Use when...' clause with natural trigger terms. It follows third-person voice correctly and is concise without unnecessary padding. It closely matches the good examples provided in the rubric.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'automated testing', 'manual verification', 'remediation guidance', 'auditing websites', 'fixing WCAG violations', 'implementing accessible design patterns'. These are distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance') and when ('Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns') with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'accessibility', 'WCAG', 'audits', 'WCAG violations', 'accessible design patterns'. Covers the standard 'WCAG 2.2' and common terms like 'accessibility' that users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on WCAG 2.2 accessibility auditing. The specific mention of WCAG, accessibility audits, and remediation guidance makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is essentially a WCAG 2.2 reference manual rather than a focused operational guide. While it excels in actionability with concrete, executable code examples and before/after remediation patterns, it is far too verbose—reproducing well-known WCAG criteria that Claude already understands. The content desperately needs restructuring into a concise overview with references to detailed sub-files, and an explicit audit workflow with validation checkpoints.
Suggestions
Restructure into a concise SKILL.md overview (~50-80 lines) covering the audit workflow and key patterns, with detailed checklists split into separate files (e.g., CHECKLIST-PERCEIVABLE.md, CHECKLIST-OPERABLE.md, REMEDIATION-PATTERNS.md)
Add an explicit end-to-end audit workflow with numbered steps and validation checkpoints: automated scan → triage by severity → manual verification → remediation → re-scan → report
Remove the Core Concepts section (conformance levels, POUR principles, common violations taxonomy) — Claude already knows WCAG fundamentals; replace with project-specific configuration or decision criteria
Cut the exhaustive per-criterion checklists to focus on the most commonly missed or hardest-to-fix issues, linking to the full WCAG spec for completeness
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Includes extensive WCAG reference material that Claude already knows (POUR principles, conformance levels, basic HTML semantics). The 'Core Concepts' section explains fundamentals Claude doesn't need, and the full checklist essentially reproduces the WCAG specification rather than adding unique operational value. | 1 / 3 |
Actionability | Provides fully executable code examples throughout: axe-core integration with Playwright, CLI commands, concrete HTML before/after remediation patterns, CSS fixes with specific contrast ratios, and a complete keyboard-accessible custom element implementation. All examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | The checklist provides a clear sequence through POUR principles, and the automated testing section gives concrete steps. However, there's no explicit audit workflow (e.g., 'run automated scan → triage violations → manual verification → remediation → re-test') with validation checkpoints. For an audit process that could miss critical issues, the lack of a feedback loop caps this at 2. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. The entire WCAG checklist, all remediation patterns, automated testing code, and best practices are inlined in a single massive document. The checklist sections alone could be split into separate reference files, with SKILL.md serving as a concise overview with navigation links. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (556 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
47823e3
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.