# ML engineering

> ML engineering is an open-source agent skill for developer tools. Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and be. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/stas00/ml-engineering/tree/master/skills/ml-engineering
- **Repository:** https://github.com/stas00/ml-engineering
- **GitHub stars:** 19,720
- **License:** CC-BY-SA-4.0
- **Skill name:** ml-engineering
- **Collection:** https://github.com/stas00/ml-engineering
- **Categories:** developer tools
- **Listing updated:** 2026-11-17

## About

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering
The latest SKILL.md version can be found at https://github.com/st

## When your agent uses it

> Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/st

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/stas00/ml-engineering/tree/HEAD/skills/ml-engineering)
- [License: CC-BY-SA-4.0](https://github.com/stas00/ml-engineering/tree/HEAD/skills/ml-engineering)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/ml-engineering` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/stas00/ml-engineering.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/ml-engineering &&
cp -R "$tmp/skills/ml-engineering" ~/.claude/skills/ml-engineering &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/ml-engineering` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/ml-engineering` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/stas00/ml-engineering.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/ml-engineering &&
cp -R "$tmp/skills/ml-engineering" ~/.agents/skills/ml-engineering &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/ml-engineering` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/ml-engineering` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/stas00/ml-engineering.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/ml-engineering &&
cp -R "$tmp/skills/ml-engineering" ~/.cursor/skills/ml-engineering &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/ml-engineering` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/stas00/ml-engineering.git --path skills/ml-engineering
```

Or copy the folder to `~/.gemini/skills/ml-engineering` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/ml-engineering`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/stas00/ml-engineering.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/ml-engineering &&
cp -R "$tmp/skills/ml-engineering" ~/.copilot/skills/ml-engineering &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/ml-engineering` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/stas00/ml-engineering.git
```

Then copy `ml-engineering/skills/ml-engineering` into your agent's skills folder as `ml-engineering`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install ML engineering in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/ml-engineering to use it in all your projects, or to .claude/skills/ml-engineering in one project.

### Does ML engineering run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use ML engineering?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to ML engineering?

The closest alternatives to ML engineering are Rea changelog update, Code review, Code review, Acreadiness assess and Code review.

## Alternatives

- [Rea changelog update](https://ai-powered.com/skills/rea-changelog-update): Rea changelog update is an open-source agent skill for developer tools.
- [Code review](https://ai-powered.com/skills/code-review-mattpocock): Code review is an open-source agent skill for developer tools.
- [Code review](https://ai-powered.com/skills/code-review): Code review is an open-source agent skill for developer tools.
- [Acreadiness assess](https://ai-powered.com/skills/acreadiness-assess): Acreadiness assess is an open-source agent skill for developer tools.
- [Code review](https://ai-powered.com/skills/code-review-flutter): Code review is an open-source agent skill for developer tools.

---
Source: https://ai-powered.com/skills/ml-engineering
