KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#developer-tools #codex #typescript #ai-agents #ai-agent #cli #claude-code #open-source #deepseek-harness #dsh-plugin #python #mcp

computational-chemistry-agent-skills

★ 128 Open GitHub ↗

Agent skills to run computational-chemistry tasks, used in OpenClaw

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Computational Chemistry Agent Skills

[![DOI:10.1021/acs.jctc.6c00622](https://img.shields.io/badge/DOI-10.1021%2Facs.jctc.6c00622-blue?style=for-the-badge&logo=arxiv&color=b31b1b)](https://doi.org/10.1021/acs.jctc.6c00622)
[![GitHub Created At](https://img.shields.io/github/created-at/jinzhezenggroup/computational-chemistry-agent-skills?style=for-the-badge&logo=github)](https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/commit/138d93e41935fb954857c29eafad4999144d6e26)
[![GitHub contributors](https://img.shields.io/github/contributors/jinzhezenggroup/computational-chemistry-agent-skills?style=for-the-badge&logo=github)](https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/graphs/contributors)

[![Skills](https://img.shields.io/badge/skills-34-blue?style=for-the-badge)](https://raw.githubusercontent.com/jinzhezenggroup/computational-chemistry-agent-skills/master/)

This repository hosts [Agent Skills](https://agentskills.io/home) to run computational-chemistry tasks.
These skills can be installed and used in [OpenClaw](https://github.com/openclaw/openclaw), enabling OpenClaw to run complex computational-chemistry workflows.

A website, [https://skills.jinzhezeng.group](https://skills.jinzhezeng.group), is hosted to view all skills.

## Citation

If you use this repository in your research, please cite the following work:

> Mingwei Ding, Chen Huang, Yibo Hu, Yifan Li, Zitian Lu, Xingtai Yu, Duo Zhang, Wenxi Zhai, Tong Zhu, Qiangqiang Gu, Jinzhe Zeng, Automating Computational Chemistry Workflows via OpenClaw and Domain-Specific Skills, *J. Chem, Theory Comput.,*, 2026, DOI: [10.1021/acs.jctc.6c00622](https://doi.org/10.1021/acs.jctc.6c00622). [![Citations](https://citations.njzjz.win/10.1021/acs.jctc.6c00622)](https://badge.dimensions.ai/details/doi/10.1021/acs.jctc.6c00622)

```bibtex
@Article{Ding_JChemTheoryComput_2026,
    author =   {Mingwei Ding and Chen Huang and Yibo Hu and Yifan Li and Zitian Lu and
             Xingtai Yu and Duo Zhang and Wenxi Zhai and Tong Zhu and Qiangqiang Gu
             and Jinzhe Zeng},
    title =    {{Automating Computational Chemistry Workflows via OpenClaw and Domain-
             Specific Skills}},
    journal =  {J. Chem. Theory Comput.},
    year =     2026,
    pages =    {acs.jctc.6c00622},
    doi =      {10.1021/acs.jctc.6c00622},
}
```

## Install the skills

Copy/paste this message to your OpenClaw agent.

```md
Please install ALL visible skills from computational-chemistry-agent-skills on the OpenClaw host.

Steps
1) Download repository ZIP: https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/archive/refs/heads/master.zip
2) Unzip it to get: computational-chemistry-agent-skills-master/
3) From your OpenClaw workspace root, for each top-level skill matching `*/*/SKILL.md`, run:
   npx -y skills add <that-skill-folder> -a openclaw -y
   (Without `-g`, this installs into the current workspace's `./skills/` directory.)
4) Start a NEW OpenClaw session so skills reload

Verify
openclaw skills list --eligible
```

