a11y-audit

Scan a frontend project for WCAG 2.2 accessibility violations and fix them. Usage: /a11y-audit [path]

Quality

61%

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 ./.gemini/skills/cmd-a11y-audit/SKILL.md

Quality

Content

68%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 an actionable, well-structured four-step workflow with concrete commands, but its batch auto-fixing flow lacks a validation/re-verification checkpoint and the referenced bundle files are not present locally.

Suggestions

Add a validation step after the Fix phase, e.g. re-run a11y_scanner.py on fixed files and only report issues that remain, creating a fix → verify → retry loop.

Inline the key fix patterns (or at least the most common ones like alt="" and lang) so the skill is self-contained, and correct the reference paths to point at the actual local bundle.

Drop or trim the redundant 'Skill Reference' list since the same paths are already referenced inline in the steps.

Dimension	Reasoning	Score
Conciseness	The body is efficient with executable commands and tight lists, assuming Claude's competence; minor trimmable padding exists (the redundant 'Skill Reference' path list and the 'What It Does' header), keeping it just below the lean 5.	4 / 5
Actionability	It gives concrete, runnable commands (a11y_scanner.py --json, contrast_checker.py --batch) and specific auto-fixable/user-input issue lists, but the actual fix implementations are deferred to an external reference file rather than shown inline, leaving a minor gap.	4 / 5
Workflow Clarity	Scan → Fix → Contrast → Report is a clear four-step sequence, but this batch auto-fixing workflow has no validation checkpoint (e.g. re-scan after fixing) before reporting, so the destructive/batch cap holds it at 3.	3 / 5
Progressive Disclosure	The body is a well-organized overview with a dedicated, clearly-signaled Skill Reference section pointing one level deep to references and scripts; the odd engineering-team/... path prefix and absence of a local bundle are minor organization gaps rather than deep nesting.	4 / 5
	Total	15 / 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 states what the skill does and carves out a distinct a11y-audit niche, but it stops at two generic actions and lacks an explicit 'Use when...' trigger clause, leaving keyword coverage and completeness at mid-range.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions accessibility, WCAG, screen readers, ARIA, or color contrast issues in a frontend project.'

Expand the action list beyond scan/fix to concrete capabilities (e.g. '...groups findings by severity, suggests accessible color alternatives, and generates a markdown report').

Include more natural trigger terms users actually say (ARIA, screen reader, keyboard navigation, alt text, color contrast) to raise trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Scan a frontend project for WCAG 2.2 accessibility violations and fix them" names the domain plus two concrete actions (scan, fix), matching the 1-2-actions anchor; it does not enumerate the several specific actions needed for a 4.	3 / 5
Completeness	The 'what' is clear (scan and fix WCAG violations), but the only 'when' guidance is the invocation hint "Usage: /a11y-audit [path]" rather than an explicit 'Use when...' trigger clause, so completeness is capped at 3 per the missing-trigger-guidance rule.	3 / 5
Trigger Term Quality	It surfaces relevant keywords (accessibility, WCAG 2.2, a11y, frontend) but omits common natural variations users say (screen reader, ARIA, color contrast, keyboard, alt text), fitting the 'some relevant keywords but missing synonyms' anchor.	3 / 5
Distinctiveness Conflict Risk	WCAG 2.2 accessibility auditing is a clear niche with distinct triggers and only minor overlap risk with general frontend linting skills, fitting the 'mostly distinct' anchor rather than the fully-comprehensive 5.	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: alirezarezvani/claude-skills
Path: .gemini/skills/cmd-a11y-audit/SKILL.md
Commit: 19392f7

Reviewed: ~2 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.