cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
npx skills add NVIDIA/skills --skill cuopt-numerical-optimization-formulation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides an AI agent to conceptually map a problem description to an LP/MILP/QP formulation, identifying problem type (LP, MILP, QP), roles of sentences (parameter/given, constraint, decision, objective), and appropriate objective handling (explicit or implicit). It emphasizes avoiding API code and sticking to formulation concepts, with rules for dealing with ambiguity and different problem patterns.
How it works
The skill presents definitions for LP, MILP, and QP and notes how to classify sentences from user-provided problem text. It instructs to label each sentence as parameter/given, constraint, decision, or objective. It explains how to recognize implicit objectives (e.g., "determine the plan" with costs) and mandatory steps to ask clarifying questions when ambiguous. It requires resolving ambiguity by exploring plausible interpretations and reporting all outcomes when complete-path runs are requested. It provides a structured parsing workflow and a checklist to ensure every sentence is labeled and an objective is identified before formulating the math model. It covers common modeling patterns and notes specific rules for QP (minimize only) and for interpreting problem statements in terms of decisions, constraints, and parameters.
When to use it
Use when converting natural-language problem descriptions into mathematical formulations for LP, MILP, or QP without coding an API. Apply when you need a disciplined problem-classification and objective-definition process before modeling, especially if the text contains potential ambiguities or multiple plausible interpretations.
What it can touch
Not applicable here since the skill is concept-based and does not touch external tools or APIs.
Caveats
QP objectives must be minimization. If the problem presents a maximization of a quadratic term, negate and minimize as instructed. The skill emphasizes asking the user about ambiguity and reporting all plausible outcomes in complete-path scenarios.
# Numerical Optimization Formulation Concepts and workflow for going from a problem description to a clear formulation across LP, MILP, and QP. No API code here. ## What is LP / MILP / QP - **LP**: Linear objective, linear constraints, continuous variables. - **MILP**: Same as LP plus some integer or binary variables (e.g., scheduling, facility location, selection). - **QP**: Quadratic objective (
What does the cuopt-numerical-optimization-formulation skill do?
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
How do I install it?
Run `npx skills add NVIDIA/skills --skill cuopt-numerical-optimization-formulation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From NVIDIA/skills, a repository with 2,789 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.