PINA-org/PINA

condition-setup

Set up conditions for PINA problems. Covers data types (LabelTensor, Graph, PyG Data), time series conditions, binding equations to domains, and data-driven input→target mapping.

create-problem

Entry point for creating PINA problems. Routes to sub-skills based on problem type (data-driven vs physics-driven), problem class selection, domain setup, equations, conditions, and discretisation.

create-skill

Create, modify, and improve PINA skills. Use when the user wants to create a new skill for PINA development guidance, edit an existing PINA skill, or add cross-tool compatibility (opencode, Claude Code, Codex CLI) to a skill. Covers skill directory structure,…

define-domains

Create and manipulate domains for PINA physics-driven problems. Covers domain types (Cartesian, Ellipsoid, Simplex), set operations, partial/update methods, and domain discretisation.

define-equations

Define PDEs, ODEs, boundary conditions, and custom equations for PINA physics-driven problems. Covers the equation zoo, custom equation functions, and inverse problem equation signatures.

pina-workflow

Orchestrates a complete session from problem definition through trained solver. This is the entry point for solving differential equations or physics problems with neural networks. Use when the user has a vague open-ended request like "I have a differential…

select-model

Guides users through selecting, configuring, or creating a PyTorch model for a PINA problem. Use when the user asks about models, architecture, neural network choice, or how to build/choose a model for their PINA problem. Also triggers on phrases like "what…

select-solver

Guides users through selecting the right PINA solver for their problem, or creating a custom solver when no built-in fits. Use when the user asks "what solver should I use", "how do I train this", "which solver", "choose a solver", "pick a solver", "solver…

select-trainer

Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options. Use when the user asks "how do I train", "how to train", "set up training", "trainer", "Trainer", "train my model",…

skill-sync-checker

Audits SKILL.md files in this repo's skills directory for references to functions, classes, or modules (mentioned by name in prose, e.g. `parse_invoice`) that no longer exist in the codebase because they were renamed, moved, or deleted. Proposes a targeted…