Content
85%Weight 40%Scale 1-5Reviews 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 validated workflow and clean progressive disclosure into two reference files. The only real improvement space is trimming minor redundancy and adding a concrete code/tool-call example block.
Suggestions
Consolidate the three 'IMPORTANT' asset-handling bullets into a single concise rule to tighten conciseness.
Add one short example showing the exact MCP tool-call sequence (get_design_context -> get_screenshot -> implementation) to push actionability to anchor 5.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is directive and assumes Claude's competence without explaining what Figma is, but the three overlapping 'IMPORTANT' asset-handling bullets and some restated rules keep it just shy of the lean anchor 5. | 4 / 5 |
Actionability | Concrete, specific MCP tool calls (get_design_context, get_metadata, get_screenshot) with an explicit ordered flow are highly actionable, but there is no literal executable code/command block, leaving a minor gap versus anchor 5. | 4 / 5 |
Workflow Clarity | A numbered 'Required flow (do not skip)' sequence includes an explicit validation checkpoint (step 6: 'Validate against Figma for 1:1 look and behavior') and a feedback loop (step 2: if truncated, get_metadata then re-fetch), matching the anchor 5 example. | 5 / 5 |
Progressive Disclosure | SKILL.md is a concise overview that offloads setup/debugging and the tool catalog to two real, one-level-deep reference files, both clearly signaled inline and in a References section. | 5 / 5 |
Total | 18 / 20 Passed |