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 exceptionally concise and well-structured with a clear sequence and an explicit merge gate checkpoint. Its main weakness is actionability: instructions name what to do but rarely how to do it concretely.
Suggestions
Add concrete commands or tool invocations for steps like running tests and validating API/contracts (e.g., the actual test command or contract-checking tool).
Specify how to 'Flag commit hygiene violations' with the concrete checks to run (e.g., lint commit messages, squash checks).
Provide a short example of an actionable 'request changes' item so the feedback branch is concrete rather than abstract.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and efficient with zero padding; it assumes Claude's competence and every line earns its place (e.g., 'Read full diff, not only summary.'). | 5 / 5 |
Actionability | Steps are concrete in intent ('Run relevant tests locally', 'Validate API/contracts and migration safety') but provide no specific commands, tools, or examples, leaving key execution details missing. | 3 / 5 |
Workflow Clarity | A clearly numbered review protocol (1-5) is followed by an explicit Merge Gate checkpoint with a feedback branch ('Otherwise request changes with actionable items'); only minor validation gaps remain. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no external references needed and no bundle files present; the content is organized into well-signaled sections (When to Use, Review Protocol, Merge Gate), meeting the simple-skill exception. | 5 / 5 |
Total | 17 / 20 Passed |