Fully autonomous SDLC pipeline — plan to PR, zero user intervention. Invoke via /auto-pr.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add bravros/bravros --skill auto-pr --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Auto Pr?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/bravros-auto-pr-bravros)More formats (shields.io, HTML) on the badges page.
---
name: auto-pr
core: true
description: Fully autonomous SDLC pipeline — plan to PR, zero user intervention. Invoke via /auto-pr.
---
# /auto-pr — plan → orchestrate → PR → review loop, autonomously
INTENT: one command, one merge-ready PR. Stages delegate to `/recon` (which reviews inline) → `/orchestrate` → `/pr` → review loop, all with `--auto`.
Read [briefing.md](references/briefing.md) on demand for detailed context and instructions.
## Key Constraints & Execution Summary
1. **Only runs when explicitly typed `/auto-pr`.**
2. **Zero user questions.** Compact and continue on context pressure.
3. **NEVER merge to main.** `/promote` with out-of-band token is the only path.
4. **Lock before Stage 1:** `bravros autopr preflight --skill auto-pr`.
5. **Review loop sentinel:** Uses `BRAVROS-VERDICT: approved` or `BRAVROS-VERDICT: changes-requested`.
6. **Worktree isolation:** Refer to [worktree-mode.md](references/worktree-mode.md).
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!
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.
