brainstorming
MUST USE when the user wants new features, behavior changes, refactoring with new capabilities, or architecture decisions and no…
MUST USE when implementation is verified and you need to choose the branch outcome: merge, PR, keep, or discard. Triggers on: "merge this", "create a PR", "squash and merge", "we're done with this branch", "clean up the branch", "push this", "get it merged", after
$ npx -y skills add REPOZY/superpowers-optimized --skill finishing-a-development-branch --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/finishing-a-development-branchContext preview
The summary Claude sees to decide when to auto-load this skill.
MUST USE when implementation is verified and you need to choose the branch outcome: merge, PR, keep, or discard. Triggers on: "merge this", "create a PR", "squash and merge", "we're done with this branch", "clean up the branch", "push this", "get it merged", after
name: finishing-a-development-branch description: > MUST USE when implementation is verified and you need to choose the branch outcome: merge, PR, keep, or discard. Triggers on: "merge this", "create a PR", "squash and merge", "we're done with this branch", "clean up the branch", "push this", "get it merged", after verification-before-completion passes. Routed by using-superpowers or executing-plans at completion.
Close development work with explicit integration choice.
Run full project verification before offering options.
If verification fails, stop and return to implementation.
Detect merge base (`main`/`master` or repo default) and confirm if unclear.
1. Merge back to `<base-branch>` locally 2. Push branch and open PR 3. Keep branch/worktree as-is 4. Discard branch/worktree
If `session-log.md` has `[saved]` entries written during this branch's lifetime, extract the Decisions and Rejected bullets from the most recent entry and include them here. This ensures PR reviewers see the "why" without needing to read the log.
Include:
The production-grade fork of obra/superpowers — same trusted workflow, dramatically leaner, safer, and more intelligent.
MUST USE when the user wants new features, behavior changes, refactoring with new capabilities, or architecture decisions and no…
Creates minimal, high-signal CLAUDE.md and AGENTS.md context files based on empirical best practices. Invoke on /init command,…
Use in long or noisy sessions to persist durable state across session boundaries via state.md. Also generates project-map.md when…
Use BEFORE brainstorming when facing a complex architectural, technology, or design decision where the options are not yet…
MUST USE when updating, migrating, or auditing project dependencies: upgrading packages, fixing security vulnerabilities (CVEs),…
Use when 2+ tasks are independent and can run concurrently without file or state conflicts or sequential dependencies. Triggers…