Publisher: Jesse Vincent / Prime Radiant · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Prepare an isolated checkout for a synthetic feature while preserving an uncommitted change in the original repository.
What input and output should you expect?
Input: A repository, desired starting revision, branch policy and the location of existing uncommitted changes. Keep a separate record of the original file content.
Output: An identified working directory and branch state, plus setup and baseline-check results. Existing work should remain intact in its original checkout.
What does it need to run?
Git and a coding agent with filesystem and command access. Native worktree tools depend on the host. Project setup may require language runtimes and dependency downloads.
Publisher README documents Claude Code, Codex and Cursor installation paths, among other harnesses. Tool availability and behavior depend on the host; this is publisher-declared support, not a cross-platform test result.
How should you approach installation?
- Review the pinned folder and its referenced files before enabling the workflow. The folder belongs to the broader Superpowers plugin, not an independently verified standalone installer.
- Follow the publisher README for your chosen coding-agent platform. The publisher documents several harnesses; use the instructions for your installed version and review plugin hooks and permissions.
- Try the suggested task in a disposable repository with synthetic inputs. Check the acceptance list before applying the workflow to shared work.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Can create directories and Git branches, inspect ignore rules, and run setup or test commands. Dependency setup can use the network and execute package lifecycle scripts; review it before enabling the workflow.
What does the skill cost?
No separate skill purchase is specified in the MIT-licensed source. Coding-agent subscriptions, model tokens, test compute and any external services have their own charges. Review or repeated execution can increase model usage.
What are its limits and alternatives?
A worktree separates files and branch state but is not a security sandbox. External services, credentials and some resources may still be shared. The source distinguishes linked worktrees from submodules; incorrect classification can create redundant or misplaced checkouts.
Use the current checkout for a small isolated edit when no competing work exists. Use a separate container when the requirement is execution security rather than branch isolation.
What could you ask in a small trial?
Try this with a small sample:
Prepare an isolated workspace from the agreed revision in this disposable repository. Detect whether isolation already exists, preserve the original dirty file and report the actual branch and baseline checks.
How would you verify the result?
- The original uncommitted file remains unchanged.
- The reported path and branch match Git state, including detached HEAD when applicable.
- The workflow does not create a second worktree when already in a suitable linked checkout.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
MIT — repository LICENSE at the reviewed commit. Dependencies and external services retain their own terms. License evidence
Version details and review scope
Source: obra/superpowers/skills/using-git-worktrees
Reviewed commit: 2ce8aa15d05bd57213e6f746f953aafb7ded7a8b
SKILL.md SHA-256: 8cfb86f121269e8f7f12361e6795c4f6738828340e28964c9229d365666c9edd
Source-document review. This profile covers the source workflow, stated dependencies and license evidence. See our editorial methodology for how we distinguish source reviews and hands-on evaluations.