Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, executable skill body: copy-paste commands, safety rails on the destructive operation, and a single well-signaled reference rather than an inline wall of text.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean operational body that assumes Claude's competence; nearly every line is executable guidance or a genuinely useful convention/gotcha rather than explanation of known concepts. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready commands ('uv run .claude/skills/prp-worktree/scripts/worktree.py create <name> [--base <branch>]') with concrete flags and the printed-path cue for create. | 3 / 3 |
Workflow Clarity | Three subcommands are clearly sequenced with explicit safety/validation for the destructive 'remove' (refuses on uncommitted changes, --force discards, --delete-branch only if merged, 'Never force without first investigating what would be lost'). | 3 / 3 |
Progressive Disclosure | Well-organized overview with a single one-level-deep, clearly-signaled reference to scripts/worktree.py ('run it, don't read it; --help on any subcommand'), which exists as a real bundle file. | 3 / 3 |
Total | 12 / 12 Passed |