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 body is highly actionable with executable commands throughout, well-organized into clear sections, and includes a verification step in its workflow; its main weaknesses are minor trimmable prose and the absence of an explicit error-recovery feedback loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is code-driven and mostly lean, but lines like "Choose the command based on which issue you are already editing" and the "Equivalent mental model" restatement could be trimmed without losing guidance. | 4 / 5 |
Actionability | Every section provides copy-paste-ready, executable `gh issue` commands (e.g., `gh issue edit 123 --parent 100`, `gh issue view <number> --json parent,subIssues,...`) covering the common create/edit/inspect cases. | 5 / 5 |
Workflow Clarity | The "Safe workflow" section gives a clear numbered sequence with a verification checkpoint (step 3), but it lacks an explicit validate→fix→retry feedback loop for the destructive remove operations. | 4 / 5 |
Progressive Disclosure | No bundle files exist and none are needed; the single-purpose skill is organized into clearly headed sections (reference format, parent/sub-issue, blocked-by/blocking, inspecting, safe workflow), satisfying the simple-skill exception for well-organized self-contained content. | 5 / 5 |
Total | 18 / 20 Passed |