Directory / Scientific Agent Skills (K-Dense) / optimize-for-gpu

optimize-for-gpu

GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS, cuCIM, KvikIO, Warp, Newton, Numba-CUDA, or RAFT questions; and profiling, memory-transfer, kernel, or multi-GPU bottlenecks. Also use when large data-parallel Python code is slow and GPU acceleration is a plausible option, even if the user does not name CUDA.
Description from the SKILL.md front matter.

Install

GitHub CLI v2.90+ (Copilot by default)

gh skill install K-Dense-AI/scientific-agent-skills optimize-for-gpu

For Claude Code

gh skill install K-Dense-AI/scientific-agent-skills optimize-for-gpu --agent claude-code

For Codex

gh skill install K-Dense-AI/scientific-agent-skills optimize-for-gpu --agent codex

Commands follow each host's documentation (Any Agent Skills host (Claude Code, Codex, Cursor, Gemini CLI, Copilot…) docs). gh skill needs GitHub CLI 2.90 or later and is in public preview.

Listed from K-Dense Inc.'s catalog, not reviewed by us. Read the source before installing.

Catalog: Scientific Agent Skills (K-Dense)
Author: K-Dense, Inc.
Source code: K-Dense-AI/scientific-agent-skills
License: MIT
Repository stars: 52,795 for K-Dense-AI/scientific-agent-skills (the whole catalog repo)
Version: 1.6
Added to catalog: Not tracked for this source
Last change: 2026-10-19 (last push to the repo)

What it contains

Skills: 1

Similar in Science, research & learning

13c-metabolic-flux (K-Dense science skill)
adaptyv (K-Dense science skill)
aeon (K-Dense science skill)
alphagenome (K-Dense science skill)
analytical-method-validation (K-Dense science skill)
anndata (K-Dense science skill)