wcag22-a11y-audit

WCAG 2.2 Accessibility Audit skill that systematically evaluates web pages against 8 core Success Criteria (1.1.1, 1.4.3, 1.4.11, 2.1.1, 2.1.2, 2.4.3, 2.4.7, 4.1.2) using accessibility tree inspection and visual analysis. Use this skill when you need to perform accessibility testing/auditing on a live webpage.

Quality

83%

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

Quality

Content

77%

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

A thorough, highly actionable audit skill with concrete tool commands and a clearly sequenced per-criterion workflow. Its weaknesses are token efficiency (a very long inline report template and restated common-knowledge fixes) and a monolithic structure that does not split the large report template into a reference file.

Suggestions

Move the ~210-line report output template into a separate reference file (e.g. references/report-template.md) and link to it, reducing the SKILL.md token footprint.

Trim or collapse the repeated "Common Failures" and "Fix Recommendations" blocks, which mostly restate accessibility knowledge Claude already has; keep only non-obvious, skill-specific guidance.

Consider extracting the per-SC test procedures into a reference file so SKILL.md stays a lean overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	The body is largely actionable rather than padded with concept explanations, but at ~630 lines it is token-heavy: a ~210-line inline report template and per-SC "Common Failures / Fix Recommendations" sections restate accessibility knowledge Claude already knows and could be tightened.	2 / 3
Actionability	Provides concrete, specific executable guidance throughout — real tool calls like `search_elements(tabId, "image \| img")`, `computer(action='key', text='Tab')`, explicit PASS/FAIL conditions, and spelled-out visual-analysis prompts.	3 / 3
Workflow Clarity	A clear 5-step per-test workflow, numbered steps per Success Criterion, cross-SC references (2.4.7 → 1.4.11), and checklist-like state-coverage matrices give an explicit, well-sequenced process; no destructive-operation feedback loop is required for a read-only audit.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is a single monolithic ~630-line file with no bundle files, and the large report template is inline content that would be better split into a separate reference — matching the "content that should be separate is inline" anchor.	2 / 3
	Total	10 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both capability and trigger conditions with natural keyword coverage. The only notable weakness is the second-person "you need to" phrasing, which violates the third-person-voice convention and caps specificity.

Suggestions

Rewrite the trigger clause in third person to avoid the voice penalty, e.g. "Use when performing accessibility testing or auditing on a live webpage."

Dimension	Reasoning	Score
Specificity	Names concrete actions ("systematically evaluates web pages against 8 core Success Criteria ... using accessibility tree inspection and visual analysis") and enumerates specific criteria, which would merit 3, but the second-person phrasing "Use this skill when you need to perform" triggers the rubric's one-point penalty for non-third-person voice.	2 / 3
Completeness	Explicitly answers both what ("evaluates web pages against 8 core Success Criteria ... using accessibility tree inspection and visual analysis") and when ("Use this skill when you need to perform accessibility testing/auditing on a live webpage").	3 / 3
Trigger Term Quality	Includes natural terms users would say — "accessibility testing/auditing", "WCAG 2.2", "live webpage" — giving good coverage of common phrasings rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The WCAG 2.2 accessibility-audit niche with named SC numbers and inspection methods is a clear, distinct trigger set unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (635 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: AIPexStudio/AIPex
Path: packages/browser-runtime/src/skill/built-in/wcag22-a11y-audit/SKILL.md
Commit: 2c7b22c

Reviewed: 3 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.