Superpowers Finishing a Development Branch

Publisher: Jesse Vincent / Prime Radiant · Editorial profile by AI Tools Ratings · Review method

What task is this skill designed for?

Finish a synthetic feature in a detached worktree and preserve it for later review without merging or deleting it.

What input and output should you expect?

Input: The feature changes, test command, known starting revision and the intended integration choice. Identify whether the workspace is host-managed.

Output: A verified handoff with branch or detached-HEAD state, test results and the selected next action. Retained work should remain discoverable.

What does it need to run?

Git and the project test environment. Creating a remote pull request additionally needs an authenticated forge integration and authorization to push.

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?

1. 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.
2. 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.
3. 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 run tests, switch branches, merge, push or clean up worktrees depending on the selected action. These operations have different consequences; the source includes explicit decision points before integration or discarding work.

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?

Passing tests do not establish that the merge target is correct. A worktree may hold uncommitted files that exist nowhere else. Cleanup ownership must be checked, particularly for host-managed or detached workspaces.

Use your existing repository release process when it already covers branch handoff and cleanup. Use Verification Before Completion when only an accurate result report is needed.

What could you ask in a small trial?

Try this with a small sample:

Finish this disposable feature by checking the suite and repository state. Keep the detached worktree intact for later review; report its path and unresolved checks. Do not merge, push or delete.

How would you verify the result?

1. The result correctly reports detached HEAD rather than inventing a branch name.
2. Uncommitted files and the worktree remain intact for the keep option.
3. Tests and integration state are reported separately; no remote change is inferred from local checks.

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: 2026-10-27

MIT — repository LICENSE at the reviewed commit. Dependencies and external services retain their own terms. License evidence

Report an error, license concern or request a new review.