Content
85%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is concise, well-structured, and includes a pre-delivery quality gate, but its research guidance stays at the level of 'what to collect' rather than concrete sourcing or example outputs. Tightening actionability would lift the weakest dimension.
Suggestions
Add 1–2 concrete sourcing hints or example data sources per research mode (e.g., specific public datasets or report types for market sizing) to move guidance from 'what to collect' to 'how to collect'.
Include a short worked example of the output format (e.g., a sample executive summary block) so the expected deliverable is unambiguous.
Tie the Quality Gate items more explicitly back to the Research Standards so verification maps to specific evidence requirements.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean — '提供支持决策的研究，而非流于形式的研究报告' — and avoids explaining concepts Claude already knows; every section earns its place without padding. | 3 / 3 |
Actionability | It lists specific data points to collect per mode ('基金规模、阶段和典型单笔投资额', '分销渠道和定价线索') but offers no concrete sourcing methods, templates, or worked examples, leaving guidance incomplete per the instruction-only anchor. | 2 / 3 |
Workflow Clarity | A clear progression (standards → modes → output format) culminates in an explicit '在交付前确认' Quality Gate checklist that serves as a validation checkpoint before delivery. | 3 / 3 |
Progressive Disclosure | A single, well-sectioned SKILL.md with no bundle files and clear headings; for a compact single-purpose skill this satisfies the well-organized-content allowance without external references. | 3 / 3 |
Total | 11 / 12 Passed |