Content
100%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 a tight, executable reference with clear structure, inline validation, and a verification checklist, all appropriate for a simple single-purpose skill. No bundle files are present or needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: two executable snippets plus brief, purposeful rationale and red flags; it assumes Claude's competence and avoids explaining basic git or shell concepts. | 5 / 5 |
Actionability | Both bash snippets are complete and copy-paste ready, covering the core lookup and TASK_NUM extraction from agent variables. | 5 / 5 |
Workflow Clarity | The single action is unambiguous with inline validation (skip cleanly when no worktree found) and an explicit Verification checklist; the simple-skill exception applies. | 5 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references, the content is organized into well-labeled sections (When to Use, Pattern, Why this works, Red Flags, Verification). | 5 / 5 |
Total | 20 / 20 Passed |