Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, actionable skill body with a clear sequenced workflow and clean progressive disclosure to real reference files. The main weakness is mild redundancy between the required-flow steps and the implementation-rules bullets.
Suggestions
De-duplicate guidance that appears in both 'Required flow' and 'Implementation rules' (e.g., translate-to-conventions and validate-against-Figma) so each rule lives in one place and the body tightens toward a 3 on conciseness.
Consider merging the 'Implementation rules' bullets that restate flow steps into a single source of truth, keeping the numbered flow as the spine.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with no concept-explaining padding, but the 'Required flow' and 'Implementation rules' overlap — translate-to-conventions and validate-against-Figma each appear in both sections — so it could be tightened rather than every token earning its place. | 2 / 3 |
Actionability | Names concrete MCP tools (get_design_context, get_metadata, get_screenshot) with precise directives and exact asset-handling rules; for an instruction-only skill the guidance is concrete and specific rather than abstract. | 3 / 3 |
Workflow Clarity | A clearly numbered six-step flow with explicit ordering ('do not skip', 'Only after you have both'), a re-fetch feedback loop for truncation, and an explicit validation checkpoint before marking complete. | 3 / 3 |
Progressive Disclosure | SKILL.md is a concise overview that signals two real, one-level-deep reference files (figma-mcp-config.md, figma-tools-and-prompts.md) with one-line descriptions in a References section for easy navigation. | 3 / 3 |
Total | 11 / 12 Passed |