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.
The body is a lean, well-structured guide with executable commands, clear sequencing, and validation checkpoints for a risky merge operation. The only gaps are a few trims for conciseness and one command given as prose rather than code.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence without explaining what a PR or CI is, but a few caveat-dense sentences ('Green CI means...', 'A generic request for human review is not...') could be trimmed, placing it at anchor 4 rather than the fully lean anchor 5. | 4 / 5 |
Actionability | Provides executable commands ('gh pr view ...', 'gh api ... --paginate') plus concrete decision guidance, but inspecting failed job logs is described rather than given as a command, leaving a minor gap at anchor 4 rather than the copy-paste-ready anchor 5. | 4 / 5 |
Workflow Clarity | A clear sequenced process (monitor → fetch checks/reviews → read feedback → assess/fix → verify → final report/merge) with validation checkpoints ('recheck title, body, labels, head, and checks immediately before an authorized merge') and a CI retry/diagnose feedback loop; it is prose sections rather than an explicit numbered checklist with error-recovery, so it sits at anchor 4. | 4 / 5 |
Progressive Disclosure | Under 50 lines, single-purpose, with well-organized sections and a single one-level reference to the code-review skill; with no bundle files needed, the simple-skill exception lets a well-organized body score 5. | 5 / 5 |
Total | 17 / 20 Passed |