Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Covers the native 5.0 build and environment API, published 3.0.0 Gymnasium/PettingZoo adaptation, and a pinned historical 4.0 profile.
安装
npx skills add K-Dense-AI/scientific-agent-skills --skill pufferlibnpx skills add K-Dense-AI/scientific-agent-skills --skill pufferlib -a claude-code -gnpx skills add K-Dense-AI/scientific-agent-skills --skill pufferlib -a codex -ggemini skills install https://github.com/K-Dense-AI/scientific-agent-skills.git --path skills/pufferlibgh skill install K-Dense-AI/scientific-agent-skills pufferlibgit clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills /tmp/K-Dense-AI__scientific-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/K-Dense-AI__scientific-agent-skills/skills/pufferlib ~/.claude/skills/pufferlib # Claude Code
cp -R /tmp/K-Dense-AI__scientific-agent-skills/skills/pufferlib ~/.agents/skills/pufferlib # Codex, Cursor, Gemini CLI, Copilot, OpenCode