Skill · em Dados, IA e pesquisa

pufferlib

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this…

Procedência

Origem: davila7/claude-code-templates
Caminho: cli-tool/components/skills/scientific/pufferlib
Versão fixada: 57f899e5394bb8ca166f38eacae8f0853cbfe033
Licença: MIT
Espelhado em 25/09/2026
nenhum download no Claude Code Templates (lido em 25/09/2026)

Antes de instalar

8 arquivos · 97,2 KB · inclui 2 scripts que executam: scripts/env_template.py, scripts/train_template.py

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/skills/pufferlib/.

d=".claude/skills/pufferlib"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/pufferlib"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/environments.md" "$u/references/environments.md" \
  -o "$d/references/integration.md" "$u/references/integration.md" \
  -o "$d/references/policies.md" "$u/references/policies.md" \
  -o "$d/references/training.md" "$u/references/training.md" \
  -o "$d/references/vectorization.md" "$u/references/vectorization.md" \
  -o "$d/scripts/env_template.py" "$u/scripts/env_template.py" \
  -o "$d/scripts/train_template.py" "$u/scripts/train_template.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.claude/skills/pufferlib/.

d="$HOME/.claude/skills/pufferlib"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/pufferlib"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/environments.md" "$u/references/environments.md" \
  -o "$d/references/integration.md" "$u/references/integration.md" \
  -o "$d/references/policies.md" "$u/references/policies.md" \
  -o "$d/references/training.md" "$u/references/training.md" \
  -o "$d/references/vectorization.md" "$u/references/vectorization.md" \
  -o "$d/scripts/env_template.py" "$u/scripts/env_template.py" \
  -o "$d/scripts/train_template.py" "$u/scripts/train_template.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Codex

Neste projeto: instala em .agents/skills/pufferlib/.

d=".agents/skills/pufferlib"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/pufferlib"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/environments.md" "$u/references/environments.md" \
  -o "$d/references/integration.md" "$u/references/integration.md" \
  -o "$d/references/policies.md" "$u/references/policies.md" \
  -o "$d/references/training.md" "$u/references/training.md" \
  -o "$d/references/vectorization.md" "$u/references/vectorization.md" \
  -o "$d/scripts/env_template.py" "$u/scripts/env_template.py" \
  -o "$d/scripts/train_template.py" "$u/scripts/train_template.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.agents/skills/pufferlib/.

d="$HOME/.agents/skills/pufferlib"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/pufferlib"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/environments.md" "$u/references/environments.md" \
  -o "$d/references/integration.md" "$u/references/integration.md" \
  -o "$d/references/policies.md" "$u/references/policies.md" \
  -o "$d/references/training.md" "$u/references/training.md" \
  -o "$d/references/vectorization.md" "$u/references/vectorization.md" \
  -o "$d/scripts/env_template.py" "$u/scripts/env_template.py" \
  -o "$d/scripts/train_template.py" "$u/scripts/train_template.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Antigravity

Neste projeto: instala em .agents/skills/pufferlib/.

d=".agents/skills/pufferlib"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/pufferlib"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/environments.md" "$u/references/environments.md" \
  -o "$d/references/integration.md" "$u/references/integration.md" \
  -o "$d/references/policies.md" "$u/references/policies.md" \
  -o "$d/references/training.md" "$u/references/training.md" \
  -o "$d/references/vectorization.md" "$u/references/vectorization.md" \
  -o "$d/scripts/env_template.py" "$u/scripts/env_template.py" \
  -o "$d/scripts/train_template.py" "$u/scripts/train_template.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.gemini/antigravity-cli/skills/pufferlib/.

d="$HOME/.gemini/antigravity-cli/skills/pufferlib"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/scientific/pufferlib"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/environments.md" "$u/references/environments.md" \
  -o "$d/references/integration.md" "$u/references/integration.md" \
  -o "$d/references/policies.md" "$u/references/policies.md" \
  -o "$d/references/training.md" "$u/references/training.md" \
  -o "$d/references/vectorization.md" "$u/references/vectorization.md" \
  -o "$d/scripts/env_template.py" "$u/scripts/env_template.py" \
  -o "$d/scripts/train_template.py" "$u/scripts/train_template.py" \
  -o "$d/LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.pufferlib

Prévia do SKILL.md

---
name: pufferlib
description: This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill fo…
---

# PufferLib - High-Performance Reinforcement Learning

## Overview

PufferLib is a high-performance reinforcement learning library designed for fast parallel environment simulation and training. It achieves training at millions of steps per second through optimized vectorization, native multi-agent support, and efficient PPO implementation (PuffeRL). The library provides the Ocean suit…

## When to Use This Skill

Use this skill when:
- **Training RL agents** with PPO on any environment (single or multi-agent)
- **Creating custom environments** using the PufferEnv API
- **Optimizing performance** for parallel environment simulation (vectorization)
- **Integrating existing environments** from Gymnasium, PettingZoo, Atari, Procgen, etc.
- **Developing policies** with CNN, LSTM, or custom architectures
- **Scaling RL** to millions of steps per second for faster experimentation
- **Multi-agent RL** with native multi-agent environment support

## Core Capabilities

### 1. High-Performance Training (PuffeRL)

PuffeRL is PufferLib's optimized PPO+LSTM training algorithm achieving 1M-4M steps/second.

**Quick start training:**
```bash
# CLI training
puffer train procgen-coinrun --train.device cuda --train.learning-rate 3e-4

# Distributed training
torchrun --nproc_per_node=4 train.py
```

**Python training loop:**
```python
import pufferlib
…

Ver todo o marketplace