figma
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Use when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting. Covers general Figma data fetching and exploration. Do NOT use when the goal is specifically pixel-perfect code implementation from a Figma design (use figma-implement-design instead).
88
85%
Does it follow best practices?
Impact
Pending
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 capabilities, provides natural trigger terms, explicitly states when to use it, and proactively distinguishes itself from a related skill. The inclusion of a 'Do NOT use when' clause with a specific alternative skill name is a best practice that minimizes conflict risk. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'fetch design context, screenshots, variables, and assets from Figma', 'translate Figma nodes into production code', and 'Figma MCP setup and troubleshooting'. These are clearly defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (fetch design context, screenshots, variables, assets; translate nodes to code) and 'when' ('Use when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup'). Also includes an explicit negative boundary ('Do NOT use when...') which further clarifies usage. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Figma URLs', 'node IDs', 'design-to-code', 'Figma MCP', 'screenshots', 'variables', 'assets'. These cover the natural language a user would use when requesting Figma-related tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from a sibling skill ('figma-implement-design') by defining a clear boundary: general Figma data fetching vs. pixel-perfect code implementation. This negative trigger clause significantly reduces conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%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-structured skill with clear workflow sequencing and good progressive disclosure through reference files. Its main weakness is the lack of concrete executable examples (e.g., actual MCP tool invocation syntax) and some minor redundancy between sections. The workflow clarity is strong with explicit ordering and validation steps.
Suggestions
Add a concrete example showing an actual MCP tool invocation (e.g., a sample get_design_context call with a real-looking node ID and expected output structure) to improve actionability.
Remove the duplicate 'validate against Figma' instruction that appears in both the required flow (step 6) and implementation rules to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy—e.g., 'Validate against Figma for 1:1 look and behavior' appears in both the required flow and implementation rules. Some bullet points like 'Treat the Figma MCP output as a representation of design and behavior, not as final code style' could be tightened. Overall mostly lean but not maximally efficient. | 2 / 3 |
Actionability | Provides a clear ordered workflow with specific tool names (get_design_context, get_screenshot, get_metadata), but lacks concrete executable code examples or copy-paste commands. The guidance is specific enough to follow but remains at the instruction level rather than providing executable snippets. | 2 / 3 |
Workflow Clarity | The required flow is clearly numbered with explicit sequencing and a conditional fallback step (step 2 for truncated responses). There's a clear validation checkpoint at step 6, and the 'do not skip' directive makes the workflow unambiguous. The progression from data fetching → screenshot → assets → implementation → validation is well-structured. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to figma-mcp-config.md for setup/debugging and figma-tools-and-prompts.md for tool catalog and prompts. Content is appropriately split between the main skill and reference files. | 3 / 3 |
Total | 10 / 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
- tech-leads-club/agent-skills
- Commit
81e7e0d
- 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.