NVIDIA cuOpt Optimization Formulation

Skill

NVIDIA's skill for turning a word problem into a clean LP, MILP or QP: decisions, constraints and objective, before any code.

Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.

Product badge

Share this product's name and rating in your README or on your website.

Updates may be delayed by image caching.

Official skill from NVIDIA/skills, by the cuOpt team.

Explains when a problem is LP, MILP or QP
Parses problem text into parameters, decision variables, constraints and an objective
Shares common formulation patterns like scheduling and selection
Concepts only; pair it with the cuOpt API skills to actually solve

Used it? Write the first review.

Skill— Clean, reproducible notebooks for experiments and tutorials

Clean, reproducible notebooks for experiments and tutorials

Skill— NVIDIA-verified agent skills for CUDA-X, RAG, and Physical AI

NVIDIA-verified agent skills for CUDA-X, RAG, and Physical AI

Skill— 166 scientific research skills that turn any agent into a co-scientist

166 scientific research skills that turn any agent into a co-scientist

Skill— Create, edit, and analyze Excel workbooks from an agent

Create, edit, and analyze Excel workbooks from an agent

Skill— 70+ agent skills for local-first clinical NLP: de-identifying text, clinical NER, FHIR export and terminology mapping.

70+ agent skills for local-first clinical NLP: de-identifying text, clinical NER, FHIR export and terminology mapping.

Skill— NVIDIA's skill that converts one CT DICOM series into a Hounsfield-unit NIfTI volume, with affine evidence in a JSON result.

NVIDIA's skill that converts one CT DICOM series into a Hounsfield-unit NIfTI volume, with affine evidence in a JSON result.