Use when development work is complete and you need to prepare for merge. Guides through cleanup, testing, documentation, and creating a well-structured pull request.
Scanned 9/5/2026
Install to Claude Code
npx -y skills add peintune/runjam --skill finishing-a-development-branch --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Finishing A Development Branch?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/peintune-finishing-a-development-branch)More formats (shields.io, HTML) on the badges page.
---
name: finishing-a-development-branch
description: "Use when development work is complete and you need to prepare for merge. Guides through cleanup, testing, documentation, and creating a well-structured pull request."
---
# Finishing a Development Branch
## Checklist
1. **Clean up**: Remove debug logs, commented-out code, TODO markers
2. **Test**: Run full test suite, verify edge cases
3. **Lint**: Run linter and formatter
4. **Document**: Update README, changelog, or inline docs if needed
5. **Review diff**: Self-review the full diff before pushing
6. **Commit**: Use descriptive commit messages (what + why, not how)
7. **Push**: Push branch and create PR with clear description
## PR Description Template
```
## What
Brief description of the change
## Why
Why this change is needed
## How
High-level approach (not implementation details)
## Testing
How to verify the change works
```Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...