finishing-a-development-branch — official finishing-a-development-branch, superpowers, official, ide skills, Claude Code, Cursor, Windsurf

Verified
v1.0.0

About this Skill

Ideal for Code Management Agents requiring streamlined development workflow integration, particularly those utilizing npm, cargo, pytest, or go test. Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

obra obra
[113.6k]
[9110]
Updated: 3/26/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reviewed Landing Page Review Score: 10/11

Killer-Skills keeps this page indexable because it adds recommendation, limitations, and review signals beyond the upstream repository text.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review Locale and body language aligned
Review Score
10/11
Quality Score
68
Canonical Locale
en
Detected Body Locale
en

Ideal for Code Management Agents requiring streamlined development workflow integration, particularly those utilizing npm, cargo, pytest, or go test. Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Core Value

Empowers agents to efficiently complete development work by verifying tests, presenting merge, PR, or cleanup options, and executing chosen workflows, leveraging protocols like npm test, cargo test, pytest, or go test to ensure seamless integration.

Ideal Agent Persona

Ideal for Code Management Agents requiring streamlined development workflow integration, particularly those utilizing npm, cargo, pytest, or go test.

Capabilities Granted for finishing-a-development-branch

Automating development branch completion
Verifying test suites for project validation
Streamlining merge, PR, or cleanup workflows

! Prerequisites & Limits

  • Requires project test suite setup
  • Limited to development branches with passing tests
  • Dependent on specific testing frameworks like npm, cargo, pytest, or go test

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Curated Collection Review

Reviewed In Curated Collections

This section shows how Killer-Skills has already collected, reviewed, and maintained this skill inside first-party curated paths. For operators and crawlers alike, this is a stronger signal than treating the upstream README as the primary story.

Reviewed Collection

Claude Code Workflow Tools to Install First

Reviewed 2026-04-17

Reviewed on 2026-04-17 for setup clarity, maintainer reliability, review coverage, and operator handoff readiness. We kept the tools that make Claude Code easier to trial and easier to standardize.

People landing here usually already know they want Claude Code. What they need next is a smaller list tied to review, guardrails, and handoff instead of another broad skills roundup.

6 entries Killer-Skills editorial review with monthly collection checks.
Reviewed Collection

Windsurf Workflow Tools to Install First

Reviewed 2026-04-17

Reviewed on 2026-04-17 for setup clarity, maintainer reliability, review support, and handoff readiness. We kept the tools that make Windsurf easier to trial, explain, and standardize.

People landing here usually already know they want Windsurf. What they need next is a smaller list tied to coding speed, review support, rules sync, and handoff instead of another broad skills roundup.

5 entries Killer-Skills editorial review with monthly collection checks.
Reviewed Collection

12 Official AI Agent Skills & Trusted Tools to Install First

Reviewed 2026-04-16

Reviewed on 2026-04-16 for first-party ownership, documentation quality, install clarity, and production relevance. This is the safest collection to use as a default starting point.

We prioritize this page because it lets users verify trust first and then move into one clear installation path instead of bouncing across more repo lists.

12 entries Maintained through Killer-Skills editorial review with trust, install-path, and operator checks.
After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is finishing-a-development-branch?

Ideal for Code Management Agents requiring streamlined development workflow integration, particularly those utilizing npm, cargo, pytest, or go test. Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

How do I install finishing-a-development-branch?

Run the command: npx killer-skills add obra/superpowers/finishing-a-development-branch. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for finishing-a-development-branch?

Key use cases include: Automating development branch completion, Verifying test suites for project validation, Streamlining merge, PR, or cleanup workflows.

Which IDEs are compatible with finishing-a-development-branch?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for finishing-a-development-branch?

Requires project test suite setup. Limited to development branches with passing tests. Dependent on specific testing frameworks like npm, cargo, pytest, or go test.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add obra/superpowers/finishing-a-development-branch. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use finishing-a-development-branch immediately in the current project.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

finishing-a-development-branch

Install finishing-a-development-branch, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command...

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Finishing a Development Branch

Overview

Guide completion of development work by presenting clear options and handling chosen workflow.

Core principle: Verify tests → Present options → Execute choice → Clean up.

Announce at start: "I'm using the finishing-a-development-branch skill to complete this work."

