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 review procedure with a concrete runnable script and explicit human-in-the-loop checkpoints, appropriately offloading logic to a bundled script. Minor gaps are the lack of an example summary format and any error-recovery guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~12-line body is lean and assumes Claude can analyze diffs and commit logs, with only minor redundancy between the opening sentence and the 'OBJECTIVE' line that could be trimmed. | 4 / 5 |
Actionability | It gives a concrete runnable command ('Run the `scripts/fetch-pr-info.js` script') and specific output-formatting rules (✅ for resolved, [1] reference numbers for open), but lacks an example of the summary format, leaving a minor gap. | 4 / 5 |
Workflow Clarity | The three-step procedure is clearly sequenced with explicit checkpoints ('MAKE SURE you read the entire output' and 'allow the user to guide you... DO NOT begin fixing issues automatically'), but there is no error-recovery feedback loop, fitting 'clear sequence with most checkpoints present'. | 4 / 5 |
Progressive Disclosure | The short body is well-organized under one section header and references a single real one-level bundle file (`scripts/fetch-pr-info.js`) with logic appropriately split out, matching 'clear overview with well-signaled one-level-deep references'. | 5 / 5 |
Total | 17 / 20 Passed |