Content
72%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 content is a concise, actionable, well-structured single-purpose workflow with concrete gh commands and a template. Its main weakness is workflow clarity on a batch operation: it has a summary step but no per-issue validation or error-recovery feedback loop.
Suggestions
Add a validation checkpoint per issue, e.g. verify each gh issue view succeeded and the body is non-empty before writing the file, with a retry on failure.
Show the concrete mechanism for iterating issues and padding numbers to 3 digits (e.g. a shell loop or printf '%03d') to make the guidance fully copy-paste ready.
Trim the filler 'Extract all relevant metadata' line and the closing 'IMPORTANT:' reminder, which restate what the numbered steps already specify.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence, with only minor trimmable padding such as 'Extract all relevant metadata' and the closing 'IMPORTANT:' reminder line; not a 5 because those small filler phrases remain. | 4 / 5 |
Actionability | Provides copy-paste-ready gh commands (gh issue list, gh issue view --json, mkdir -p), a concrete file-naming pattern with an example, and a full markdown template; not a 5 because the iteration loop and number-padding mechanics are left implied rather than shown. | 4 / 5 |
Workflow Clarity | Steps 1-6 are clearly sequenced and include a final summary, but as a batch operation over all issues it lacks per-item validation or error-recovery checkpoints, so the batch-operation cap holds it at 3. | 3 / 5 |
Progressive Disclosure | The body is under 50 lines, single-purpose, and well-organized with numbered steps and an isolated template block, with no need for external references, satisfying the simple-skill exception for a top score. | 5 / 5 |
Total | 16 / 20 Passed |