Content
78%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 tight, well-structured meta-skill that respects the token budget and gives a clear workflow with an exit checkpoint. Its main weakness is high-level rather than fully concrete actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient with no padding; it assumes Claude's competence and every directive earns its place. | 5 / 5 |
Actionability | Provides concrete directives (inspect context, identify verification, do not make changes, exit when decision-ready) but stays high-level without specific executable steps. | 3 / 5 |
Workflow Clarity | Sequences inspect → resolve → produce → exit with an explicit exit checkpoint; no destructive or batch operations so the validation cap does not apply. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references and a single well-organized header, qualifying for the simple-skills exception. | 5 / 5 |
Total | 17 / 20 Passed |