figma-design
Figma design-to-code workflows, design token extraction, component inspection, and asset export. Use when translating Figma designs into code, extracting design tokens, or referencing component specs.
77
96%
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 a strong skill description that clearly identifies its domain (Figma), lists specific capabilities, and includes an explicit 'Use when' clause with natural trigger terms. It follows the third-person voice convention and is concise without being vague. It closely matches the good examples in the rubric.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'design-to-code workflows', 'design token extraction', 'component inspection', and 'asset export'. These are distinct, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (design-to-code workflows, design token extraction, component inspection, asset export) and 'when' with an explicit 'Use when' clause covering translating Figma designs, extracting tokens, or referencing component specs. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Figma', 'design-to-code', 'design tokens', 'component specs', 'asset export'. These cover the primary terms a user working with Figma would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The 'Figma' anchor makes this highly distinctive. It's unlikely to conflict with generic code generation or design skills because it's specifically scoped to Figma design workflows. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with strong actionability, a clear multi-step workflow with validation and feedback loops, and efficient use of tokens. The main weakness is that it references REFERENCE.md which doesn't exist in the bundle, slightly undermining progressive disclosure. Overall, the content is highly practical and well-structured for guiding Claude through Figma design-to-code tasks.
Suggestions
Provide the referenced REFERENCE.md file containing the verification script and Figma→CSS translation rules, or inline the most critical rules if the file won't be bundled.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Figma is or how MCP tools work conceptually—it jumps straight to tool names, purposes, and invocation examples. Every section earns its place. | 3 / 3 |
Actionability | Provides concrete MCP invocation JSON, a complete TSX component example, specific acceptance criteria (<=4px spacing, matching token colors/fonts), and named file paths for token output. Guidance is specific and executable. | 3 / 3 |
Workflow Clarity | The design-to-code workflow is clearly sequenced (6 steps), includes an explicit verification step with measurable thresholds, and has a feedback loop (step 6) that routes back to step 2 when deviations are detected. | 3 / 3 |
Progressive Disclosure | References REFERENCE.md for verification scripts and translation rules, and mentions a 'frontend-design' skill for project-specific details—good signaling. However, no bundle files are provided, so REFERENCE.md doesn't actually exist, and the main content is moderately dense without additional supporting files to offload detail. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- monkilabs/opencastle
- Commit
cc13aaf
- 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.