Open a pull request from the current worktree — verify green, commit scoped, push, and write the PR from the actual diff. Trigger on "/pr", "open a PR", "make a pull request".
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add ra3orblade/swarm --skill pr --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Pr?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ra3orblade-swarm)More formats (shields.io, HTML) on the badges page.
---
name: pr
description: Open a pull request from the current worktree — verify green, commit scoped, push, and write the PR from the actual diff. Trigger on "/pr", "open a PR", "make a pull request".
---
# PR
Get finished, verified work onto a branch and into a PR. This is the last mile — if the work is a plan task, run `/chores` first (it calls this).
## Steps
1. **Confirm green** (quick if `/chores` just ran): `bun run typecheck && bun run test`.
2. **Branch** — if on `main`/detached, create `feat/<short-slug>` first. Feature work never commits to `main` directly.
3. **Commit scoped** — `git add <explicit paths>` (never `-A` in a shared checkout), one focused commit. Message: what changed + how verified; end with:
```
Co-Authored-By: Claude <noreply@anthropic.com>
```
4. **Push** — `git push -u origin <branch>` (add `--force-with-lease` only after a rebase).
5. **Open the PR** from the real diff:
```sh
gh pr create --title "<concise>" --body "<what/why + verification + test count>"
```
Body: a sentence on what it does, the key implementation notes, and the verification line (`typecheck · lint · test (N pass) · smoke · docs`). Keep one PR to a coherent batch of related tasks.
6. Print the PR URL.
Do **not** merge. Rate discipline: few, substantial PRs; push rarely and deliberately.
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', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
