CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fix-accessibility

Fix accessibility defects to WCAG 2.2 AA — missing labels, invisible focus, keyboard traps, contrast, alt text, announcements, reflow — using native semantics first, then verify with axe plus manual keyboard and screen-reader checks. Use for any accessibility finding.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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, well-structured instruction-only skill: specific HTML/ARIA guidance, numeric WCAG checkpoints, and explicit verification with exit criteria. The only gaps are minor — a runnable axe invocation and an explicit re-verify-on-failure loop would make the workflow fully self-contained.

Suggestions

Include the actual axe invocation (e.g. the axe CLI or browser extension command) so the verification step is executable rather than just named.

Add an explicit feedback loop after verification: 'If axe still reports serious/critical issues, fix and re-run until clean' rather than leaving the retry implicit.

DimensionReasoningScore

Conciseness

Every line is directive — no concept explanations, no padding, no restating what Claude already knows about accessibility. The ~19-line body covers procedure, exit criteria, and a counterpart pointer with zero wasted tokens.

5 / 5

Actionability

Concrete, specific guidance throughout: named elements ('<button>', '<label for>', '<a href>'), named ARIA mechanics ('aria-describedby', 'role="status"', 'alt=""'), and numeric criteria ('200% zoom and 320px width'). Falls short of the 5 anchor only in verification: 'axe (no serious or critical issues)' names the tool but gives no runnable command.

4 / 5

Workflow Clarity

A clear 7-step sequence ending in an explicit verification step, reinforced by a dedicated 'Exit criteria' section ('axe is clean, and the manual keyboard checklist is recorded for every touched route'). It lacks an explicit fix-and-reverify loop (what to do when axe still reports serious issues), which keeps it below the 5 anchor.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed; the body is organized into clean 'Procedure', 'Exit criteria', and counterpart-pointer sections. Per the rubric's simple-skill guideline, well-organized sections alone warrant a 5, and no bundle files exist to pull in.

5 / 5

Total

18

/

20

Passed

Description

83%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.

A strong description: concrete, well-scoped, and free of fluff, with both what and when answered. The main gap is the thin trigger clause — broadening 'Use for any accessibility finding' with concrete user phrasings (a11y, accessibility audit, screen reader) would lift trigger quality and completeness to the top anchors.

Suggestions

Expand the trigger clause to concrete phrases users naturally say, e.g. 'Use when the user reports an a11y/accessibility issue, mentions WCAG, axe, screen readers, or keyboard navigation.'

Add common synonyms such as 'a11y', 'screen reader', and 'accessibility audit' to broaden natural-term coverage.

DimensionReasoningScore

Specificity

The description enumerates concrete defect classes ('missing labels, invisible focus, keyboard traps, contrast, alt text, announcements, reflow'), states the approach ('using native semantics first'), and names verification methods ('verify with axe plus manual keyboard and screen-reader checks') — comprehensive concrete actions with no padding.

5 / 5

Completeness

Both are present: a clear 'what' (fix accessibility defects to WCAG 2.2 AA with verification) and an explicit 'when' ('Use for any accessibility finding'). The 'when' clause is explicit but could be more specific with concrete trigger phrases (e.g. 'when the user reports an a11y issue or mentions WCAG/axe'), matching the 4 anchor rather than 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage ('accessibility', 'WCAG', 'axe', 'keyboard', 'screen-reader', 'contrast', 'alt text', 'labels', 'focus'), but the trigger clause 'Use for any accessibility finding' is generic and misses common variations users would say, e.g. 'a11y', 'screen reader', 'accessibility issue/audit'. Not clearly the 5 anchor, which requires comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche (WCAG 2.2 AA remediation) with distinct domain triggers ('accessibility finding', 'axe', 'screen-reader'); unlikely to fire for unrelated skills. It explicitly names its counterpart tester skill, further reducing overlap confusion.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

itsablabla/qa-bug-agent-skills

Path

skills/fix-accessibility/SKILL.md

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.