accesslint-audit

Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A highly actionable, well-sequenced instruction skill with strong validation feedback loops, weakened mainly by duplicated content in a monolithic file with no reference split-out.

Suggestions

Remove the duplication: drop the verbatim description repeat in 'When to Use' and keep the Source:-line explanation in only one place (it currently appears in both the report-mode approach and the fix-mode recipe).

Split the report-format template and/or the fix-mode recipe into a reference file (e.g. references/report-format.md, references/fix-recipe.md) and link to them from SKILL.md to improve progressive disclosure and shorten the body.

De-duplicate the flow-picker logic, which is stated once in 'Picking a flow' and restated in the fallback note immediately after.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and directive, but the 'When to Use' section repeats the description verbatim and the Source:-line explanation is duplicated (appearing both in the report-mode approach and the fix-mode recipe), so it could be tightened rather than earning the lean score-3 anchor.	2 / 3
Actionability	Gives concrete, parameterized tool calls — audit_diff({ audit_name: "before" }), format: "compact", explain_rule({ id }), audit_live — plus an exact report template and explicit bail conditions; for an instruction-only skill this is copy-ready, actionable guidance matching the score-3 anchor.	3 / 3
Workflow Clarity	Fix mode is a clearly sequenced Baseline → Plan+apply → Verify loop with an explicit validation checkpoint (confirm -fixed covers targets and +new is empty) and a 'When to bail' feedback loop, matching the score-3 anchor with validation steps and error-recovery feedback.	3 / 3
Progressive Disclosure	No bundle files exist and the 107-line body is a single monolithic file; internal sections are well organized but nothing is split out into one-level-deep references, so it lands at the score-2 'some structure, content that could be separate is inline' anchor rather than the split-out score-3 anchor (the under-50-line simple-skill exemption does not apply).	2 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinctive description with good natural trigger coverage, held back only by the absence of an explicit 'Use when…' clause that caps completeness at 2.

Suggestions

Add an explicit 'Use when…' trigger clause, e.g. 'Use when auditing or fixing WCAG 2.2 accessibility issues, or when the user mentions a11y, accessibility, or WCAG compliance.'

Include the common shorthand 'a11y' alongside 'accessibility' to match how users most often phrase these requests.

Trim the trailing implementation jargon ('direct-CDP live-DOM', 'browser-MCP composition') which is mechanism, not trigger, and dilutes the natural-language signal.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Find and fix WCAG 2.2 accessibility issues', 'sweep a codebase or page, produce a prioritized written report', 'audit→edit→verify loop', 'live-DOM auditing', 'HTML-string audits' — matching the score-3 anchor rather than the domain-only score-2 anchor.	3 / 3
Completeness	Clearly answers 'what' but has no 'Use when…' clause or equivalent explicit trigger guidance; the judging guideline caps completeness at 2 in that case, and it cannot reach 3 without an explicit when-trigger.	2 / 3
Trigger Term Quality	Covers natural terms users would say — 'accessibility', 'WCAG 2.2', 'audit', 'report', 'fix' — broadly; the trailing CDP/MCP jargon is supplementary mechanism detail, not the triggers, so it stays at 3 rather than dropping to 2.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (WCAG 2.2 accessibility audit/fix with distinct report vs. fix modes) unlikely to collide with other skills, matching the score-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 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: sickn33/antigravity-awesome-skills
Commit: 6e69f00

Reviewed: 5 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.