CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-audit-accessibility

Use when the user mentions accessibility checking, App Store submission, code review, or WCAG compliance.

61

Quality

71%

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 ./axiom-codex/skills/axiom-audit-accessibility/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 skill body is a high-quality, actionable audit workflow with concrete grep patterns, executable fix code, clear phase sequencing, and validation checkpoints. Its only weakness is that it inlines a substantial catalog that could be partially offloaded to reference files for better progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense and largely earns its tokens with concrete grep patterns, fix examples, and tables, but a few explanatory passages (e.g. restating why partial accessibility is worse than none) could be trimmed.

4 / 5

Actionability

Each anti-pattern gives exact Grep patterns, contextual Read verification, and copy-paste fix code in both SwiftUI and UIKit, covering the common cases comprehensively.

5 / 5

Workflow Clarity

Five labeled phases are clearly sequenced with a validation checkpoint ('For every grep match, use Read to verify the surrounding context before reporting'), cross-reference bump rules, and an output checklist — explicit feedback loops throughout.

5 / 5

Progressive Disclosure

Structure is strong with phased sections and well-signaled one-level references to other skills/refs (xcui-ref, typography-ref, ux-flow-audit), but the body itself is fairly monolithic (~250 lines) with some content (e.g. the full anti-pattern catalog) that could live in a reference file.

4 / 5

Total

18

/

20

Passed

Description

58%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 clearly trigger-oriented and reads naturally, but it omits any explicit statement of what the skill does, relying entirely on 'when' guidance. Adding concrete capability verbs would raise both specificity and completeness.

Suggestions

Lead with concrete actions, e.g. 'Detects accessibility violations and missing assistive-technology support in Swift apps,' before the 'Use when' clause.

Keep the strong triggers but consider dropping or narrowing 'code review' to reduce overlap with general review skills.

Add domain synonyms users say naturally, such as 'VoiceOver', 'Dynamic Type', or 'a11y'.

DimensionReasoningScore

Specificity

The description names the domain (accessibility, App Store, WCAG) but lists only trigger contexts rather than concrete actions; there are no action verbs like 'detect', 'audit', or 'scan' that anchor a score 4.

3 / 5

Completeness

The 'when' is explicit ('Use when the user mentions...'), but the 'what' is only weakly implied — no concrete capability is stated — which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Natural phrases users would say ('accessibility checking', 'App Store submission', 'code review', 'WCAG compliance') are present, but common synonyms like 'VoiceOver', 'Dynamic Type', or 'a11y' are missing, so it stops short of a 5.

4 / 5

Distinctiveness Conflict Risk

The accessibility/WCAG/App Store niche is fairly distinct, but the broad trigger 'code review' introduces overlap risk with general code-review skills, keeping it just below a 5.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CharlesWiltgen/Axiom
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.