# senior-ml-engineer

The senior-ml-engineer Claude Code skill supports production work on ML models and LLM features. Use it to plan a deployment, design a RAG pipeline, or check for model drift.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 187 installs · ★ 1183 repo stars
- Author: borghei
- License: LicenseRef-MIT-Commons-Clause · policy=link-only · description only; the file stays with the author
- Source: https://github.com/borghei/Claude-Skills/tree/HEAD/engineering/senior-ml-engineer/SKILL.md
- Updated: 2026-11-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/borghei-senior-ml-engineer

## What it does

The skill guides work on model serving, MLOps setup, LLM integration, RAG design, and drift monitoring. Before producing artifacts, the agent asks about details that could change the result, such as the serving target or data interface.

Three Python scripts are included. One creates deployment files for Docker and Kubernetes, another plans RAG components from corpus and workload details, and the third compares baseline and current CSV data to produce drift reports. They rely on Python’s standard library and run offline.

The monitoring script returns exit code 1 when the overall status reaches `--fail-on`; its default is `alert`. That makes it usable as a gate in CI or a scheduled job. Model training algorithms and hyperparameter tuning are outside the skill’s scope.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-ml-engineer -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-ml-engineer -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-ml-engineer -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install borghei/Claude-Skills engineering/senior-ml-engineer/SKILL.md
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-ml-engineer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/borghei/Claude-Skills --path engineering/senior-ml-engineer
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill senior-ml-engineer -a opencode
```

### 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/borghei/Claude-Skills/tree/HEAD/engineering/senior-ml-engineer/SKILL.md

## When to use it
- generate Kubernetes deployment files for a trained model
- plan RAG components from corpus size and query volume
- compare baseline and current CSV data for drift
- set up LLM integration with cost tracking and output validation

## Example prompts
- Plan a Kubernetes deployment for the model described in `assets/deployment_spec.json`.
- Design a RAG pipeline and write its files to `rag-plan/`.
- Compare `assets/monitoring_baseline.csv` with `assets/monitoring_current.csv` for drift.

## Similar
- [mlops-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-mlops-engineer.md) — subagent · ★ 6505 repo stars
- [ai-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-ai-engineer.md) — subagent · 7687 installs
- [ml-pipeline-workflow](https://affpapa.org/en/nevibecode/skills/ml-pipeline-workflow.md) — skill · 11122 installs
- [ml-engineer](https://affpapa.org/en/nevibecode/skills/ml-engineer.md) — skill · 82 installs
- [senior-prompt-engineer](https://affpapa.org/en/nevibecode/skills/senior-prompt-engineer.md) — skill · 970 installs
- [mle-workflow](https://affpapa.org/en/nevibecode/skills/mle-workflow.md) — skill · 6400 installs

## Other versions with the same name
- [senior-ml-engineer · alirezarezvani](https://affpapa.org/en/nevibecode/skills/senior-ml-engineer.md) — 915 installs

From the same set: [borghei/claude-skills](https://affpapa.org/en/nevibecode/by/borghei/claude-skills.md) — 120 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
