Skip to content

ASE Skill (Jinzhe Zeng Group)

qqgu

An ASE routing Skill in the computational-chemistry-agent-skills collection that separates workflow preparation from calculator configuration and delegates execution elsewhere.

Catalog updated ·

Website ↗GitHub / Repository ↗Documentation ↗
Follow

Public link：https://chemaiatlas.com/skills/ase-skill-jinzhezenggroup/

Claim this resource

Overview

ASE Skill (Jinzhe Zeng Group) is an instruction-based entry point for ASE-related task preparation within the computational-chemistry-agent-skills collection. Its role is to classify a request and delegate it to a workflow or calculator branch, rather than perform atomistic calculations itself. The named Skill describes routes for static calculations, relaxation, molecular dynamics and NEB workflows, with GPAW and MACE identified as optional backend adapters.

The router takes a user's task intent and gathers the minimum context needed for the appropriate branch. Workflow requests go to ase/ase-workflows; backend selection or configuration requests go to ase/ase-calculators. When a request combines both concerns, it starts with the workflow branch and treats calculator configuration as a dependency. Its specified output is a selected branch path, an explanation of that choice, any missing minimum inputs and an explicit next delegation step.

This separation keeps workflow decisions distinct from calculator-specific setup. The top-level instructions prohibit directly embedding task-specific or backend-specific parameters and prohibit executing calculations. Python and ASE are stated requirements, with GPAW or MACE needed only for the corresponding adapter. Task preparation is the stated scope; execution, when requested, is delegated through dpdisp-submit. The supplied excerpt documents the routing contract, but does not establish the detailed behavior of the downstream branches or demonstrate scientific validation.

Key Features

  • Routes static, relaxation, molecular dynamics and NEB task intents to `ase/ase-workflows`.
  • Routes backend selection and calculator configuration requests to `ase/ase-calculators`, with GPAW and MACE named as optional adapters.
  • Handles mixed workflow/backend requests by selecting the workflow branch first and delegating calculator setup as a dependency.
  • Requires a structured routing response containing the branch path, selection rationale, missing minimum inputs and next delegation step.
  • Separates task/configuration preparation from execution, directing requested submission and running to `dpdisp-submit`.

Use Cases

  • Intended evaluation: check whether an assistant routes static, relaxation, molecular dynamics and NEB preparation requests to the documented workflow branch.
  • Intended evaluation: assess whether GPAW or MACE configuration questions are delegated to the calculator branch without introducing backend parameters at the top level.
  • Intended evaluation: use a combined workflow/backend request to inspect delegation order, identification of missing inputs and separation of preparation from execution.

How to Use

  1. Read the named Skill as routing instructions, not as an executable agent or an ASE installation guide.
  2. Describe the intended task: static calculation, relaxation, molecular dynamics, NEB, backend selection or a combination. Provide available context and let the router identify missing minimum inputs rather than assume task parameters.
  3. Check the selected branch. Workflow intent should lead to ase/ase-workflows; backend setup should lead to ase/ase-calculators. A mixed request should begin with the workflow branch.
  4. Inspect the response for all four required elements: branch path, selection rationale, missing inputs and the next delegation step. Evaluate routing behavior separately from any later scientific calculation.
  5. Consult the collection repository for the delegated instructions. Confirm the stated Python/ASE requirements and relevant optional backend dependencies. Keep execution outside this router; the Skill identifies dpdisp-submit for requested submission and running.

Related resources

Allegro

Model

Allegro implements an E(3)-equivariant interatomic potential as a NequIP extension, with documented GPU acceleration options and a separate plugin for LAMMPS simulations.

Open sourcePython

Computational Chemistry · Materials Discovery

Updated

ChemAgent (AI4Chem)

Agent

ChemAgent (AI4Chem) is a research framework for chemistry and materials tool use, linked to the CheMatAgent paper on tree-search planning, tool execution and ChemToolBench-based training.

Computational Chemistry · Materials Discovery

Updated

ChemGraph

Agent

ChemGraph is a Python agent framework that connects natural-language chemistry requests to molecular construction, simulations, analysis, and reporting, with CLI, Python, Streamlit, and MCP interfaces.

Open sourcePython

Computational Chemistry · Materials Discovery

Updated

CHGNet

Model

CHGNet is a pretrained, charge-informed neural network potential for crystal structures, predicting energies, forces, stresses and magnetic moments for relaxation and molecular dynamics workflows.

Open sourcePython

Computational Chemistry · Materials Discovery

Updated

DeePMD-kit

Model

DeePMD-kit is a toolkit for training and fine-tuning Deep Potential interatomic models from quantum-mechanical reference data, then exporting them for inference and molecular dynamics.

Open sourcePythonC++

Computational Chemistry · Materials Discovery

Updated

DP-GEN

Open Source

DP-GEN is a Python concurrent-learning platform that coordinates molecular simulation, first-principles calculations and DeePMD-kit workflows to generate interatomic potential models.

Open sourcePython

Computational Chemistry · Materials Discovery

Updated

Related guides

Workflows

AI for Materials Science: Tools, Agents and Skills

A practical guide to materials databases, research agents and scientific Skills: how to organize crystal screening, computation and analysis while keeping convex-hull, equilibrium, phonon and experimental-stability claims distinct.

· 9 min read
Skills

AI Skills for Chemistry: What They Are and How They Work

Understand chemistry AI Skills as reusable procedure modules: what SKILL.md contains, how hosts load instructions, how Skills differ from MCP and agents, and how to select, combine, and evaluate them without confusing guidance with scientific validation.

· 9 min read
Overview

How to Build a Chemistry AI Agent Stack

Design a chemistry AI agent stack by separating language models, orchestration, Skills, MCP interfaces, APIs, libraries and data. Follow proposed molecular and materials workflows, define input/output contracts, and plan permissions, evaluation and reproducible deployment.

· 9 min read