CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fixing-accessibility

Fix accessibility issues. Use for a11y audits or fixes.

Quality

75%

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 ./.agents/skills/04-develop/01-ui-skills-dot-com/fixing-accessibility/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a well-organized, prioritized constraint checklist that is lean, assumes Claude's competence, and gives concrete reviewable rules with specific aria attributes and verification commands. The main gaps are minor: some redundancy between sections, no example before/after fixes, and no feedback loop for the NO-GO verification case. It is a strong single-file instruction skill.

DimensionReasoningScore

Conciseness

The body is a lean constraint checklist ("icon-only buttons must have aria-label or aria-labelledby", "invalid fields must set aria-invalid") that assumes Claude's competence and never explains what accessibility is. Not 5 because of minor redundancy: the priority table repeats the category headers, "quote the exact snippet, state the failure, propose a small fix" duplicates the how-to-use output format, and "Prefer minimal, targeted fixes" repeats tool boundaries' "prefer minimal changes".

4 / 5

Actionability

Concrete, checkable rules with specific attributes and elements ("aria-describedby", "aria-expanded and aria-controls", "tabindex greater than 0") plus executable verification commands (`pnpm lint`, `pnpm test`, `pnpm build`, `pnpm verify`) — 'Mostly executable guidance; concrete code or commands with minor gaps'. Not 5 because no example fixes (before/after snippets) are shown, leaving the 'code-level suggestion' output to be constructed from scratch.

4 / 5

Workflow Clarity

A clear sequence is present: prioritized rule categories ("fix critical issues first (names, keyboard, focus, tool boundaries)"), a defined review output format (snippet + why + fix), and an explicit validation checkpoint ("If code touched: run pnpm lint, pnpm test, pnpm build, pnpm verify; report GO or NO-GO with evidence"). Not 5 because there is no feedback loop after a NO-GO result and the dual mode (apply constraints during UI work vs. file review) is not crisply sequenced.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the body references none, so this is a single-file skill with good structure: how to use, when to apply, a priority table, and per-category quick reference sections. Not 5 because at ~120 lines it exceeds the under-50-line simple-skill threshold, and the rule catalog could arguably live in a referenced file; it fits 'Good structure; most content is appropriately placed; minor organization gaps'.

4 / 5

Total

16

/

20

Passed

Description

62%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 is concise, in third person, and correctly includes an explicit 'Use for' trigger clause, giving it a clear a11y niche. However, it undersells the skill's actual scope (the body covers names, keyboard, focus, semantics, forms, announcements, contrast, media) and omits most natural trigger vocabulary like WCAG, aria, screen reader, and keyboard navigation. It reads as a compressed summary of a much richer skill.

Suggestions

Enumerate concrete capabilities in the description, e.g. 'Audit and fix accessible names, keyboard access, focus/dialog behavior, form errors, and contrast in UI code; propose minimal targeted fixes.'

Add natural trigger terms users actually say: 'WCAG', 'aria', 'screen reader', 'keyboard navigation', 'contrast' alongside the existing 'a11y'.

Broaden the when clause to mirror the body's 'when to apply' list, e.g. 'Use when adding or changing buttons, forms, dialogs, or menus, or when the user mentions accessibility, a11y, WCAG, or aria.'

DimensionReasoningScore

Specificity

"Fix accessibility issues" names the domain and one generic action, and "a11y audits" adds a second; this matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' (cf. 'Processes PDF files and extracts content'). Not 4 because it does not list several specific actions (no mention of names, keyboard, focus, forms, contrast work), and not 2 because it does go beyond naming the domain.

3 / 5

Completeness

Both parts are explicitly present: "Fix accessibility issues" answers what, and "Use for a11y audits or fixes" is an explicit when clause (so the missing-'Use when' cap at 3 does not apply). Not 5 because the when clause is narrow — it only covers audits/fixes and repeats the what, unlike the body's richer 'when to apply' list (buttons, forms, dialogs, focus).

4 / 5

Trigger Term Quality

Relevant keywords present are "accessibility", "a11y" (the key synonym), "audits", and "fixes", but common natural phrases users say in this domain are absent — "WCAG", "aria", "screen reader", "keyboard navigation", "contrast". This fits 'Some relevant keywords but missing common variations or synonyms'; not 4 because more than a few natural terms are missing for this domain.

3 / 5

Distinctiveness Conflict Risk

"accessibility" and "a11y" are distinct niche triggers with minimal conflict risk against unrelated skills. Not 5 because the thin phrasing ("Fix accessibility issues") leaves minor overlap risk with general UI-fix or frontend-review skills, fitting 'Mostly distinct; minor overlap risk with closely related skills'.

4 / 5

Total

14

/

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

marchatton/agent-skills

Path

.agents/skills/04-develop/01-ui-skills-dot-com/fixing-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.