accessibility-compliance-accessibility-audit

You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance.

Quality

33%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-accessibility-compliance-accessibility-audit/SKILL.md

Quality

Discovery

32%

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 identifies a clear domain (accessibility and WCAG compliance) and lists some high-level actions, but it lacks a 'Use when...' clause, uses second-person voice ('You are'), and misses many natural trigger terms users would employ. It needs explicit trigger guidance and more concrete, specific capabilities to be effective for skill selection.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks about accessibility, WCAG compliance, screen reader compatibility, color contrast, keyboard navigation, or ADA requirements.'

Rewrite in third person voice (e.g., 'Conducts accessibility audits...' instead of 'You are an accessibility expert...')

Include more natural trigger terms users would say, such as 'a11y', 'screen reader', 'alt text', 'ARIA', 'color contrast', 'keyboard navigation', 'ADA', and specific WCAG levels (2.0, 2.1, AA, AAA).

Dimension	Reasoning	Score
Specificity	Names the domain (accessibility, WCAG compliance) and some actions (conduct audits, identify barriers, provide remediation guidance), but the actions are somewhat general and not highly concrete—e.g., it doesn't specify what types of audits, what kinds of barriers, or what formats of remediation.	2 / 3
Completeness	Describes what it does (conduct audits, identify barriers, provide remediation guidance) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'when' is entirely absent here, warranting a score of 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'WCAG', 'accessibility', 'inclusive design', 'assistive technology', and 'audits', but misses common user variations such as 'screen reader', 'a11y', 'ADA compliance', 'alt text', 'color contrast', 'keyboard navigation', or 'ARIA'.	2 / 3
Distinctiveness Conflict Risk	The accessibility/WCAG focus provides a reasonably distinct niche, but the description also uses the persona framing ('You are an accessibility expert') which is vague, and terms like 'inclusive design' could overlap with general UX or design skills.	2 / 3
	Total	7 / 12 Passed

Implementation

35%

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

This skill reads as a high-level process outline rather than actionable guidance. It lacks concrete tools, commands, code examples, or specific WCAG criteria references that would make it executable. The workflow structure is reasonable but the complete absence of specifics means Claude would need to rely entirely on its own knowledge, making the skill add minimal value beyond what Claude already knows.

Suggestions

Add concrete tool recommendations and executable commands (e.g., `npx axe-core`, `npx pa11y`, Lighthouse CLI commands) instead of vague 'run automated scans'.

Include specific examples of manual checks with expected outcomes (e.g., 'Tab through all interactive elements — verify visible focus indicator on each; test with NVDA/VoiceOver and verify all images have descriptive alt text').

Provide a sample audit finding format/template showing how to map a violation to a WCAG criterion, severity level, and remediation step.

Either include the `resources/implementation-playbook.md` bundle file or inline the most critical actionable content from it into the skill body.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary sections like 'Context' which largely restates the description, and 'Use this skill when' / 'Do not use this skill when' sections that are somewhat verbose. The 'Limitations' section contains generic boilerplate. However, it's not egregiously padded.	2 / 3
Actionability	The instructions are vague and abstract — 'Run automated scans,' 'Perform manual checks,' 'Map findings to WCAG criteria' — without specifying any concrete tools, commands, code snippets, or executable examples. There's no specific guidance on how to actually perform any of these steps.	1 / 3
Workflow Clarity	There is a sequential list of steps (confirm scope → automated scans → manual checks → map findings → remediate → re-test), which provides a reasonable workflow. However, there are no explicit validation checkpoints, no feedback loops for error recovery, and the 're-test after fixes' step lacks specificity on what constitutes passing.	2 / 3
Progressive Disclosure	The skill references `resources/implementation-playbook.md` for detailed procedures, which is a good one-level-deep reference. However, no bundle files were provided, so the referenced file doesn't actually exist, and the main skill body is thin enough that the reference feels like it's deferring all substantive content rather than providing a useful overview.	2 / 3
	Total	7 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: boisenoise/skills-collections
Commit: 431bfad

Reviewed: 2 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.