CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

accessibility-review

Reviews keyboard navigation support, semantic HTML tags, drawer/dialog behaviors, focus management, and screen-reader standards. Use during UI audits.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/accessibility-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 concise, well-structured review checklist with concrete, actionable a11y criteria and a clear protocol sequence. Its only notable weaknesses are the absence of example markup or verification commands and external references that point outside the skill bundle rather than to bundled, one-level-deep files.

DimensionReasoningScore

Conciseness

The body is lean and efficient with zero concept explanations — it names specific elements and attributes (e.g. '<button>, <a> rather than div tags with onClick', 'aria-label', '<thead>, <tbody>, <th>') without explaining what they are, assuming Claude's competence. Every line carries actionable review criteria, matching the 'lean and efficient' anchor.

5 / 5

Actionability

Provides mostly concrete, executable review checks: semantic element choices, focus trapping with 'Esc key cancellation', 'aria-label' for icon-only buttons, and correct table structure tags. Not 5 because there are no good/bad markup examples or verification commands (e.g. a failing div+onClick anti-pattern or a query to locate offenders), leaving minor gaps.

4 / 5

Workflow Clarity

A clear before/during/after sequence is present: follow 'AGENTS.md review throttling ... before starting', guardrails ('Do not review opportunistically or mutate files'), the two-part checklist, then 'post one Review record comment on the PR' after completion. Not 5 because there is no explicit checkpoint confirming checklist completion or how findings feed into the Review record; not 3 since the sequence and guardrails are well defined.

4 / 5

Progressive Disclosure

Well-organized short body (~19 lines) with clear ## / ### sections and nothing inlined that belongs in a separate file. Not 5 because all references (AGENTS.md, docs/codex-review-protocol.md, ../../../docs/agents/pull-request-workflow.md, docs/branch-review-ledger.md) point outside the skill bundle and cannot be verified as reachable from the skill's location, leaving navigation gaps.

4 / 5

Total

17

/

20

Passed

Description

67%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 specific, concrete, and correctly structured with a third-person 'what' plus an explicit 'Use during UI audits' trigger. Its main weakness is trigger-term coverage: it never uses the words users most commonly say (accessibility, a11y, ARIA, WCAG), relying instead on narrower technical phrases.

Suggestions

Add the most common user phrasings to the trigger clause, e.g. 'Use during UI audits or when the user mentions accessibility, a11y, ARIA, WCAG, or screen-reader issues.'

Mention additional concrete review areas such as color contrast, alt text, and ARIA roles to close the coverage gaps and improve specificity and distinctiveness.

Expand 'Use during UI audits' into a fuller trigger with concrete phrases (e.g. 'when auditing a UI for keyboard or screen-reader accessibility') to reach explicit what-and-when completeness.

DimensionReasoningScore

Specificity

Lists five concrete review areas ("keyboard navigation support, semantic HTML tags, drawer/dialog behaviors, focus management, and screen-reader standards"), matching the 'several specific actions; minor gaps' anchor. Not 5 because notable a11y concerns like color contrast, alt text, and ARIA are not mentioned, leaving minor coverage gaps.

4 / 5

Completeness

Clearly answers 'what' (reviews the five listed areas) and explicitly answers 'when' ("Use during UI audits"), matching the anchor 'Has both what and when; when could be more explicit or specific'. Not 5 because the trigger clause is terse and lacks concrete trigger phrases like 'when the user mentions accessibility or screen readers'.

4 / 5

Trigger Term Quality

Includes some natural keywords users would say ("keyboard navigation", "screen-reader", "drawer/dialog", "focus management"), but misses the most common variations and synonyms: "accessibility", "a11y", "ARIA", "WCAG". Fits the 'some relevant keywords but missing common variations' anchor rather than 4, where only a few natural terms would be missing.

3 / 5

Distinctiveness Conflict Risk

The combination of keyboard navigation, focus management, and screen-reader standards carves a mostly distinct niche with minor overlap risk against general frontend/code-review skills ("semantic HTML tags" review could overlap). Not 5 because it lacks the crisply distinct trigger set of the top anchor.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.cursor/skills/accessibility-review/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.