Expert guidance for JAX (Just After eXecution) - high-performance numerical computing with automatic differentiation, JIT compilation, vectorization, and GPU/TPU acceleration; includes transformations (grad, jit, vmap, pmap), sharp bits, gotchas, and differences from NumPy
安装
npx skills add jkitchin/skillz --skill python-jaxnpx skills add jkitchin/skillz --skill python-jax -a claude-code -gnpx skills add jkitchin/skillz --skill python-jax -a codex -ggemini skills install https://github.com/jkitchin/skillz.git --path skills/programming/python-jaxgh skill install jkitchin/skillz python-jaxgit clone --depth 1 https://github.com/jkitchin/skillz /tmp/jkitchin__skillz
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/jkitchin__skillz/skills/programming/python-jax ~/.claude/skills/python-jax # Claude Code
cp -R /tmp/jkitchin__skillz/skills/programming/python-jax ~/.agents/skills/python-jax # Codex, Cursor, Gemini CLI, Copilot, OpenCode