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

—

Does it follow best practices?

Impact

95%

1.06x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with strong executable examples, but it is a large monolithic reference that restates well-known WCAG concepts and lacks an explicit sequenced audit workflow with a remediation re-verify loop. Splitting detail into reference files and adding a stepwise process would lift the weaker dimensions.

Suggestions

Add an explicit numbered audit workflow (run automated scan → triage violations → manual verification → remediate → re-run scan to verify) so the process has clear checkpoints and a feedback loop.

Move the full per-criterion checklist and remediation pattern library into one-level-deep reference files (e.g. CHECKLIST.md, REMEDIATION.md), keeping SKILL.md as a lean overview that links to them.

Trim content Claude already knows — the POUR principle glosses and A/AA/AAA conformance table — to tighten token efficiency and focus on non-obvious operational guidance.

Dimension	Reasoning	Score
Conciseness	Mostly compact checklists, but it restates concepts Claude already knows (POUR principles with "Can users perceive the content?" glosses, the A/AA/AAA conformance table, and a full enumeration of WCAG success criteria) that could be condensed to focus on non-obvious operational guidance.	2 / 3
Actionability	Provides fully executable, copy-paste-ready material — axe-core/Playwright audit scripts, CLI commands (npx @axe-core/cli, pa11y, lighthouse), and before/after HTML/CSS/JS remediation patterns including a keyboard-accessible custom dropdown.	3 / 3
Workflow Clarity	Organized as per-criterion checklists, but there is no explicit sequenced audit workflow (e.g. run automated → review → manual verify → prioritize → remediate → re-test), and the re-test/re-verify feedback loop after remediation is missing, which caps a batch audit process at 2.	2 / 3
Progressive Disclosure	Well-structured into clear sections, but it is a monolithic ~350-line SKILL.md with no bundle files; the full criteria checklist, remediation patterns, and automated-testing code that could live in one-level-deep reference files are all inlined.	2 / 3
	Total	9 / 12 Passed

Description

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.

The description is strong: third-person voice, concrete capabilities, an explicit "Use when" trigger clause, and a distinctive WCAG/accessibility niche. It cleanly satisfies all four dimensions at the top of the scale.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "automated testing, manual verification, and remediation guidance" — matching the anchor for enumerating several specific capabilities.	3 / 3
Completeness	Explicitly states what ("Conduct WCAG 2.2 accessibility audits...") and when via a clear "Use when..." clause, satisfying both halves with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms users would say — "auditing websites for accessibility", "WCAG violations", "accessible design patterns" — giving good coverage of likely phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (WCAG 2.2 accessibility auditing) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 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	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

Reviewed: 4 days 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.