wcag-audit-patterns

Comprehensive guide to auditing web content against WCAG 2.2 guidelines with actionable remediation strategies.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/wcag-audit-patterns/SKILL.md

The canonical home for this skill is wcag-audit-patterns in rmyndharis/antigravity-skills

Quality

Content

63%Weight 40%Scale 1-5

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

The body is well-structured and concise with a sensible audit workflow and re-test checkpoint, but it is held back by non-executable instructions (tool names without commands) and a broken reference to a playbook file that is not bundled.

Suggestions

Add executable commands for the named tools (e.g., `npx @axe-core/cli <url>`, `lighthouse <url> --only-categories=accessibility`) so the instructions are runnable rather than just tool names.

Create the referenced `resources/implementation-playbook.md` (which promises patterns, checklists, and templates that do not exist) or remove the dangling reference and inline the essential content.

Make the re-test checkpoint an explicit feedback loop ("if re-test still fails, fix and re-test until passing") and add a brief checklist so the validation step is concrete.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of what WCAG/axe are), with only minor redundancy: the opening line duplicates the frontmatter description and the implementation-playbook reference is stated twice.	4 / 5
Actionability	It names concrete tools (axe, Lighthouse, WAVE) and concrete manual-check types (keyboard navigation, focus order, screen reader flows), but gives no executable commands or invocation syntax, so guidance stops at named tools rather than runnable steps.	3 / 5
Workflow Clarity	The four-step sequence is clear and step 4 ("Re-test after fixes") is an explicit validation checkpoint, but there is no spelled-out error-recovery feedback loop or checklist, keeping it just below 5.	4 / 5
Progressive Disclosure	Section structure is good and the reference is one-level-deep and clearly signaled in a Resources section, but the referenced `resources/implementation-playbook.md` does not exist in the bundle, so the promised patterns/checklists/templates are unreachable.	3 / 5
	Total	14 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 clearly names its niche (WCAG 2.2 accessibility auditing) but stops at a mid-range score because it omits any "Use when..." trigger guidance and lacks common accessibility synonyms. It is competent but not trigger-optimized.

Suggestions

Add an explicit "Use when..." trigger clause, e.g. "Use when auditing web content for WCAG 2.2, ADA, Section 508, or VPAT compliance," to satisfy both completeness and trigger coverage.

Include natural trigger synonyms users actually say — "accessibility audit", "a11y", "ADA/Section 508", "VPAT" — to lift trigger term quality above 3.

Replace the generic "actionable remediation strategies" with concrete named actions (e.g., "run axe/Lighthouse scans, perform keyboard and screen-reader checks, map findings to WCAG criteria, and generate remediation guidance") to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the WCAG 2.2 domain clearly and lists two actions ("auditing web content", "remediation strategies"), but the latter is generic rather than a concrete named action, so it matches the 1-2-concrete-actions anchor without being comprehensive.	3 / 5
Completeness	It gives a clear "what" (auditing web content against WCAG 2.2 with remediation) but no "when"/"Use when..." trigger clause at all, which the rubric caps at 3.	3 / 5
Trigger Term Quality	"WCAG 2.2", "web content", and "auditing" are relevant keywords a user might say, but common natural synonyms like accessibility audit, a11y, ADA, Section 508, and VPAT are missing.	3 / 5
Distinctiveness Conflict Risk	The WCAG 2.2 accessibility-audit niche is mostly distinct with only minor overlap risk against generic web-audit or frontend skills; it is not a 5 because the description lacks distinctive trigger phrases that lock it to this skill alone.	4 / 5
	Total	13 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/wcag-audit-patterns/SKILL.md
Commit: 900c504

Reviewed: 4 hours 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.