# ml-engineer

Guides Claude Code in building production machine learning systems. It covers training, serving pipelines, feature engineering, and monitoring.

- skill · `type=skill` · Claude Code · 82 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/ml-engineer
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/ml-engineer

## What it does

This skill focuses Claude Code on production-grade machine learning workflows. It supports deep learning stacks like PyTorch 2.x and TensorFlow, alongside tabular libraries such as LightGBM or Scikit-learn. The scope covers API serving with FastAPI or TorchServe, batch jobs, container setups, and feature stores like Feast.

During tasks, the agent clarifies operational constraints, applies validation practices, and verifies outputs. System stability takes precedence over model complexity. When detailed execution patterns are needed, the skill references `resources/implementation-playbook.md`.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --skill ai-research/ml-engineer
```

2. **Skills CLI (Vercel)**
```bash
npx skills add davila7/claude-code-templates --skill ml-engineer -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/ml-engineer/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ml-engineer/

### Codex

**Manually: put the files in place**
- File: `.agents/skills/ml-engineer/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/ml-engineer/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davila7/claude-code-templates ml-engineer
```

2. **Manually: put the files in place**
- File: `.github/skills/ml-engineer/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/ml-engineer
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ml-engineer/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/ml-engineer

## When to use it
- deploy an ML inference service with FastAPI or TorchServe
- configure distributed training pipelines using PyTorch FSDP
- set up feature management and data validation workflows
- design A/B testing and drift monitoring for production models

## Example prompts
- Build a FastAPI service to serve our PyTorch model with dynamic request batching.
- Set up a data validation pipeline using Great Expectations before running training jobs.
- Design a canary rollout strategy with automated rollback on latency spikes.

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 804 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md