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.

1.06x

Quality

64%

Does it follow best practices?

Impact

95%

1.06x

Average score across 3 eval scenarios

Securityby

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.md

Quality

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 follows best practices closely. It uses third person voice, lists specific concrete capabilities, includes an explicit 'Use when' clause with natural trigger terms, and occupies a clearly distinct niche around WCAG accessibility auditing. It closely mirrors the structure and quality of the good examples 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' (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 primary terms a user would naturally use when seeking accessibility help.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focused on WCAG 2.2 accessibility auditing. The specific mention of WCAG, accessibility audits, and accessible design patterns creates a clear domain that is 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 reads more like a comprehensive WCAG reference document than an actionable skill for Claude. While the code examples and remediation patterns are excellent and executable, the content is far too verbose—reproducing large portions of the WCAG spec that Claude already knows. It critically lacks a clear audit workflow (e.g., 'run automated scan → triage violations → manual checks → remediate → re-test') and would benefit enormously from splitting the checklist into a separate reference file.

Suggestions

Replace the exhaustive WCAG checklist with a concise audit workflow: 1) Run automated scan (axe-core), 2) Triage by severity, 3) Manual keyboard/screen reader checks, 4) Remediate with validation, 5) Re-test. Move the full checklist to a separate CHECKLIST.md.

Remove explanations of WCAG fundamentals (POUR principles, conformance levels table) that Claude already knows—link to the W3C spec instead.

Add explicit validation/feedback loops: after applying a fix, re-run the automated audit to confirm the violation is resolved before moving to the next issue.

Split into SKILL.md (overview + workflow + key patterns) and supporting files like CHECKLIST.md (full criteria) and REMEDIATION.md (fix patterns), with clear navigation links.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. Explains WCAG fundamentals (POUR principles, conformance levels) that Claude already knows. The full checklist of every WCAG criterion with descriptions is reference material that belongs in external docs, not inline. Much of this is a reformatted copy of the WCAG spec itself.	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 examples are copy-paste ready.	3 / 3
Workflow Clarity	There is no clear audit workflow or sequenced process. The content is structured as a reference checklist rather than a step-by-step audit procedure. There are no validation checkpoints, no feedback loops for re-testing after fixes, and no guidance on how to sequence automated vs. manual testing phases.	1 / 3
Progressive Disclosure	Monolithic wall of text with everything inline. The entire WCAG checklist, all remediation patterns, automated testing code, and best practices are all in one massive file. The checklist content should be split into separate reference files with the SKILL.md providing an overview and navigation.	1 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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: 99da384

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.