create-voice
Generate screen reader accessibility specifications for VoiceOver (iOS), TalkBack (Android), and ARIA (Web). Use when the user mentions "voice", "voiceover", "screen reader", "accessibility spec", "talkback", "aria", or wants to create accessibility documentation for a UI component.
80
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.cursor/skills/create-voice/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent trigger term coverage and a clear 'Use when' clause that makes it easy for Claude to select appropriately. The main weakness is that the 'what' portion could be more specific about the concrete outputs or actions beyond just 'generate specifications.' Overall, it's well-crafted and clearly distinguishable from other skills.
Suggestions
Add more specific concrete actions/outputs, e.g., 'Generates trait mappings, focus order, announcement text, and role definitions for screen reader accessibility specifications.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (screen reader accessibility specifications) and lists the three platforms (VoiceOver, TalkBack, ARIA), but doesn't enumerate specific concrete actions beyond 'generate specifications' and 'create accessibility documentation'. It could list more specific outputs like trait mappings, focus order, announcement text, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate screen reader accessibility specifications for VoiceOver, TalkBack, and ARIA) and 'when' (explicit 'Use when...' clause with specific trigger terms and use cases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'voice', 'voiceover', 'screen reader', 'accessibility spec', 'talkback', 'aria', and 'accessibility documentation for a UI component'. These are terms users would naturally use when requesting this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on screen reader accessibility specifications across three named platforms. The trigger terms are specific enough to avoid conflicts with general accessibility, coding, or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with executable code and a well-structured multi-step workflow with validation checkpoints. However, it is severely bloated — the rendering script in Step 10-11 alone is ~250 lines, slot insertion logic is duplicated multiple times, and the Notes section (~60 lines) largely restates what the code already communicates. The token cost is extremely high relative to the unique information conveyed.
Suggestions
Extract the large Step 10-11 rendering script and the Step 4 extraction script into separate referenced files (e.g., render-state.js, extract-component.js) to dramatically reduce inline token count while keeping the workflow overview lean.
Eliminate the Notes section entirely or reduce it to 3-5 bullet points covering only non-obvious gotchas — most notes restate implementation details already visible in the code (e.g., 'The extraction script deep-recurses into SLOT nodes' is evident from reading the code).
Deduplicate the slot insertion logic which appears nearly identically in the main rendering path, the richest-variant fallback, and the variant search loop — extract it into a named helper function within the script.
Remove explanatory phrases like 'This walks up to the PAGE ancestor and loads its content' and 'consistent with the anatomy skill's approach' — Claude can infer these from context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~700+ lines. It contains massive JavaScript code blocks that are repeated with minor variations (e.g., slot insertion logic appears 3+ times), extensive notes sections that restate what the code already does, and explanations of internal implementation details (e.g., 'The extraction script deep-recurses into SLOT nodes') that Claude could infer from reading the code itself. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript code blocks with specific Figma API calls, concrete template names, exact placeholder patterns, and copy-paste ready scripts. Every step has specific, executable guidance with real code rather than pseudocode. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with 13 numbered steps, includes a progress checklist, has explicit validation in Step 12 with up to 3 retry iterations, and includes error handling guidance (e.g., MCP connection failures, missing template keys). The feedback loop for visual validation is well-defined. | 3 / 3 |
Progressive Disclosure | The skill references external files well (voiceover.md, talkback.md, aria.md, agent-screenreader-instruction.md) and has a clear step structure. However, the massive inline code blocks and the extensive Notes section (which restates implementation details already present in the code) make this a near-monolithic document. Much of the rendering code and notes could be extracted to separate reference files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1085 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- redongreen/uSpec
- Commit
b1213ef
- 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.