Content
93%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 concise, highly actionable skill body with executable commands and a clear sequenced workflow. The only minor gap is the absence of an explicit error-recovery/retry loop, which is largely appropriate for delegating to an external agent.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence, with every line earning its place; e.g. "the published exit-code contract is incomplete" conveys non-obvious guidance without padding. | 5 / 5 |
Actionability | It provides a copy-paste-ready command (`copilot -p "<prompt>" -s --output-format json --no-ask-user`) with specific flags, an availability check, and concrete JSONL parsing instructions. | 5 / 5 |
Workflow Clarity | A clear numbered sequence with checkpoints (availability check, nonzero-exit/error-event failure detection, auth handling), but no explicit validate-fix-retry loop; appropriate for a delegation skill yet a minor gap. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references, organized into clear ## Run and ## Authentication And Permissions sections, satisfying the simple-skill exception. | 5 / 5 |
Total | 19 / 20 Passed |