numerical-optimization-formulation

What problem does it solve?

It helps you convert an optimization problem described in natural language into a correct and complete mathematical formulation across LP, MILP, and QP, including identifying what is given, what is chosen, and what must be optimized.

Core Features & Use Cases

• Problem-type identification: Determines whether the problem is LP, MILP, or QP based on objective structure and variable types (continuous vs integer/binary), including QP minimization rules.
• Formulation question checklist: Ensures required elements are clarified—decision variables, objective sense (min/max), constraint structure, variable types, and (for QP) convexity requirements.
• Structured problem-text parsing: Labels every sentence as parameter/given, constraint, decision, or objective, including handling implicit objectives and implicit constraints from committed vs optional phrasing.
• Modeling patterns guidance: Provides reusable formulation patterns for common modeling cases (piecewise-linear objectives, cutting stock, goal programming, multi-period inventory timing, blending with shared mixing, etc.) to avoid typical pitfalls.

Quick Start

Ask the skill to parse your optimization problem text and produce a labeled summary of parameters, constraints, decisions, and the objective (explicit or inferred) before writing the LP/MILP/QP formulation.