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 an exemplary lean, single-purpose instruction skill: concrete, executable, and tightly sequenced with explicit validation checkpoints for destructive operations. It assumes Claude's competence and avoids unnecessary explanation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: five numbered steps, no padding, and no explanation of concepts Claude already knows. Every token earns its place. | 5 / 5 |
Actionability | Provides concrete, executable guidance — an exact agent-spawn task string, an explicit list of files to preserve, and a specific list of destructive actions to confirm — copy-paste ready. | 5 / 5 |
Workflow Clarity | A clear five-step sequence with explicit validation: step 4 requires separate confirmation of the merged PR, branch deletions, force deletions, remote deletions, and origin/master overwrite, and step 5 demands final-state proof before declaring the repository clean. | 5 / 5 |
Progressive Disclosure | A simple single-purpose skill under 50 lines with no external references needed; the five-step structure is well-organized and self-contained, fitting the simple-skill exception. | 5 / 5 |
Total | 20 / 20 Passed |