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
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 description that clearly communicates what the skill does and when to use it. It lists specific actions, includes natural trigger terms with good variation coverage, and occupies a distinct niche. The description is concise, uses third person voice, and follows best practices.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generating API overview specifications, documenting component properties, values, defaults, and configuration examples. | 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 natural keywords 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 | Targets a clear niche — API specification generation for component properties — with distinct trigger terms like 'api spec', 'props', 'component api' that are unlikely to conflict with general documentation or code generation 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.
The skill is highly actionable with executable code and a well-structured workflow including validation checkpoints and error recovery. However, it is severely bloated — the inline JavaScript code blocks make it extremely long and repetitive (font loading boilerplate appears 5+ times). The content would benefit enormously from extracting scripts into separate files and referencing them, which would also improve progressive disclosure.
Suggestions
Extract the large JavaScript code blocks (extraction script, fill scripts) into separate .js files and reference them from the skill, e.g., 'Run [scripts/extract-properties.js](scripts/extract-properties.js) via figma_execute'
Create a shared utility snippet for the repeated font-loading boilerplate and page-loading block, referenced once rather than duplicated in every step
Move the MCP adapter table to a separate reference file (e.g., MCP_ADAPTER.md) since it's a cross-cutting concern likely shared across multiple skills
Consolidate the Notes section content into the relevant steps rather than repeating/summarizing information already covered in the workflow
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines, with massive inline JavaScript code blocks that could be referenced from external files. The MCP adapter table, extraction script, and all the fill scripts bloat the content enormously. Much of this (font loading boilerplate, node traversal patterns) is repeated across steps. | 1 / 3 |
Actionability | Every step provides fully executable JavaScript code with specific Figma API calls, placeholder variables clearly marked, and concrete MCP tool names. The code is copy-paste ready with clear substitution points (__FRAME_ID__, __PROPERTIES_JSON__, etc.). | 3 / 3 |
Workflow Clarity | The 14-step workflow is clearly sequenced with a progress checklist, explicit validation in Step 7 (audit against instruction file) and Step 13 (visual validation with up to 3 fix iterations). Error recovery is addressed for MCP connection failures and the workflow includes conditional branching (11a vs 11b for sub-components). | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of content with all JavaScript code blocks inline. The extraction script alone is ~100 lines, and each fill step has 50-80 lines of JS. These scripts should be in separate referenced files. The skill references agent-api-instruction.md appropriately but fails to offload its own bulk content. | 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 (822 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.