wcag-audit-patterns
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.
84
64%
Does it follow best practices?
Impact
97%
1.04xAverage score across 6 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/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 communicates its purpose, lists concrete capabilities, and provides explicit trigger guidance via a 'Use when' clause. It uses appropriate third-person voice, includes natural trigger terms users would employ, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'WCAG 2.2 accessibility audits', 'automated testing', 'manual verification', and 'remediation guidance'. 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', 'auditing websites', 'WCAG violations', 'accessible design patterns'. These cover the main terms a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around WCAG 2.2 accessibility auditing. The specific mention of WCAG, accessibility audits, and accessible design patterns makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a WCAG 2.2 reference document rather than an actionable audit skill. While it provides excellent concrete code examples and remediation patterns (strong actionability), it fails as a skill by being excessively verbose with information Claude already knows, lacking a clear audit workflow with validation steps, and presenting everything as a monolithic document instead of using progressive disclosure.
Suggestions
Add a clear sequential audit workflow at the top: 1) Run automated scan with axe-core, 2) Triage violations by severity, 3) Manual verification checklist, 4) Apply remediation, 5) Re-test to verify fixes pass. Include explicit validation checkpoints.
Move the detailed per-principle checklists into separate referenced files (e.g., PERCEIVABLE.md, OPERABLE.md, UNDERSTANDABLE.md, ROBUST.md) and keep only a summary overview in the main skill.
Remove the POUR principles explanation, conformance level table, and 'Common Violations by Impact' tree — Claude already knows WCAG fundamentals. Focus the main file on the audit process and tool usage.
Add a verification/re-test step after remediation patterns to create a feedback loop (e.g., 'After applying fix, re-run axe-core on the component and confirm violation is resolved').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Includes extensive WCAG reference material Claude already knows (POUR principles, conformance levels, full criterion listings). This is essentially a WCAG specification summary rather than a skill teaching Claude something new. The tables explaining Level A/AA/AAA and POUR principles are unnecessary padding. | 1 / 3 |
Actionability | Provides fully executable code examples throughout: axe-core integration with Playwright, CLI commands, concrete HTML before/after remediation patterns, CSS fixes, and JavaScript keyboard navigation implementations. All code is copy-paste ready and specific. | 3 / 3 |
Workflow Clarity | Despite being an audit skill, there is no clear sequenced workflow for conducting an audit. The content is organized as a reference checklist rather than a process. There are no validation checkpoints, no feedback loops for verifying fixes, and no clear sequence of steps (e.g., run automated scan → triage results → manual verification → remediation → re-test). | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. The full WCAG checklist for all four principles is inlined, along with automated testing code, remediation patterns, and best practices. This content should be split across multiple files (e.g., checklist per principle, remediation patterns, automated testing setup) with the SKILL.md serving as an overview. | 1 / 3 |
Total | 6 / 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 (549 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
27a7ed9
- Reviewed
Table of Contents
Is this your skill?
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.