CtrlK
BlogDocsLog inGet started
Tessl Logo

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". Do NOT use for SEO (use seo), performance (use core-web-vitals), or comprehensive site audits covering multiple areas (use web-quality-audit).

64

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is richly actionable with copy-paste-ready code, exact contrast ratios, and concrete testing commands, but it is an over-long monolithic reference that duplicates an unreferenced bundle file and lacks a sequenced audit workflow with validation checkpoints.

Suggestions

Move the inline WCAG success-criteria detail into references/WCAG.md and link to it from the body — the bundle file already exists but is never referenced, and the ~520-line body duplicates content that belongs there.

Trim the POUR principles and conformance-levels tables, which restate concepts Claude already knows; retain only the contrast-ratio specifics and the code examples that earn their tokens.

Add an explicit audit workflow with checkpoints — e.g., run automated audit → triage findings by impact → fix criticals → re-run — instead of leaving the checklists and impact lists as disconnected sections with no verify/retry loop.

DimensionReasoningScore

Conciseness

The body is mostly lean, code-heavy reference material, but the POUR principles table and conformance-levels table restate concepts Claude already knows, and at ~520 lines the overall length could be tightened.

2 / 3

Actionability

It provides fully executable HTML/CSS/JS examples with ❌/✅ pairs, exact contrast ratios, and concrete commands ("npx lighthouse ... --only-categories=accessibility", "axe https://example.com") plus screen-reader keyboard bindings — copy-paste ready.

3 / 3

Workflow Clarity

Automated/manual testing checklists and a Critical/Serious/Moderate impact triage are present, but there is no connective audit sequence or validate→fix→retry feedback loop tying the pieces together.

2 / 3

Progressive Disclosure

A references/WCAG.md bundle file exists but is never referenced or linked from the body, and the ~520-line body inlines WCAG success-criteria detail that belongs in that separate file — content that should be split is inline and the reference is not signaled.

2 / 3

Total

9

/

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 strong description with explicit what/when triggers, natural trigger-term coverage including the a11y abbreviation, and exemplary disambiguation against adjacent skills. The only minor weakness is the limited set of concrete action verbs, which keeps specificity at 2 rather than 3.

DimensionReasoningScore

Specificity

"Audit and improve web accessibility following WCAG 2.1 guidelines" names the domain and two actions, but the action list is limited and not as comprehensive as the anchor-3 example (which lists multiple concrete actions).

2 / 3

Completeness

It clearly answers both what ("Audit and improve web accessibility following WCAG 2.1 guidelines") and when (explicit "Use when asked to..." clause with concrete triggers).

3 / 3

Trigger Term Quality

"improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", "make accessible" give strong coverage of natural phrasings a user would say, including the common a11y abbreviation.

3 / 3

Distinctiveness Conflict Risk

The explicit "Do NOT use for SEO (use seo), performance (use core-web-vitals), or comprehensive site audits ... (use web-quality-audit)" disambiguates against adjacent skills, giving a clear niche unlikely to conflict.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (532 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
tech-leads-club/agent-skills
Reviewed

Table of Contents

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.