finishing-a-development-branch
Structures the end of feature work: verify tests pass, then present explicit merge/PR/cleanup options instead of assuming an integration path.
Anatomy
| Parent repo | obra/superpowers |
|---|---|
| Path | skills/finishing-a-development-branch |
| Trigger conditions | "Use when implementation is complete, all tests pass, and you need to decide how to integrate" |
| Instruction format | yaml-frontmatter-md |
| Required tools | git |
| Reusability | universal |
| Complexity | low |
| Ships scripts / examples / tests / boundaries | no / yes / no / yes |
Failure modes
Depends on the agent honestly assessing that tests pass; pairs with verification-before-completion for exactly that reason.
Verdict
A small skill that closes a real governance gap: integration decisions belong to humans, and this makes the agent present them instead of taking them.
Related skills
Blocks the agent from claiming work is complete, fixed, or passing until it has run verification commands and confirmed output. Evidence…
Forces root-cause investigation before any fix: reproduce, hypothesize one cause at a time, test the hypothesis, then patch. Bans…
Frequently asked questions
What does the finishing-a-development-branch skill do?
Structures the end of feature work: verify tests pass, then present explicit merge/PR/cleanup options instead of assuming an integration path.
When does finishing-a-development-branch trigger?
Its stated trigger: "Use when implementation is complete, all tests pass, and you need to decide how to integrate". Trigger precision is a scored reliability dimension.