Content
81%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-structured, actionable workflow with explicit validation and error-recovery guidance for running a branch design review. It is concise and clear, with only minor redundancy and placeholder notation keeping it from the top marks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient and assumes Claude's competence without explaining known concepts, with only minor redundancy (the IMPORTANT boilerplate and the "Explicit invocation only" section partly restate trigger rules). | 4 / 5 |
Actionability | It provides concrete executable commands (roborev review, git rev-parse --verify) with worked examples, but the heredoc <branch> placeholder and bracketed [--panel ...] notation leave minor gaps in copy-paste readiness. | 4 / 5 |
Workflow Clarity | A clear 4-step sequence includes an explicit validation checkpoint (git rev-parse --verify, "Do not proceed" on failure) and error-recovery feedback loops (suggest roborev status/init/re-run); the review is read-only so the destructive/batch cap does not apply. | 5 / 5 |
Progressive Disclosure | The single-file body is well-organized with clear section headers and a See-also list, with no content that needs splitting into bundle files; it exceeds 50 lines and lacks the one-level-deep references the 5 anchor calls for. | 4 / 5 |
Total | 17 / 20 Passed |