## Skills Summary

| Skill | Description | Version | Compatibility |
|---|---|---|---|
| [agent-taskboard-manifest](agent-workflow/agent-taskboard-manifest/SKILL.md) | It is a specification for semantic workflows used by agents to plan, generate, formalize, summarize, and execute complex tasks, projects, experiments,and research efforts for agents, requiring explicit structure, lazy loading,scoped context, evidence-grounded routing, and human review at critical checkpoints. USE WHEN the user asks for a complex task, project, experiment, or research effort that needs to be carefully planned before execution USE WHEN the user provides a text-based plan and wants it to be made more detailed and formalized according to this specification. USE WHEN the user asks to summarize ongoing or completed work into a reusable workflow manifest. USE WHEN the user specifies the location of an existing agent workflow and wants it loaded and executed according to the specification. | 0.1.0 | - |
| [phonopy](analysis/phonopy/SKILL.md) | General phonon-workflow skill built around phonopy, independent of force backend. USE WHEN you need to prepare finite-displacement phonon calculations, build force constants, and analyze phonon properties (band structure, DOS, thermal quantities) while obtaining forces from different engines such as VASP, Quantum ESPRESSO, or ML force fields. | 0.1.0 | Requires phonopy and a force provider workflow (e.g., VASP/QE/MLFF) that can return forces for displaced supercells. |
| [reacnetgenerator](analysis/reacnetgenerator/SKILL.md) | Run ReacNetGenerator on reactive MD trajectories to generate reaction networks and reports. Use when the user wants to analyze LAMMPS dump/xyz/bond trajectories with ReacNetGenerator. Handles LAMMPS dump quirks like x/y/z vs xs/ys/zs by converting to x/y/z (orthorhombic + triclinic supported via reacnet-md-tools). Can infer atomname order from a LAMMPS data file. Runs via local reacnetgenerator if available or via `uvx --from reacnetgenerator ...`. Writes outputs into `out/<input_basename>/` with logs and a summary. | 2.3 | Requires `uv` and `python3`. Usually requires internet access for `uvx --from ...` resolution unless packages are already cached. |
| [ase](atomistic-workflows/ase/SKILL.md) | Unified ASE router skill with a tree of subskills for static/relax/MD/NEB workflows and backend adapters (GPAW, MACE). Use when you need backend-agnostic workflow orchestration while keeping calculator-specific setup isolated in adapter subskills, with reproducible task preparation as output. | 0.1.0 | Requires Python and ASE. Optional backend dependencies are GPAW and/or MACE depending on selected adapter. Prepares tasks/configuration only; submit and run via dpdisp-submit when execution is requested. |
| [dpdata-cli](data-processing/dpdata-cli/SKILL.md) | A command-line utility for converting and manipulating over 50 atomic simulation data formats, including outputs from DFT and MD software (VASP, LAMMPS, Gaussian, QE, CP2K, ABACUS, etc.). USE WHEN you need to convert structural or trajectory files between different computational chemistry formats, or when parsing raw simulation outputs into structured training datasets (e.g., deepmd/raw, deepmd/npy, deepmd/hdf5) for DeePMD-kit. | 1.0 | Requires uvx (uv) for running dpdata |
| [openbabel](data-processing/openbabel/SKILL.md) | A versatile CLI tool for converting molecular file formats, generating 3D atomic coordinates from SMILES, rendering 2D chemical structure images, and preparing or extracting structures for computational workflows. USE WHEN you need to convert between chemical file formats (e.g., xyz, pdb, mol, smi, gjf), generate 3D structures from SMILES using `--gen3d`, render molecule images (PNG/SVG), or extract geometries from simulation logs to build new inputs. | 1.1 | Requires uv and internet access (uses `uvx --from openbabel obabel ...`). |
| [packmol-generate-mixture](data-processing/packmol-generate-mixture/SKILL.md) | A tool for generating initial packed molecular configurations (XYZ format) from single-molecule structures by calculating box dimensions, writing input scripts, and executing Packmol. USE WHEN you need to randomly pack a specific number of molecules into a simulation box (defined by target density or fixed lengths) to create starting geometries for molecular dynamics or related computational chemistry workflows. | 1.0 | Requires uv and internet access (uses `uvx packmol ...`). |
