# pyre-code-ml-practice

This skill walks you through hosting Pyre Code, a practice platform with 68 ML problems, and through writing your own. Handy when you want hands-on work on transformer and diffusion internals without a GPU.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 517 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/pyre-code-ml-practice/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/pyre-code-ml-practice

## What it does

Pyre Code is an ML practice platform you run on your own machine. The problem set spans 68 entries, from ReLU and softmax up to flow matching, DPO, GRPO and Mamba SSM. You write code in a browser editor and get a pass or fail back right away. Everything is graded on CPU, so no graphics card is involved.

The skill covers three install routes. The quick one runs `./setup.sh`, which builds a `.venv`, pulls in the Python dependencies and prints the command to start things. There is also a conda path pinned to Python 3.11, and a Docker path via `docker compose up --build`. Once running, the grading API answers on `http://localhost:8000` and the web app on `http://localhost:3000`. Under Docker your progress lives in a volume; `docker compose down -v` wipes it.

Adding problems is the other half. Each one is a Python module under `torch_judge/problems/` holding a description, starter code, a reference solution and the test function. The skill lays out that structure, so you can copy the shape for your own exercise. The built-in AI hint is optional and switches on through `AI_HELP_BASE_URL`, `AI_HELP_API_KEY` and `AI_HELP_MODEL` in `web/.env`; any OpenAI-compatible endpoint works. With no server-side key, a user can still paste their own in the interface.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill pyre-code-ml-practice -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill pyre-code-ml-practice -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill pyre-code-ml-practice -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills pyre-code-ml-practice
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill pyre-code-ml-practice -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/pyre-code-ml-practice
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill pyre-code-ml-practice -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/reason-machines/trending-skills/tree/HEAD/skills/pyre-code-ml-practice/SKILL.md

## When to use it
- host an ML practice platform locally
- write a new problem module for Pyre Code
- run the grading service on its own
- point the AI hint at your own endpoint
- debug a submission that keeps failing

## Example prompts
- Set up Pyre Code with Docker and tell me which ports the services use
- Add a new problem to `torch_judge/problems/` for implementing RMSNorm
- Wire the AI hint to my endpoint through `web/.env`

## 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 · 349800 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 139 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