Content
88%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 dense, executable procedure for a destructive operation, with strong validation gates and feedback loops that justify a high workflow-clarity score. The only soft dimension is progressive disclosure, where the skill is self-contained with no external references to structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and assumes git competence (no basics explained), with tight code blocks and decision tables; a few justifying sentences like the merge-base containment note are slightly more than minimal but earn their place, keeping it just below a 5. | 4 / 5 |
Actionability | Fully executable: a complete copy-paste audit bash script, exact per-worktree reap commands ('git worktree remove <path>; git branch -d/-D <branch>'), and concrete recovery commands ('git worktree prune', 'rm -rf <path>') cover the common cases. | 5 / 5 |
Workflow Clarity | Clear sequence (signal → audit → decide → gate → final checks) with explicit validation checkpoints and feedback loops — re-run the audit, never reap on self-report, approve-list before destructive commands — satisfying the destructive/batch validation requirement rather than hitting the cap of 3. | 5 / 5 |
Progressive Disclosure | Single self-contained file with well-organized, clearly headed sections and one-level-deep Related Skills links; no bundle files exist to reference, and the body slightly exceeds the under-50-lines simple-skill threshold, so it stops short of a 5. | 4 / 5 |
Total | 18 / 20 Passed |