nvidia/skills · skills/cuopt-numerical-optimization-formulation/SKILL.md

cuopt-numerical-optimization-formulation skillA

cuopt-numerical-optimization-formulation is agent-read markdown (skill) from nvidia/skills: LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add nvidia/skills/cuopt-numerical-optimization-formulation@v26.10.00
Exact content
mdr add nvidia/skills/cuopt-numerical-optimization-formulation@sha256:349af0dc4e57a34b

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_syuhtz6ac3h74epq.svg)](https://markdownregistry.com/a/art_syuhtz6ac3h74epq)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v26.10.00 latest2026-08-07 e0cd22d 19,584 BA view · diff
v26.08.002026-06-29 e37c0a0 19,583 BA view · diff
v26.08.002026-06-24 78532c0 19,582 BA view · diff
v26.08.002026-06-22 9e9a108 19,329 BA view · diff
v26.08.002026-05-29 1ba3403 18,676 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (19584 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

nvidia/skills · 3,326 stars · license Apache-2.0 · pushed 2026-09-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_syuhtz6ac3h74epq
GET https://markdownregistry.com/api/v1/resolve?ref=nvidia/skills/cuopt-numerical-optimization-formulation
GET https://markdownregistry.com/api/v1/blob/349af0dc4e57a34b40eb27734229c3c2298ad4d9b91b5489e6191ba2b2aaa36f

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.