| [pymatgen-structure](data-processing/pymatgen-structure/SKILL.md) | Structure manipulation and crystal analysis workflows based on pymatgen. USE WHEN you need to read/write common atomistic formats (CIF, POSCAR, XYZ), build supercells, perform site substitution/doping, inspect symmetry (space group), or compute local structure descriptors for materials tasks. | 0.1.0 | Requires Python 3.10+ and pymatgen (recommended via uv). |
| [deepmd-finetune-dpa3](machine-learning-potentials/deepmd-finetune-dpa3/SKILL.md) | Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 model to a new downstream dataset. Supports fine-tuning from a self-trained DPA3 model (.pt checkpoint), from a multi-task pre-trained model, or from a built-in pretrained model downloaded via `dp pretrained download` (e.g., DPA-3.1-3M, DPA-3.2-5M, DPA-3.3-1M). Covers single-task and multi-task fine-tuning workflows. | 1.0 | Requires deepmd-kit with PyTorch backend installed. GPU strongly recommended. |
| [deepmd-python-inference](machine-learning-potentials/deepmd-python-inference/SKILL.md) | Run Python inference with DeePMD-kit models using the DeepPot API. Use when the user wants to load a trained/frozen DeePMD model (.pth or .pb) or a built-in pretrained model (e.g., DPA-3.2-5M) in Python, predict energy/force/virial for atomic configurations, evaluate descriptors, or calculate model deviation between multiple models. Also covers using `dp test` CLI for batch evaluation against labeled data. | 1.0 | Requires deepmd-kit Python package installed. PyTorch backend for .pth models, TensorFlow for .pb models. |
| [deepmd-train](machine-learning-potentials/deepmd-train/SKILL.md) | Train DeePMD-kit models with progressive disclosure. Use when the user wants to train a DeePMD-kit potential, prepare an input.json, choose between model families such as se_e2_a/DeepPot-SE and DPA3, run `dp train`, monitor learning curves, freeze checkpoints, or test trained models. Start with model selection and read only the selected model reference under `models/` when model-specific configuration is needed. | 1.1 | Requires deepmd-kit installed. The selected backend and model may require PyTorch, TensorFlow, JAX, Paddle, GPU support, or custom OP libraries. |
| [dpgen-simplify](machine-learning-potentials/dpgen-simplify/SKILL.md) | Prepare, explain, validate, and run DP-GEN simplify workflows for reducing repeated or redundant DeepMD datasets. Use when the user wants to generate or modify `param.json` and `machine.json`, run `dpgen simplify param.json machine.json`, organize repeated simplify experiments, or inspect simplify outputs. | 0.2.0 | Requires a runnable environment with Python and an activated DP-GEN runtime where `dpgen` is available in PATH for the outer simplify command. Real execution also requires DeePMD-kit and any backend-specific software required by the selected `fp_style`. For scheduler execution, each stage environment must be explicitly activated in `resources.source_list`. |
| [rdkit-conf](molecular-conformer/rdkit-conf/SKILL.md) | A standardized CLI wrapper for RDKit 3D/2D conformer generation that samples multiple conformers per molecule (ETKDGv3, default 10), optimizes each with a force field (MMFF94s/UFF), keeps the lowest-energy conformer, automatically falls back to 2D layout on total embedding failure with a printed warning, and writes results to SDF or XYZ format. USE WHEN you need to generate 3D (or 2D fallback) molecular geometries from SMILES datasets (.csv/.smi) for downstream tasks such as docking, visualization, or 3D-descriptor computation. | 1.0 | Requires uv. Dependencies (rdkit, pandas) are declared as PEP 723 inline script metadata and are installed automatically when the script is invoked with `uv run <script_path>` (do NOT use `uv run python <script_path>` -- that bypasses the inline metadata and will not install dependencies automatically). |
