AI Blocks › Build and ship software
Dev container setup builder
Name your project and language. Get a ready dev container with tools and saved volumes, so setup is the same each time.
Dev container setup builder is a free AI skill for the job "Build and ship software". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · CC BY 4.0 licence · Made by sickn33 · Thinking: low
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
A .devcontainer folder that opens your project in the same clean, sandboxed workspace every time, with Claude Code and the right language tools already installed. No more "works on my machine". The skill looks at your project first. It reads package.json, pyproject.toml, Cargo.toml or go.mod to find the project name, and checks file types to detect your languages. Then it writes the configuration: a Dockerfile, the container settings, and volumes that keep your command history and tool settings between rebuilds. It is meant for development only, not for production deployment. If you already have a working dev container, it is better to edit that one by hand.
You give it
- Your project folder
- The languages or tools you use (optional)
- Anything the container must install (optional)
- Ports your app needs open (optional)
You get
- A .devcontainer folder with all config files
- A Dockerfile with your language tools
- Saved volumes for history and settings
- A short note on how to open it
Use it when
- You want a safe sandbox for running an AI coding agent on your code.
- New teammates lose a day installing tools before they can run the project.
- Your project uses more than one language and the setup is fiddly.
- You need your shell history and settings to survive when the container is rebuilt.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run code and read your project files.