The Process

Step 1: Verify Tests

Before presenting options, verify tests pass:

bash
1# Run project's test suite 2npm test / cargo test / pytest / go test ./...

If tests fail:

Tests failing (<N> failures). Must fix before completing:

[Show failures]

Cannot proceed with merge/PR until tests pass.

Stop. Don't proceed to Step 2.

If tests pass: Continue to Step 2.

Step 2: Determine Base Branch

bash
1# Try common base branches 2git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null

Or ask: "This branch split from main - is that correct?"

Step 3: Present Options

Present exactly these 4 options:

Implementation complete. What would you like to do?

1. Merge back to <base-branch> locally
2. Push and create a Pull Request
3. Keep the branch as-is (I'll handle it later)
4. Discard this work

Which option?

Don't add explanation - keep options concise.

Step 4: Execute Choice

Option 1: Merge Locally

bash
1# Switch to base branch 2git checkout <base-branch> 3 4# Pull latest 5git pull 6 7# Merge feature branch 8git merge <feature-branch> 9 10# Verify tests on merged result 11<test command> 12 13# If tests pass 14git branch -d <feature-branch>

Then: Cleanup worktree (Step 5)

Option 2: Push and Create PR

bash
1# Push branch 2git push -u origin <feature-branch> 3 4# Create PR 5gh pr create --title "<title>" --body "$(cat <<'EOF' 6## Summary 7<2-3 bullets of what changed> 8 9## Test Plan 10- [ ] <verification steps> 11EOF 12)"

Then: Cleanup worktree (Step 5)

Option 3: Keep As-Is

Report: "Keeping branch <name>. Worktree preserved at <path>."

Don't cleanup worktree.

Option 4: Discard

Confirm first:

This will permanently delete:
- Branch <name>
- All commits: <commit-list>
- Worktree at <path>

Type 'discard' to confirm.

Wait for exact confirmation.

If confirmed:

bash
1git checkout <base-branch> 2git branch -D <feature-branch>

Then: Cleanup worktree (Step 5)

Step 5: Cleanup Worktree

For Options 1, 2, 4:

Check if in worktree:

bash
1git worktree list | grep $(git branch --show-current)

If yes:

bash
1git worktree remove <worktree-path>

For Option 3: Keep worktree.

Quick Reference

OptionMergePushKeep WorktreeCleanup Branch
1. Merge locally--
2. Create PR--
3. Keep as-is---
4. Discard---✓ (force)

Common Mistakes

Skipping test verification

  • Problem: Merge broken code, create failing PR
  • Fix: Always verify tests before offering options

Open-ended questions

  • Problem: "What should I do next?" → ambiguous
  • Fix: Present exactly 4 structured options

Automatic worktree cleanup

  • Problem: Remove worktree when might need it (Option 2, 3)
  • Fix: Only cleanup for Options 1 and 4

No confirmation for discard

  • Problem: Accidentally delete work
  • Fix: Require typed "discard" confirmation

Red Flags

Never:

  • Proceed with failing tests
  • Merge without verifying tests on result
  • Delete work without confirmation
  • Force-push without explicit request

Always:

  • Verify tests before offering options
  • Present exactly 4 options
  • Get typed confirmation for Option 4
  • Clean up worktree for Options 1 & 4 only

Integration

Called by:

  • subagent-driven-development (Step 7) - After all tasks complete
  • executing-plans (Step 5) - After all batches complete

Pairs with:

  • using-git-worktrees - Cleans up worktree created by that skill

Related Skills

Looking for an alternative to finishing-a-development-branch or another official skill for your workflow? Explore these related open-source skills.

View All

flags

Logo of facebook
facebook

Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.

244.2k
0
Developer

extract-errors

Logo of facebook
facebook

extract-errors is a React error handling skill that automates the process of extracting and assigning error codes, ensuring accurate and up-to-date error messages in React applications.

244.2k
0
Developer

fix

Logo of facebook
facebook

fix is a code optimization skill that automates formatting and linting using yarn prettier and linc.

244.2k
0
Developer

flow

Logo of facebook
facebook

Use when you need to run Flow type checking, or when seeing Flow type errors in React code.

244.2k
0
Developer