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-organized command reference that assumes Claude's intelligence and provides copy-paste-ready gh commands. Its main weakness is the lack of validation checkpoints around destructive operations like merging and closing.
Suggestions
Add an explicit validation step before destructive commands (e.g., 'gh pr checks <PR> --required' before 'gh pr merge') so merges and closes are gated on CI/mergeability status.
Frame the PR and issue sections as short numbered workflows (check -> view -> act -> verify) rather than a flat command list to surface sequencing and checkpoints.
Consider moving the complex jq Templates into a references file and keeping only the canonical pattern inline, to tighten the main body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a lean command reference that assumes Claude's competence without explaining basic concepts, though the 'When to Use/When NOT to Use' sections partly restate the frontmatter description. | 4 / 5 |
Actionability | Commands throughout are fully executable with real flags and copy-paste-ready examples covering PRs, issues, CI runs, and API queries for the common cases. | 5 / 5 |
Workflow Clarity | Commands are organized by category but presented as a flat reference; destructive operations like 'gh pr merge', 'gh issue close', and 'gh run rerun' appear without validation checkpoints, capping workflow clarity at 3. | 3 / 5 |
Progressive Disclosure | The single self-contained SKILL.md is well-organized into clearly headed sections with no nested references; at over 50 lines it stays appropriately in one file but could split the complex jq templates into a reference. | 4 / 5 |
Total | 16 / 20 Passed |