Content
78%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.
The content is compact, well-structured, and actionable via a concrete tool-routing table and sequenced workflow with validation, with only minor gaps (a duplicated purpose line, no usage examples, and no explicit error-recovery feedback loop).
Suggestions
Add an explicit feedback loop after the validate step (e.g., "If validation fails, fix the reported issues and re-run design_validate before proceeding") to push workflow_clarity toward 5.
Remove the redundant "## Purpose" line (it repeats the frontmatter description) or replace it with unique framing to improve conciseness.
Include one or two short worked examples of calling a tool (e.g., design_create_screen for a frame, design_update_shapes for a shape) to move actionability from 4 to 5.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with no concept over-explanation and a dense tool-routing table; not a 5 because the "## Purpose" line duplicates the frontmatter description verbatim and could be trimmed. | 4 / 5 |
Actionability | The tool-routing table lists concrete executable tool names (design_create_screen, design_update_shapes, etc.) mapped to uses; not a 5 because no worked usage examples are shown for the common cases. | 4 / 5 |
Workflow Clarity | A clear 5-step sequence with an explicit "Validate the resulting design" checkpoint plus a Completion-gates checklist; not a 5 because no validate→fix→retry feedback loop is described for error recovery. | 4 / 5 |
Progressive Disclosure | At ~35 lines the self-contained body is organized into well-signaled sections (Purpose, Tool routing, Workflow, Completion gates, Boundaries, Delivery) with no nested references, meeting the simple-skill exception for a 5. | 5 / 5 |
Total | 17 / 20 Passed |