sno-ai/sno-station-skills

253 stars · Last commit 2026-10-08

Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Cross-vendor peer review, automatic handoff when an agent hits its quota, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup.

README preview

# Sno Station Skills 🧊 — The working habits of a real team, installed into your AI agents.

![Sno Station — Agents, assemble. Two heads are better than one, and smarter by morning.](https://raw.githubusercontent.com/sno-ai/sno-station/main/docs/images/hero-banner.png)

[![license Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-97ca00.svg?labelColor=3b3b3b)](LICENSE)
![31 skills in 22 units](https://img.shields.io/badge/skills-31%20in%2022%20units-2dd4bf.svg?labelColor=3b3b3b)
![self-tested before every release](https://img.shields.io/badge/every%20release-self--tested-3b82f6.svg?labelColor=3b3b3b)
![agents Claude Code, Codex](https://img.shields.io/badge/agents-Claude%20Code%20%C2%B7%20Codex-f0a04b.svg?labelColor=3b3b3b)

One AI agent is a brilliant new hire with no colleagues. It reviews its own work, so it misses
what it cannot see. It stops dead when its quota runs out, at 3 a.m., halfway through your
build. It says "done" when the tests are green and nothing actually happened. It builds three
layers of machinery you never asked for. And tomorrow it makes the same mistake it made today,
because nobody told it otherwise.

**Sno Station Skills fixes the team, not the model.** These are the skills
[Sno Station](https://github.com/sno-ai/sno-station) installs into the agents you already
run. They give Claude Code and Codex the habits every good engineering team has: a second pair
of eyes from a different vendor, a clean handover when someone has to leave, a lead who hands
out work with a written definition of done, a one-page brief when you come back, and a

View full repository on GitHub →