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

45%

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 ./.agent/skills/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 establishes a clear accessibility domain and mentions relevant technical concepts (WCAG, assistive technology), but suffers from two key weaknesses: it uses second person voice ('You are') which violates the third-person requirement, and it completely lacks explicit trigger guidance for when Claude should select this skill. The actions listed are also somewhat abstract rather than concrete.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when the user asks about accessibility, WCAG compliance, screen readers, color contrast, keyboard navigation, or ADA requirements'

Rewrite in third person voice: 'Conducts accessibility audits, identifies WCAG compliance issues, and provides remediation guidance for inclusive design'

Include more natural trigger terms users would say: 'a11y', 'screen reader support', 'alt text', 'color contrast', 'keyboard accessible', '.aria attributes'

Dimension	Reasoning	Score
Specificity	Names the domain (accessibility/WCAG) and some actions ('conduct audits, identify barriers, provide remediation guidance'), but these are somewhat general rather than listing multiple concrete specific actions like 'test screen reader compatibility, validate color contrast ratios, check keyboard navigation'.	2 / 3
Completeness	Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance should cap completeness at 2, and this has no trigger guidance at all.	1 / 3
Trigger Term Quality	Includes relevant terms like 'WCAG', 'accessibility', 'inclusive design', 'assistive technology', but misses common user variations like 'a11y', 'screen reader', 'ADA compliance', 'color contrast', 'keyboard navigation', or 'alt text'.	2 / 3
Distinctiveness Conflict Risk	The accessibility/WCAG focus provides some distinctiveness, but 'conduct audits' and 'provide guidance' are generic enough to potentially overlap with other audit or compliance-focused skills. The domain is clear but triggers are not sharply defined.	2 / 3
	Total	7 / 12 Passed

Implementation

57%

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

This skill provides a reasonable high-level framework for accessibility auditing with good progressive disclosure to detailed resources. However, it lacks concrete, executable guidance (specific tools, commands, code snippets) and explicit validation checkpoints in the workflow. The content could be tightened by removing meta-framing sections.

Suggestions

Add specific tool commands for automated scanning (e.g., 'npx axe-core url' or 'lighthouse --accessibility') to make the scan step actionable

Include explicit validation criteria between steps (e.g., 'Proceed to manual checks only when automated scan shows <X violations' or 'Re-test must show 0 critical issues before sign-off')

Remove or condense the 'Use this skill when' / 'Do not use this skill when' sections as Claude can infer appropriate usage from the instructions

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient but includes some unnecessary framing ('You are an accessibility expert...') and the 'Use this skill when' / 'Do not use this skill when' sections add bulk that Claude doesn't need. The core instructions are lean.	2 / 3
Actionability	Instructions provide a clear checklist of steps but lack concrete examples, specific tool commands, or executable code. 'Run automated scans' and 'Perform manual checks' are directional but not copy-paste actionable.	2 / 3
Workflow Clarity	Steps are sequenced logically (scope → scan → manual → map → remediate → re-test), but validation checkpoints are implicit. No explicit feedback loop for failed re-tests or criteria for when to proceed between steps.	2 / 3
Progressive Disclosure	Clear overview structure with well-signaled one-level-deep reference to 'resources/implementation-playbook.md' for detailed procedures. Content is appropriately split between overview and detailed implementation.	3 / 3
	Total	9 / 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: Dokhacgiakhoa/antigravity-ide
Commit: 3395991

Reviewed: 25 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.