Content
53%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 well-routed orchestrator that clearly delegates per-task detail to real asset files with one-level-deep references. Its weaknesses are attitudinal padding over concrete steps and the absence of explicit validation checkpoints in the main batch workflow.
Suggestions
Add an explicit validate->fix->retry checkpoint sequence in the main body for batch review/implementation runs, rather than relying on asset files to imply it.
Trim ALL-CAPS emphasis and repeated 'ask advisor, then user' phrasing into a single concise escalation rule.
Convert attitudinal directives ('always dig deeper', 'never mechanically') into concrete, checkable actions so the guidance is executable rather than motivational.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly terse imperative bullets, but ALL-CAPS shouting, repeated 'ask advisor, then user' phrasing, and the lengthy 'Lessons learned' entries with root-cause prose could be tightened, fitting the 'mostly efficient but includes some unnecessary explanation' anchor. | 3 / 5 |
Actionability | Concrete routing rules ('MUST APPLY SKILL FILE assets/issues-review.md'), a dependency ordering, and delegation instructions are actionable, but much of the body is attitudinal ('always dig deeper', 'never mechanically') without specific executable steps, matching the 'some concrete guidance but incomplete' anchor. | 3 / 5 |
Workflow Clarity | The Routing section gives a clear priority order and delegates per-task flows to asset files, but the main body lacks explicit validate->fix->retry checkpoints; since this is a batch operation skill, the rubric caps workflow clarity at 3 when validation is missing from the main flow. | 3 / 5 |
Progressive Disclosure | The body cleanly signals one-level-deep references to real bundle files (assets/issues-review.md, issues-implementation.md, prs-review.md, discussions-review.md) with just-in-time loading guidance, matching the 'good structure; references mostly clear' anchor; the long inline 'Lessons learned' log is a minor organization gap keeping it below 5. | 4 / 5 |
Total | 13 / 20 Passed |