Content
88%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 tight, actionable skill body with an explicit workflow, output contract, and fallback. Its main weakness is progressive disclosure: the body references a script under scripts/ that is not present in the bundle, leaving a dangling reference.
Suggestions
Ship the referenced scripts/fetch_review_requests.py in a scripts/ bundle directory so the primary command resolves, or inline the equivalent gh api logic if no bundle is intended.
Trim the example JSON output and presentation table to the minimal fields needed to convey the contract.
Make the fallback section explicitly conditional on the script being unavailable, so the two paths are clearly alternatives rather than parallel guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and assumes Claude's competence — the JSON output contract, reasons legend, presentation table, and fallback all earn their place. The example output block and table could be trimmed slightly, placing it just below the maximally lean 5 anchor. | 4 / 5 |
Actionability | Provides a concrete copy-paste command with arguments, a multi-team variant, a documented output JSON schema, and a fully concrete gh api fallback path, covering the common cases. | 5 / 5 |
Workflow Clarity | A clear three-step sequence (identify team, run script, present results) with explicit edge-case handling for zero results and script failure. It is a read-only query skill, so the destructive/batch validation cap does not apply and the simple-skill exception justifies a 5. | 5 / 5 |
Progressive Disclosure | Well-organized sections with a clearly signaled, one-level-deep script reference, but the referenced scripts/fetch_review_requests.py has no corresponding scripts/ bundle directory, so the navigation reference is partially broken — a minor organization gap below the top anchor. | 4 / 5 |
Total | 18 / 20 Passed |