Content
82%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 efficient, well-structured instruction-only skill with concrete collection checklists and a quality gate. It could be strengthened with explicit data-acquisition methods and a feedback loop for surfacing source gaps.
Suggestions
Add specific, named source types or retrieval methods (e.g., 'company 10-K filings', 'Crunchbase for funding history', 'CB Insights for market sizing reports') to make the collection checklists more executable.
Introduce a brief validate-and-iterate loop in the Quality Gate (e.g., 'if any number is unsourced, return to research before delivering') to strengthen the feedback path.
Consider splitting the per-mode collection lists into a reference file so SKILL.md stays a tighter overview once the skill grows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and well-organized with no padding or explanation of concepts Claude already knows; every section ('Research Standards', 'Common Research Modes', 'Quality Gate') earns its place. | 5 / 5 |
Actionability | Provides concrete, actionable guidance via collection checklists per mode, a numbered output format, and a quality-gate checklist, though it stops short of specifying sources or methods for acquiring the data. | 4 / 5 |
Workflow Clarity | A clear sequence runs from activation criteria through research modes to output format and a pre-delivery Quality Gate checklist, but there is no explicit validate-fix-retry feedback loop. | 4 / 5 |
Progressive Disclosure | Well-structured with clear section headers and self-contained content; no bundle files exist, so the one-level-deep reference pattern of the top anchor does not apply, leaving minor organization gaps. | 4 / 5 |
Total | 17 / 20 Passed |