Content
86%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 tight, well-structured instruction skill with concrete commands and thoughtful idempotency guards. The main gap is the omission of exact gh CLI flag syntax and an explicit post-change verification step.
Suggestions
Specify the full gh CLI invocation, e.g. 'gh issue edit <issue> --remove-label "status: needs triage" --add-label "status: pending-close"', so the guidance is copy-paste ready.
Add an explicit verification step after the edit, such as re-reading the issue to confirm the triage labels are gone and pending-close is present.
Show the comment-posting command explicitly (e.g. 'gh issue comment <issue> --body "..."') alongside the conditional logic for when it should be skipped.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and efficient with no padding or explanation of concepts Claude already knows; every line earns its place and it assumes Claude's competence. | 5 / 5 |
Actionability | Provides the concrete command 'gh issue edit', lists exact label names, and gives the verbatim comment, but does not spell out the full flag syntax (e.g. '--remove-label') for copy-paste execution. | 4 / 5 |
Workflow Clarity | Clear sequence (parse args, read state/labels, remove labels, conditionally add pending-close and comment) with idempotency checkpoints and an open/closed branch, but lacks an explicit post-action verification that the label changes landed. | 4 / 5 |
Progressive Disclosure | A simple skill under 50 lines with no need for external references, organized as a clear single-purpose flow with a title, intro, and listed labels; qualifies for the simple-skill exception at 5. | 5 / 5 |
Total | 18 / 20 Passed |