ampl

What problem does it solve?

This Skill prevents vague or error-prone AMPL guidance by enforcing consistent environment detection, response modes, and formulation standards while grounding answers in AMPL documentation chunks.

Core Features & Use Cases

• Conversation setup & routing: Detects Pure AMPL vs amplpy/Jupyter vs Python scripts and selects the correct code/output style.
• Response-mode control: Switches between Full Build, Debug, Explanation, Refactor, Performance, and Data modes based on user intent and whether code exists.
• Optimization-quality guardrails: Enforces native AMPL constructs (e.g., abs/min/max/PWL/logical operators) to avoid manual linearizations and weak big-M formulations.
• amplpy-safe data handling: Directs users to load data via Python/pandas (and explicitly avoids AMPL data; blocks in amplpy).
• Solver selection guidance: Recommends appropriate solvers per problem class (LP/MIP/NLP/MINLP/conic/global/VRP) with tuning and diagnosis hints.

Quick Start

Ask your question naturally, for example: "In Jupyter, help me debug an infeasible AMPL model and refactor the formulation to improve numerical stability."