Content
93%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.
An exemplary lean skill body: specific collection checklists per research mode, a mandated output structure, and a pre-delivery quality gate that enforces sourcing and decision orientation. The only improvement space is making the overall process sequence explicit rather than implied by section order.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence ('Produce research that supports decisions, not research theater.'; terse checklists like 'fund size, stage, and typical check size') with zero padding and no explanation of concepts Claude already knows — every token earns its place. | 5 / 5 |
Actionability | For an instruction-only skill, the guidance is fully concrete: mode-specific collection checklists, an explicit default output structure ('1. executive summary ... 6. sources'), and a pre-delivery quality gate. No gaps in what to collect or how to structure the deliverable. | 5 / 5 |
Workflow Clarity | The flow (standards → mode-specific collection → output structure → Quality Gate) is clearly sequenced and the Quality Gate is an explicit validation checklist before delivery, but the end-to-end process order is implied by section order rather than a numbered sequence, and there is no fix-and-retry feedback loop — fitting 'clear sequence with most checkpoints present; minor validation gaps' rather than the fully explicit anchor at 5. | 4 / 5 |
Progressive Disclosure | A single self-contained file with well-organized, clearly headed sections and no external references (none exist, and none are needed at ~70 lines); per the rubric's simple-skill guidance, well-organized sections alone warrant the top score here. | 5 / 5 |
Total | 19 / 20 Passed |