Push the current branch and open a GitHub PR with a structured title and body.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add black141312/ada --skill open-pr --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Open Pr?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/black141312-open-pr)More formats (shields.io, HTML) on the badges page.
---
name: open-pr
description: Push the current branch and open a GitHub PR with a structured title and body.
category: git
---
# Open a PR
Requires `gh` authenticated (`gh auth status`) and a GitHub remote.
1. **Sanity-check.** `git status` should be clean — commit first if not. Confirm you're on a feature branch, not the repo's default branch. If on the default branch, create one: `git checkout -b <type>/<short-desc>`.
2. **Push.** `git push -u origin HEAD`.
3. **Summarize the change.** `git diff <base>...HEAD --stat` and the commit log since the base branch.
4. **Open the PR.** `gh pr create` with:
- **Title** — a clear one-line summary (Conventional-Commits style is fine).
- **Body** — three sections: **Summary** (what & why), **Changes** (bullets), **Test plan** (how it was verified).
5. **Return the PR URL** from `gh`.
## Rules
- Never merge as part of this — opening the PR is the end state.
- Confirm the base branch if there's any doubt; don't target the wrong one.
- Don't force-push over a shared branch.
- Keep the body honest: if something wasn't tested, say so in the test plan.
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', ...