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

66%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 content is highly actionable with concrete tool calls and clear judgment rules, but it is monolithic: all eight SC procedures and a full report template live inline in one file with no bundle files or progressive disclosure. Workflow clarity is adequate but lacks explicit validation checkpoints.

Suggestions

Split the per-Success-Criterion test procedures and the report template into separate reference files (e.g., references/sc-procedures.md, references/report-template.md) and link to them from SKILL.md to improve progressive disclosure.

Add explicit validation checkpoints to the workflow (e.g., 'After each SC, re-run search_elements to confirm state changes before recording the result') to strengthen feedback loops.

De-duplicate the privacy/contrast-estimate caveats into a single shared note referenced from each applicable SC to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tool calls, but the privacy notes and contrast-as-estimate caveats are repeated across sections, and the full inline report template plus per-SC failure/fix lists add length that could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready tool calls (search_elements queries, computer key sequences, capture_screenshot usage) and concrete per-SC PASS/FAIL judgment rules that directly drive execution.	5 / 5
Workflow Clarity	A general 5-step workflow and per-SC test sequences are present, but validation/checkpoint steps are implicit (e.g., 're-run search_elements to verify state updates') rather than framed as explicit validate-then-proceed gates; the read-only audit nature avoids the destructive cap, but explicit feedback loops are still missing.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ all absent) and the entire body—eight SC test procedures plus a full ~200-line report template—is inlined monolithically in a single SKILL.md with no external references or navigation pointers.	2 / 5
	Total	13 / 20 Passed

Description

100%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 is concrete, comprehensive, and clearly distinguishes the skill's niche while providing explicit trigger guidance in third person. It answers both what the skill does and when to use it without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (evaluates web pages against 8 named Success Criteria, accessibility tree inspection, visual analysis) with comprehensive, specific coverage rather than vague phrasing.	5 / 5
Completeness	Explicitly answers both 'what' (evaluates pages against 8 specific SCs via tree inspection and visual analysis) and 'when' ('Use this skill when you need to perform accessibility testing/auditing on a live webpage') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ('accessibility testing/auditing', 'live webpage', 'WCAG 2.2') plus the technical SC identifiers, covering synonyms users would actually say.	5 / 5
Distinctiveness Conflict Risk	The WCAG 2.2 audit niche with named Success Criteria is a clear, distinct specialization unlikely to trigger for unrelated skills.	5 / 5
	Total	20 / 20 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: 8726844

Reviewed: 6 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.