figma-code-connect
Creates and maintains Figma Code Connect template files that map Figma components to code snippets. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.ts or .figma.js files.
71
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 an excellent skill description that clearly defines its purpose, lists concrete actions, includes a well-formed 'Use when...' clause with multiple natural trigger terms, and occupies a highly distinctive niche. It follows the third-person voice convention and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Creates and maintains Figma Code Connect template files' and 'map Figma components to code snippets'. Also mentions specific file types (.figma.ts, .figma.js). | 3 / 3 |
Completeness | Clearly answers both 'what' (creates and maintains Figma Code Connect template files that map Figma components to code snippets) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'Code Connect', 'Figma component mapping', 'design-to-code translation', '.figma.ts', '.figma.js'. These cover both the conceptual terms users would say and the specific file extensions they might reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — Figma Code Connect is a very specific tool/workflow. The mention of .figma.ts/.figma.js files and 'Code Connect' makes it extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, highly actionable skill with an excellent multi-step workflow, clear validation checkpoints, and comprehensive executable examples. Its main weakness is length — the document is verbose with redundant patterns shown in multiple sections and an inline API reference that likely duplicates the referenced api.md file. The progressive disclosure could be improved by moving the quick reference and some detailed pattern examples into the referenced files.
Suggestions
Move the 'Inline Quick Reference' section to api.md (or confirm it lives there) and replace it with a brief pointer, reducing the main file by ~50 lines
Consolidate redundant icon/executeTemplate examples — the same pattern appears in property mapping, nested components, rules/pitfalls, and the worked example; show it once in detail and reference it elsewhere
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive and mostly well-structured, but it's quite long (~400+ lines) with some redundancy. Several patterns are shown multiple times (e.g., the icon/executeTemplate pattern appears in property mapping, nested components, rules/pitfalls, and the worked example). The inline quick reference duplicates information already covered in the step-by-step sections. Some explanations could be tightened, though it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | Extremely actionable with fully executable TypeScript code examples, specific MCP tool calls with exact parameter names, concrete URL parsing examples, complete property mapping tables, and a full worked example from URL to finished template file. Every step has concrete, copy-paste-ready guidance. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit validation in Step 6 including a detailed checklist. Steps 2-3 include explicit error handling (empty responses, missing components) with stop conditions. Step 4 includes a confirmation checkpoint with the user before proceeding. The feedback loop in Step 6 (read back, verify, flag missing properties) covers the validation requirement well. | 3 / 3 |
Progressive Disclosure | References to advanced-patterns.md and api.md are well-signaled and one level deep, which is good. However, the main SKILL.md itself is very long with substantial inline content (the full API quick reference, extensive property mapping tables, rules/pitfalls section) that could arguably be split into reference files. The inline quick reference section essentially duplicates what should be in api.md. Without bundle files to verify, the references exist but the main file carries too much detail inline. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (528 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- figma/mcp-server-guide
- Commit
fabc1ca
- 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.