Use to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends on wp.Tape gradients, so treat any misbehavior of such a workflow as a gradient problem until proven otherwise — use this when training diverges or NaNs, won't train at all, stalls or plateaus above the expected loss, converges to a wrong or…
Install
npx skills add NVIDIA/skills --skill warp-debug-gradientsnpx skills add NVIDIA/skills --skill warp-debug-gradients -a claude-code -gnpx skills add NVIDIA/skills --skill warp-debug-gradients -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/warp-debug-gradientsgh skill install NVIDIA/skills warp-debug-gradientsgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/warp-debug-gradients ~/.claude/skills/warp-debug-gradients # Claude Code
cp -R /tmp/NVIDIA__skills/skills/warp-debug-gradients ~/.agents/skills/warp-debug-gradients # Codex, Cursor, Gemini CLI, Copilot, OpenCode