Content
76%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.
A highly actionable, well-structured skill body with executable API calls and a complete output template. Its main weakness is workflow clarity on a batch operation: validation, error handling, and pagination are under-specified.
Suggestions
Add a validation/checkpoint step for the batch operation: e.g., 'Confirm the fetched PR count matches the repo's open-PR total' and retry-on-error guidance for API rate limits (429/403).
Provide an explicit pagination loop (iterate page=1,2,… until a short response) rather than only stating 'Paginate if there are more than 100'.
Collapse the duplicated curl and gh CLI blocks for each step into one primary path with the other as a short fallback to reduce token cost.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean and assumes Claude's competence with no concept over-explanation, but duplicates the same operations as both curl and gh CLI variants, adding tokens that could be trimmed. | 4 / 5 |
Actionability | Fully executable curl/jq and gh CLI commands, concrete classification rules ('first match wins'), and a copy-paste-ready markdown output template cover the common cases. | 5 / 5 |
Workflow Clarity | Six clearly sequenced steps exist, but this is a batch operation over many PRs with no validation checkpoints — no API error/rate-limit handling, no 'verify all PRs accounted for' step, and pagination is only mentioned not looped. | 3 / 5 |
Progressive Disclosure | Well-organized into clear sections with no nested references and single-purpose scope; the long inline output-format template (lines 179–235) could live in a separate reference file but is reasonable inline. | 4 / 5 |
Total | 16 / 20 Passed |