accessibility

Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

Quality

83%

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

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-structured reference skill with concrete code and a clear testing workflow; its main gaps are encyclopedic length (some content Claude already knows) and an unreferenced bundled WCAG.md file.

Suggestions

Link to references/WCAG.md from the body (e.g., in the References or WCAG Principles section) so the bundled file is clearly signaled and discoverable.

Trim or relocate patterns Claude already knows well (e.g., the full visually-hidden CSS, focus-visible boilerplate) to shorten the body and improve token efficiency.

Consider moving the exhaustive success-criteria detail into references/WCAG.md, keeping SKILL.md as a concise overview that points one level deep.

Dimension	Reasoning	Score
Conciseness	Largely lean and reference-style with minimal preamble, but the body is encyclopedically long (~510 lines) and includes patterns Claude already knows (visually-hidden CSS, focus-visible), so it could be tightened to reach level 3.	2 / 3
Actionability	Provides fully executable code and commands throughout, including copy-paste HTML/CSS/JS patterns, Lighthouse/axe CLI commands, and a concrete screen-reader shortcut table.	3 / 3
Workflow Clarity	For an audit skill, the sequenced testing checklist plus the Critical/Serious/Moderate triage order forms an unambiguous workflow; no destructive or batch operations exist that would require validation checkpoints.	3 / 3
Progressive Disclosure	Sections are clearly organized with external reference links, but the provided bundle file references/WCAG.md is never linked or signaled from the body, leaving a navigation gap that falls short of the one-level-deep, clearly-signaled anchor.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 well-formed description with explicit triggers and a clear niche; its only weakness is that the capability verbs ("Audit and improve") are broad rather than enumerating several concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and two actions ("Audit and improve web accessibility"), but the verbs are broad and generic compared to the multi-action concrete anchor, so it falls short of level 3.	2 / 3
Completeness	Explicitly answers both what ("Audit and improve web accessibility following WCAG 2.1 guidelines") and when ("Use when asked to..." with enumerated triggers), matching the level-3 anchor.	3 / 3
Trigger Term Quality	Covers a strong range of natural terms users would say, including the colloquial "a11y audit", "WCAG compliance", "screen reader support", and "keyboard navigation".	3 / 3
Distinctiveness Conflict Risk	Occupies a clear, distinct accessibility niche with specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (523 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: gsd-build/gsd-2
Path: src/resources/skills/accessibility/SKILL.md
Commit: 33c00aa

Reviewed: about 13 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.