Pufferlib
k-dense-ai/scientific-agent-skillsReinforcement learning trains agents to make decisions through trial and error. PufferLib makes this training much faster. It can simulate millions of steps every second. That means experiments finish in minutes instead of hours.
The library works with many game environments like Atari and NetHack. It also supports multi-agent systems where multiple agents interact. Users can create custom environments with the included tools.
PufferLib achieves 2 to 10 times speedups over standard methods. It is designed for developers and researchers who need high performance. The library is open source and uses the MIT license.
Add Pufferlib skill to your workflow
Global
mkdir -p ~/.claude/skills/pufferlibProject
mkdir -p .claude/skills/pufferlibSource Repository
More AI & Agent Building Claude Code Skills
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly