Content
71%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-organized instruction-only skill with a sequenced workflow and explicit verification checks. Its weakest point is actionability: the steps describe what to do but not concretely how to execute each step.
Suggestions
Flesh out the higher-level steps with concrete execution detail, e.g. for intelligence gathering list sources to check (reputation networks, local informants, former associates) and for approach give a sample opening gambit.
Add a brief feedback/recovery note in Verification for what to do when a check fails (e.g. re-approach on different terms) to close the loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and well-sectioned with no over-explanation of concepts Claude already knows; only the slightly philosophical Key Principles / Expected Outcomes framing could be trimmed. | 4 / 5 |
Actionability | Steps are concrete behavioral directives ("Approach them informally, without entourage or ceremony") but stay high-level, lacking specific execution detail or examples for how to gather intelligence or approach. | 3 / 5 |
Workflow Clarity | A clear 7-step sequence is paired with an explicit Verification section of three confirmatory checks; it lacks an explicit validate-then-fix feedback loop, so it sits just below the top anchor. | 4 / 5 |
Progressive Disclosure | Under 50 lines, single-purpose, no external references needed, and organized into clear sections (Overview, Steps, Key Principles, Expected Outcomes, Verification) — meeting the simple-skill exception for a top score. | 5 / 5 |
Total | 16 / 20 Passed |