Content
93%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 well-structured, executable skill body that keeps the CLI logic in its bundled script and surfaces only usage, conventions, and gotchas. Its only gap is the absence of an explicit feedback-loop/checklist for the destructive teardown workflow, though safety rails are documented.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | A lean ~40-line body that assumes Claude's competence — it does not explain what git or worktrees are and lets every bullet/command earn its place. | 5 / 5 |
Actionability | Provides copy-paste-ready 'uv run ... worktree.py create/list/remove' commands with each subcommand's flags and behavior documented, covering the common cases. | 5 / 5 |
Workflow Clarity | Each subcommand is unambiguous and the destructive 'remove' has explicit validation ('refuses if the worktree has uncommitted changes', 'Never force without first investigating what would be lost'), but there is no explicit validate→fix→retry feedback loop or checklist framing. | 4 / 5 |
Progressive Disclosure | The body is an overview that points one level deep to the single bundle scripts/worktree.py ('run it, don't read it'), with well-organized Run it / Conventions / Gotchas / Resources sections and no inlined CLI logic. | 5 / 5 |
Total | 19 / 20 Passed |