agentsclimarketplace

Git workflow skill

Skill Mickos79/aria-skills/git-workflow-skill

Production AI agent skills for OpenClaw — extracted from a real personal AI OS. RAG memory, safety guards, cost tracking, architect agent and more.

Install
npx -y skills add Mickos79/aria-skills --skill git-workflow-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.1 KB, 270 tokens by cl100k_base, as published. Nobody here has run it

Git Workflow Skill — AI Agent Branching Rules

Safe git branching strategy when multiple AI agents (Cursor, ARIA, etc.) work on the same repo.

The problem

Multiple AI agents pushing to main = merge conflicts and lost work.

Solution: Branch by agent

main        ← production, only ARIA merges here
cursor      ← Cursor AI writes here
feature/*   ← other agents/humans

Rules for Cursor (coding agent)

  • ALWAYS commit and push to branch cursor
  • NEVER push directly to main
  • Command: git push origin cursor

Rules for ARIA (orchestrator)

  • Reviews changes: git diff cursor main
  • Merges only when safe: git merge cursor --no-ff
  • Pushes to main: git push origin main

Rules for humans

  • Review ARIA's merge before it goes to main
  • Can push feature branches freely

Workflow

1. Cursor: task → commit → git push origin cursor
2. ARIA: git diff cursor main → review → merge → push main
3. No conflicts, full audit trail

Why not branch protection?

GitHub branch protection requires Pro for private repos. This workflow achieves the same result through convention.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.