skill

ml-engineer — Claude Code skill: what it does, how to install

Q: How do I install ml-engineer in Claude Code?

Run `npx claude-code-templates@latest --skill ai-research/ml-engineer` in your terminal.

Q: Where does this skill store implementation playbooks?

Detailed patterns and step-by-step examples are located in `resources/implementation-playbook.md`.

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

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --skill ai-research/ml-engineer

Open on GitHub

What ml-engineer 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.

What it helps with

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 for the agent

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.

How to install ml-engineer

1claude-code-templates

npx claude-code-templates@latest --skill ai-research/ml-engineer

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill ml-engineer -a claude-code

3Manually: put the files in place

~/.claude/skills/ml-engineer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ml-engineer/

Manually: put the files in place

.agents/skills/ml-engineer/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/ml-engineer/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install davila7/claude-code-templates ml-engineer

2Manually: put the files in place

.github/skills/ml-engineer/SKILL.md

Platform CLI

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

Manually: put the files in place

.devin/skills/ml-engineer/SKILL.md

The legacy .windsurf/skills/ path still works

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ml-engineer

How do I install ml-engineer in Claude Code?

Run npx claude-code-templates@latest --skill ai-research/ml-engineer in your terminal.

What does the ml-engineer skill do?

It instructs the assistant to handle production ML tasks, including model serving, feature pipelines, distributed training, and system observability.

Where does this skill store implementation playbooks?

Detailed patterns and step-by-step examples are located in resources/implementation-playbook.md.

Similar skills

All skills for AI and ML →

skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. CX Codex +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 350,300installs

From the same set804

The whole set →

gws-drive Use this command to manage Google Drive files and shared drives through Claude Code. It helps when you want an agent to run Drive operations through the gws CLI. 84installs drizzle-orm-expert Guides schema authoring, relational queries, and migrations in Drizzle ORM. Helpful when structuring type-safe database layers in TypeScript. 83installs ship-learn-next Takes a transcript, article or tutorial and turns it into concrete steps through the Ship-Learn-Next loop: ship something, reflect, plan the next rep. 82installs git-context-controller Maintains agent memory inside a versioned .GCC/ folder. It records task milestones, isolates experimental branches, and restores historical context across development sessions. 82installs trading-risk-manager Calculates position sizes, liquidation boundaries, and portfolio drawdown metrics for retail traders and investors. 82installs personal-tool-builder Guides you through building small personal utilities and terminal scripts. Helps solve personal daily friction before attempting to create complex products. 81installs worktree-deliver Commits changes and opens a GitHub pull request directly from your Git worktree. Useful when packaging isolated work in Claude Code. 81installs worktree-check Tells you which worktree you are in, what branch is checked out, how far ahead of main you are, and what task is assigned. 81installs