create-property
Generate a visual property annotation in Figma showing each configurable property axis with component instance previews. Use when the user mentions "property", "properties", "property annotation", "create property", or wants to document a component's configurable properties visually.
81
77%
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-property/SKILL.mdQuality
Discovery
100%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 skill description that clearly communicates a specific capability within Figma, includes explicit trigger guidance with natural user terms, and occupies a distinct niche. It follows the recommended pattern of stating what the skill does followed by a 'Use when...' clause with concrete trigger terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists specific concrete actions: 'Generate a visual property annotation in Figma showing each configurable property axis with component instance previews.' This clearly describes what is produced and how it works. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate a visual property annotation in Figma showing configurable property axes with component instance previews) and 'when' (explicit 'Use when...' clause with specific trigger terms and intent description). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'property', 'properties', 'property annotation', 'create property', 'configurable properties', and 'Figma'. These cover common variations of how a user would request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche of Figma property annotations with component instance previews. The combination of 'Figma', 'property annotation', and 'component instance previews' makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at actionability and workflow clarity — every step has executable code, clear sequencing, validation checkpoints, and error recovery. However, it is severely undermined by its extreme length (~1500+ lines) with massive code duplication (helper functions repeated 8+ times), redundant explanatory notes, and a complete lack of progressive disclosure. The content desperately needs to be split across multiple files with the SKILL.md serving as a concise overview.
Suggestions
Extract the repeated helper functions (loadAllFonts, loadFontWithFallback, findNestedChild, findControllingBoolRawKey) into a shared reference file and reference them once, rather than duplicating them in every script block.
Move the detailed script templates (6a through 6g) into a separate TEMPLATES.md or SCRIPTS.md file, keeping only the workflow overview and decision logic in the main SKILL.md.
Remove or drastically condense the Notes section — most of it restates information already present in the workflow steps (e.g., variant-gated booleans, coupled axis detection, slot awareness are all explained in both the steps and the notes).
Consolidate the MCP Adapter table and font-loading workaround into a separate MCP_ADAPTER.md reference file, since these are cross-cutting concerns not specific to this skill's core logic.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~1500+ lines. It contains massive amounts of duplicated code (the loadAllFonts and loadFontWithFallback helper functions are repeated verbatim in nearly every script block), extensive explanatory notes that Claude could infer, and a Notes section that largely restates what was already covered in the workflow steps. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript code blocks for every step, with specific Figma Plugin API calls, concrete data structures, and copy-paste-ready scripts with clear placeholder conventions (__PLACEHOLDER__). Every operation has a complete, runnable implementation. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with a progress checklist, explicit step numbering (1-8), validation checkpoints (Step 3e AI validation layer, Step 8 visual validation with up to 3 iterations), error recovery via try/catch rollback patterns on every chapter creation, and clear conditional branching (in-context vs blown-out rendering, figma-console vs figma-mcp adapter). | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of content with no references to external files. Steps 3a-3e, 6a-6g, and the extensive Notes section could be split into separate reference files. The inline code blocks alone account for hundreds of lines that could be externalized, with the main SKILL.md providing an overview and navigation. | 1 / 3 |
Total | 8 / 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 (2090 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.