Agent Skills

The ALCHEMI Toolkit ships a set of agent skills — concise instruction files that AI coding assistants (Claude, Copilot, Cursor, etc.) can load to get up to speed with the nvalchemi API without lengthy context-gathering.

Skills live in the repository under .claude/skills/.

Installing skills

Point your AI assistant at the repository and ask it to install the skills from .claude/skills/. Most assistants will auto-detect them once the repository is open.

Project-level install (recommended) — keeps the skills scoped to your nvalchemi project so they are loaded only when you work in this repository.

User-level install — if you work with nvalchemi frequently across multiple checkouts or worktrees, you can install the skills in your user configuration directory (e.g. ~/.claude/skills/) so they are always available.

Available skills

Skill	Description	Related user guide
nvalchemi-data-structures	How to use AtomicData and Batch for representing atomic systems and batching them for GPU computation.	AtomicData and Batch
nvalchemi-data-storage	How to write, read, and load atomic data using the composable Zarr-backed storage pipeline (Writer, Reader, Dataset, DataLoader).	Data Loading Pipeline
nvalchemi-model-wrapping	How to wrap an arbitrary MLIP using the BaseModelMixin interface to standardize inputs, outputs, and embeddings.	Models: Wrapping ML Interatomic Potentials
nvalchemi-dynamics-api	How to configure and run dynamics simulations, compose multi-stage pipelines (FusedStage, DistributedPipeline), use inflight batching, and manage data sinks.	Dynamics: Optimization and Molecular Dynamics
nvalchemi-dynamics-implementation	How to implement a dynamics integrator by subclassing BaseDynamics and overriding pre_update() and post_update().	Dynamics: Optimization and Molecular Dynamics
nvalchemi-dynamics-hooks	How to use and write dynamics hooks — callbacks that observe or modify batch state at specific points during each simulation step.	Hooks