create-api
Generate API overview specifications documenting component properties, values, defaults, and configuration examples. Use when the user mentions "api", "api spec", "props", "properties", "component api", or wants to document a component's configurable properties.
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-api/SKILL.mdQuality
Discovery
92%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 well-crafted skill description that clearly communicates its purpose and includes explicit trigger guidance. It lists concrete actions and provides good keyword coverage for matching user intent. The only minor weakness is potential overlap with other API-related skills due to the breadth of the 'api' trigger term.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate API overview specifications', 'documenting component properties, values, defaults, and configuration examples'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate API overview specifications documenting component properties, values, defaults, and configuration examples) and 'when' (explicit 'Use when...' clause with specific trigger terms). | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms users would say: 'api', 'api spec', 'props', 'properties', 'component api', and 'document a component's configurable properties'. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | While it targets API documentation specifically for component properties, the term 'api' is broad and could overlap with skills for API client generation, API testing, or general documentation skills. The focus on 'component properties' helps narrow it but 'api spec' could still conflict. | 2 / 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 excellent workflow clarity, providing complete executable code and a well-structured multi-step process with validation checkpoints. However, it severely suffers from token inefficiency — the inline JavaScript blocks alone consume hundreds of lines that could be externalized, and there is redundant commentary throughout. The progressive disclosure is partially implemented but the main file remains monolithic due to all the inline code.
Suggestions
Extract the large JavaScript code blocks (Steps 4b, 10, 11, 12) into separate referenced files (e.g., `scripts/extract-properties.js`, `scripts/fill-table.js`) and reference them from SKILL.md with brief descriptions of inputs/outputs.
Remove redundant explanations of what extracted fields mean — the field names and the code are self-documenting. For example, the bullet list after Step 4b explaining each field of the return object adds ~30 lines that duplicate what the code already shows.
Consolidate the repeated font-loading pattern into a note that says 'All scripts use the loadAllFonts helper' rather than repeating the same 10-line block in every code snippet.
Move the MCP Adapter table and figma-mcp page context workaround to a shared reference file since these appear to be cross-skill concerns, not specific to API overview generation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~600+ lines. It includes massive inline JavaScript code blocks that could be referenced from external files, extensive explanatory commentary that Claude could infer, and repeated patterns (font loading, template cloning) that bloat the token budget significantly. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript code blocks with specific Figma API calls, concrete placeholder patterns for variable substitution, and precise step-by-step instructions. Every step has copy-paste ready code with clear parameter documentation. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with 14 numbered steps, includes a progress checklist, has explicit validation in Step 7 (audit against instruction file) and Step 13 (visual validation with up to 3 fix iterations), and includes error recovery guidance for MCP connection failures. | 3 / 3 |
Progressive Disclosure | The skill references an external instruction file (agent-api-instruction.md) and config file (uspecs.config.json) appropriately, but the SKILL.md itself is monolithic — massive code blocks for Steps 4b, 10, 11, and 12 should be in separate referenced files rather than inline, making the main file a wall of code. | 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 (974 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- redongreen/uSpec
- Commit
4eae941
- 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.