Skip to content

agent-skills.md

Latest commit

 

History

History
92 lines (73 loc) · 4.26 KB

agent-skills.md

File metadata and controls

92 lines (73 loc) · 4.26 KB
Raw

Agent Skills

DeePMD-kit provides official Agent Skills that help AI agents run DeePMD-kit workflows in a reproducible way. These skills capture project-specific operating knowledge—such as training inputs, model selection, deployment, LAMMPS integration, and Python inference patterns—so an agent can turn a high-level request into concrete files, commands, and validation steps.

The DeePMD-kit skills were initially developed in the Computational Chemistry Agent Skills project as part of the work described below. They are now maintained directly in the DeePMD-kit repository under skills/.

List of skills

  • deepmd-train: Choose a DeePMD-kit model family, then train from scratch. The skill uses progressive disclosure: the top-level workflow handles common training steps and model selection, while model-specific configuration lives under skills/deepmd-train/models/ and is read only after a model is chosen. Current references include DPA3, DPA4/SeZM, and se_e2_a.
  • deepmd-finetune-dpa3: Fine-tune DPA3 models from self-trained checkpoints, multi-task pretrained models, or built-in models downloaded by dp pretrained download.
  • deepmd-finetune-dpa4: Fine-tune DPA4/SeZM checkpoints with the PyTorch backend using standard or LoRA fine-tuning, then validate and export to .pt2.
  • deepmd-python-inference: Run Python and CLI inference with trained or frozen DeePMD-kit models, including DPA4/SeZM .pt2 archives and energy, force, virial, descriptor, embedding, and model-deviation workflows.
  • lammps-deepmd: Prepare, explain, and run LAMMPS simulations with DeePMD-kit potentials, including DPA4/SeZM .pt2 deployment and common NVE, NVT, and NPT setups.
  • matmaster-dpa4-workflows: Run prepared DPA4 training, fine-tuning, inference, and LAMMPS cases on MatMaster/Bohrium while delegating scientific setup and acceptance to the sibling DeePMD-kit skills.

Related reference

The DeePMD-kit skills were originally developed as part of the following paper:

Install skills

If you are a user

The easiest way is to send this page to your agent and ask it to install the skills for you. Users usually do not need to perform manual installation.

If you are an agent

If you already have a DeePMD-kit checkout, run this command from the repository root:

npx -y skills add ./skills -a openclaw -y

If you do not have a checkout, the same skills can also be installed directly from GitHub:

npx -y skills add https://github.com/deepmodeling/deepmd-kit/tree/master/skills \
    -a openclaw -y

The examples above require Node.js/npm so that npx is available, and they install the skills for OpenClaw. Replace openclaw with the target agent name when installing for another agent. The GitHub command lets the skill CLI fetch the repository for you. For large repositories or slow networks, this can take longer than installing from an existing local checkout. Refresh or restart the session afterward so the installed skills are reloaded.

Minimal verification

Ask the agent to perform a small task that exercises the installed skill without launching an expensive calculation. For example:

  • “Use the deepmd-python-inference skill to write a minimal Python snippet for loading a frozen DeePMD-kit model and evaluating one frame.”
  • “Use the deepmd-train skill to choose between DPA3 and se_e2_a for a small water dataset and draft a training input, but do not start training.”
  • “Use the deepmd-finetune-dpa4 skill to inspect a DPA4 checkpoint and draft a LoRA fine-tuning input, but do not start training.”
  • “Use the lammps-deepmd skill to prepare an NVT LAMMPS input file for a DeePMD-kit model, and explain each command.”
  • “Use the matmaster-dpa4-workflows skill to prepare and validate a Bohrium job specification for an existing DPA4 case, but do not submit it.”