Content
86%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.
A compact, well-structured instruction-only skill that keeps the overview in SKILL.md and delegates deeper questions to a real reference file. Actionability and workflow clarity are strong but could be strengthened with a short worked example.
Suggestions
Add one short worked example showing a sample risk verdict and the five-part output for a concrete idea, to raise actionability.
Include an explicit checkpoint for when to escalate to references/risk-checklist.md beyond the single 'verdict not obvious' cue.
Show a brief example of a 'reduced build scope' recommendation so the Do-next and Delay outputs are unambiguous.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean ~45-line body that assumes Claude's competence; no padding or explanation of concepts Claude already knows, and every section earns its place. | 5 / 5 |
Actionability | Provides concrete checklist questions and a specific five-part output format, but lacks any worked example of a verdict or sample output to anchor the guidance. | 4 / 5 |
Workflow Clarity | Clear sequence from risk review through a conditional reference checkpoint to a numbered output format, though there is no explicit validation or feedback loop for the verdict. | 4 / 5 |
Progressive Disclosure | Well-organized overview sections with a single clearly signaled one-level-deep reference (references/risk-checklist.md, which exists) for deeper questions, splitting content appropriately. | 5 / 5 |
Total | 18 / 20 Passed |