Prepare a branch for review by committing scoped changes, rebasing on main, running builds, and creating or updating a pull request. Use when the user wants the branch ready for PR review.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add dcouple/Pane --skill prepare-pr --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Prepare Pr?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dcouple-prepare-pr-pane)More formats (shields.io, HTML) on the badges page.
---
name: prepare-pr
description: Prepare a branch for review by committing scoped changes, rebasing on main, running builds, and creating or updating a pull request. Use when the user wants the branch ready for PR review.
---
# Prepare PR
This is a high-trust workflow. Surface any destructive or ambiguous step before proceeding.
Workflow:
1. Group current changes into logical commits, ideally by done-plan.
2. Create focused commits without staging unrelated work.
3. Fetch and rebase onto `origin/main`.
4. Resolve obvious conflicts directly. Ask the user about semantic conflicts.
5. Run the relevant build steps and fix straightforward failures.
6. Create or update the PR with a summary built from the plans and current diff.
7. Push with `--force-with-lease` only when rebase made it necessary.
Rules:
- Never use blanket staging.
- Treat secrets and credentials as stop conditions.
- Keep build-fix commits separate when they are distinct from the feature work.
- If GitHub CLI or network access is unavailable, report exactly where the flow stopped.
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', ...
