Content
81%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 body delivers a clearly sequenced, highly actionable two-phase workflow with explicit checkpoints and feedback loops, written for the model without concept padding. The only weaknesses are minor redundancy in the closing guidelines section and a slightly under-specified Linear step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient and assumes Claude's competence — no re-teaching of concepts — but the 'Important guidelines' section partially repeats guidance already stated inline (e.g., the no-visual-assumptions rule appears in both Phase 1 and the guidelines), which could be trimmed. | 4 / 5 |
Actionability | Highly concrete guidance throughout — literal conversational scripts, named tools (Figma MCP get_design_context/get_screenshot, Read, EnterPlanMode/ExitPlanMode), a detailed plan template, and a fallback path — with one minor gap: 'Use the Linear MCP tools' leaves the actual tool invocation unspecified. | 4 / 5 |
Workflow Clarity | The two-phase workflow is clearly sequenced with explicit validation checkpoints ('If they confirm, move to Phase 2'; 'After the plan is confirmed, create a Linear issue') and genuine feedback loops (loop back on user adjustments; fall back to a markdown file if Linear MCP is unavailable), matching the top anchor. | 5 / 5 |
Progressive Disclosure | A single well-sectioned file with no nested or dead references and all content appropriately inline for a conversational workflow; at ~120 lines it exceeds the simple-skill threshold, and segments like the plan template or example dialogues could be moved to reference files, so it fits the 'good structure, minor organization gaps' anchor. | 4 / 5 |
Total | 17 / 20 Passed |