HomeRated skills › using-git-worktrees
B

using-git-worktrees

by obra/superpowers · view source ↗
Planning & TaskMIT1,866 tok/call
Usable — but review before you trust it
Safety grade
B
81/100 · gate: review
Token cost
1,866
around median
Efficacy
Not yet measured

What it claims to do

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

What we found · 2

What its scripts can do

mediumWrites / deletes files
mediumInstalls packages

Conflicts with · 8

brainstormingshadowwork, implementation
finishing-a-development-branchshadowimplementation, work
test-driven-developmentshadowfeature, implementation
xlsxshadowexist
using-superpowersshadowstart
verification-before-completionshadowwork
subagent-driven-developmentoverlapexecut, implementation, plan, current
executing-plansoverlapimplementation, plan

If you have both installed, they compete for the same triggers — the top cause of an agent picking the wrong skill.

Have you installed using-git-worktrees? Scan everything you run.

One command grades every skill in your Claude Code / Codex — safety, token bloat, and conflicts, 100% locally.

npx skillmoo scan

Browse all rated skills

Grade computed 2026-07-13 · rubric static-v1. Efficacy shown only when measured on a labeled model + task suite — never invented.

Show the badge

Add this independent grade to the skill's README — the badge links back to this rating and updates when we re-grade.

SkillMOO grade B

[![SkillMOO](https://skillmoo.com/badge/using-git-worktrees)](https://skillmoo.com/skill/using-git-worktrees/)

Does this rating match your experience with using-git-worktrees?
Anonymous & aggregate. We watch these as a trend and re-check flagged skills — a single click never moves a grade on its own.
Independent static analysis by SkillMOO — the Consumer Reports for agent skills. Safety, token, and conflict grades are computed, not opinions. Efficacy is only ever claimed when measured. We rate & link to the source; we do not rehost skill content.