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.
75
64%
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 communicates its purpose, lists concrete actions, includes natural trigger terms, and has an explicit 'Use when' clause. It follows the recommended pattern closely and is well-scoped to a distinct domain (WCAG accessibility auditing), making it easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'automated testing', 'manual verification', 'remediation guidance', 'auditing websites for accessibility', 'fixing WCAG violations', and 'implementing accessible design patterns'. | 3 / 3 |
Completeness | Clearly answers both 'what' (conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance) and 'when' (explicit 'Use when' clause covering auditing, fixing violations, and implementing accessible design patterns). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'WCAG 2.2', 'accessibility audits', 'WCAG violations', 'accessible design patterns', 'auditing websites for accessibility'. These cover the main terms a user would naturally use when seeking accessibility help. | 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 like general web development or testing 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 reads as a comprehensive WCAG 2.2 reference document rather than an actionable skill for Claude. While it has excellent concrete code examples and remediation patterns, it is severely bloated with reference material Claude already knows, lacks a clear audit workflow with sequenced steps and validation checkpoints, and dumps everything into a single monolithic file. The content would be far more effective as a concise workflow overview with references to separate checklist and remediation files.
Suggestions
Add a clear sequenced audit workflow (e.g., 1. Run automated scan with axe-core, 2. Review violations by severity, 3. Perform manual keyboard/screen reader checks, 4. Generate report, 5. Apply remediation patterns) with explicit validation steps between phases.
Move the detailed per-criterion checklists (Perceivable, Operable, Understandable, Robust) into separate reference files (e.g., CHECKLIST-PERCEIVABLE.md) and keep only a summary in the main skill file.
Remove the 'Core Concepts' section explaining WCAG levels and POUR principles - Claude already knows these. Replace with a brief note on which level to target (AA) and jump straight into the audit process.
Cut the skill to under 100 lines by keeping only the audit workflow, automated testing commands, and links to detailed checklists and remediation patterns in separate files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Includes extensive WCAG reference material that Claude already knows (POUR principles, conformance levels, individual success criteria descriptions). This is essentially a WCAG reference document rather than a skill teaching Claude something new. The 'Core Concepts' section explaining what WCAG levels and POUR principles are is 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 with specific contrast ratios, and a complete keyboard-accessible custom element implementation. All code is copy-paste ready. | 3 / 3 |
Workflow Clarity | Despite being a multi-step audit process, there is no clear sequenced workflow. The content is organized as a reference checklist rather than a process with steps. There are no validation checkpoints, no feedback loops for fixing issues, and no guidance on how to sequence the audit (e.g., run automated tests first, then manual checks, then remediate). The audit checklist is just a flat list of criteria without prioritization or sequencing. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline. The massive audit checklist covering all four POUR principles with every success criterion should be split into separate reference files. No content is delegated to external files despite the document being extremely long. The Resources section at the end links to external sites but doesn't organize the skill's own content across files. | 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 (556 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- 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.