CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

a11y-audit

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

54

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/cmd-a11y-audit/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A lean, actionable workflow with concrete commands and a clear step sequence, weakened by the absence of a post-fix validation loop for a batch, file-modifying operation. Reference organization is good but two reference files are unsignaled and paths are inconsistent.

Suggestions

Add a validation step after fixes: re-run a11y_scanner.py on the fixed files and only report issues as resolved when the re-scan is clean, looping back for failures.

Signal wcag-quick-ref.md and aria-patterns.md in the workflow steps where they apply (e.g., consult wcag-quick-ref.md when classifying severity) instead of only listing them in the Skill Reference section.

Unify reference paths (use {skill_path}/relative/path consistently) and drop the redundant Skill Reference entries that duplicate paths already shown inline.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence (no WCAG concept explanations), but the "Skill Reference" section repeats script and reference paths already used inline, with verbose "engineering-team/a11y-audit/skills/a11y-audit/" prefixes that could be trimmed.

4 / 5

Actionability

Provides executable commands (a11y_scanner.py --json, contrast_checker.py --batch), an explicit auto-fixable list, and a per-finding before/after loop, but leaves placeholder handling and scanner-failure/error-output cases unspecified.

4 / 5

Workflow Clarity

The scan → fix → contrast → report sequence is clearly defined with an auto-fix vs. ask-first checkpoint, but this batch file-modifying workflow has no validation loop (e.g., re-running the scanner to confirm fixes before generating the report), which caps it at 3.

3 / 5

Progressive Disclosure

Fix patterns are appropriately deferred to references/framework-a11y-patterns.md (well signaled in Step 2) and scripts stay out of the body, but wcag-quick-ref.md and aria-patterns.md are only listed in a footer with no in-context signal, and path style is inconsistent ({skill_path}/ vs. long repo prefixes).

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 has a clear what with a specific domain, but lacks an explicit when-to-use trigger clause and broader trigger synonyms, and its action list is not comprehensive. It is clearly distinguishable from unrelated skills.

Suggestions

Add a trigger clause, e.g. "Use when the user mentions accessibility, a11y, WCAG, screen readers, or asks to audit/fix a frontend for accessibility issues."

Broaden trigger synonyms to include "a11y", "ARIA", and "contrast" so the skill surfaces for the phrasings users actually say.

Mention the contrast checking and report generation actions to make the capability list comprehensive.

DimensionReasoningScore

Specificity

"Scan a frontend project for WCAG 2.2 accessibility violations and fix them" names the domain and two concrete actions (scan, fix), but coverage is not comprehensive — contrast checking and report generation are absent.

3 / 5

Completeness

The "what" is clear (scan and fix WCAG violations), but there is no "Use when..." clause or equivalent trigger guidance — "Usage: /a11y-audit [path]" is invocation syntax, not a usage condition, which caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms users would say ("WCAG 2.2", "accessibility", "frontend") but misses common synonyms and related triggers such as "a11y", "ARIA", "screen reader", or "contrast".

3 / 5

Distinctiveness Conflict Risk

"WCAG 2.2 accessibility violations" on "frontend project" carves a mostly distinct niche with only minor overlap risk against general linting or contrast-only skills; it is not a fully clear niche with comprehensive distinct triggers.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Revision

19392f7

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill