Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, well-structured procedural skill: lean directives, concrete tool usage, an explicit hint-priority order, and error-recovery feedback loops. It appropriately delegates parameter mechanics to the tool description rather than duplicating them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and directive — it avoids explaining what Figma is or how libraries work, and actively avoids duplication by pushing parameter mechanics onto the get_design_context tool description ('follow them there'). Not level 2: there is no unnecessary explanation to tighten. | 3 / 3 |
Actionability | Gives concrete, specific guidance — exact tool names (get_design_context vs get_metadata/get_screenshot), an ordered 5-level priority scheme for response hints, and named error conditions. As an instruction-only workflow skill, the absence of code is not penalized because the guidance is actionable. | 3 / 3 |
Workflow Clarity | A clearly numbered four-step sequence (call get_design_context → treat as reference → reuse project assets → honor hints by priority) with an explicit Error Recovery section containing feedback loops (stop and read the message before retrying; retry against a smaller node on timeout). | 3 / 3 |
Progressive Disclosure | Under ~50 lines with no bundle files and no need for external references, yet well-organized into Direction/Scope, Workflow, and Error Recovery sections — matching the scoring note that simple skills can score 3 with just well-organized sections. | 3 / 3 |
Total | 12 / 12 Passed |