| [antechamber](molecular-dynamics/antechamber/SKILL.md) | A command-line tool in AmberTools for preparing small molecules or non-standard residues within GAFF/AMBER-compatible chemical space for molecular mechanics simulations, by automating atom/bond typing, charge generation or import, and force-field–compatible input generation. USE WHEN you are working in AMBER, dealing with molecules not covered by standard force fields, and already have a structure that can be processed (e.g., pdb, mol2, ac, gout). Typical use cases include parameterizing ligands or modified residues (assigning atom/bond types, generating or reading partial charges), converting structures from upstream tools into mol2/prepi formats, and preparing topology-ready inputs for downstream tools such as LEaP. DO NOT USE for standard residues, metal complexes, inorganic systems, or when no valid molecular structure is available (e.g., only SMILES). | 1.0 | Requires AmberTools installed and available in PATH |
| [lammps-deepmd](molecular-dynamics/lammps-deepmd/SKILL.md) | A tool and knowledge base for running molecular dynamics (MD) simulations in LAMMPS with the DeePMD-kit plugin. It handles input script preparation, ensemble selection (NVE/NVT/NPT), and job execution via `uv` or offline binaries. USE WHEN you need to set up, write, explain, or execute a LAMMPS molecular dynamics simulation using a DeePMD machine learning potential (e.g., `graph.pb`). | 1.0 | Requires LAMMPS with DeePMD-kit support. Online mode prefers `uvx --from lammps --with deepmd-kit[gpu,torch,lmp] lmp`; offline mode requires a user-provided LAMMPS executable or module. |
| [lammps-reaxff](molecular-dynamics/lammps-reaxff/SKILL.md) | Run reactive molecular dynamics simulations in LAMMPS with the ReaxFF potential, including preparing input scripts (pair_style reaxff + fix qeq/reaxff), mapping LAMMPS atom types to elements via pair_coeff, choosing ensembles (NVE/NVT/NPT), and adding common ReaxFF diagnostics such as species analysis. Use when the user wants LAMMPS+ReaxFF workflows or needs a working, annotated `input.lammps` template. | 1.0 | Requires a LAMMPS build with the REAXFF package enabled (pair_style reaxff and fix qeq/reaxff). Optional acceleration variants: reaxff/omp or reaxff/kk. |
| [rdkit-repr](molecular-representation/rdkit-repr/SKILL.md) | A standardized CLI wrapper for RDKit molecular featurization workflows that handles physicochemical descriptor computation (outputs .csv) and molecular fingerprint extraction (outputs .npy or .csv), with built-in SMILES validation. USE WHEN you need to compute RDKit molecular descriptors or fingerprints from SMILES datasets (.csv/.smi), or when you want to list all available descriptor names and presets. | 1.0 | Requires uv. Dependencies (rdkit, pandas, numpy) are declared as PEP 723 inline script metadata and are installed automatically when the script is invoked with `uv run <script_path>` (do NOT use `uv run python <script_path>` -- that bypasses the inline metadata and will not install dependencies automatically). |
| [unimol](molecular-representation/unimol/SKILL.md) | A standardized CLI wrapper for Uni-Mol molecular ML workflows that handles representation extraction (embeddings), model training (regression/classification), and property prediction with built-in RDKit SMILES validation. USE WHEN you need to generate molecular embeddings, train machine learning models for chemical properties, or run predictions on SMILES datasets (.csv/.smi) using the Uni-Mol framework. | 1.0 | Requires uv. Dependencies (unimol-tools, rdkit, etc.) are handled automatically via inline script metadata in unimol_helper.py. |
| [dft-abinit](quantum-chemistry/dft-abinit/SKILL.md) | Route ABINIT requests to task-specific subskills based on user intent. Use when the user asks for ABINIT workflows and you must decide between static, relaxation, molecular dynamics, or electronic-analysis preparation. This orchestration skill dispatches to the correct ABINIT subskill and enforces consistent handoff to submission skills. | 0.1.0 | Requires a runnable ABINIT environment and suitable pseudopotential data for target elements. |
| [dft-cp2k](quantum-chemistry/dft-cp2k/SKILL.md) | Route CP2K requests to task-specific subskills based on user intent. Use when the user asks for CP2K workflows and you must decide between static, relaxation, molecular dynamics, or electronic-analysis preparation. This orchestration skill dispatches to the correct CP2K subskill and enforces consistent handoff to submission skills. | 0.1.0 | Requires a runnable CP2K environment and suitable basis/pseudopotential data for target elements. |
| [dft-gpaw](quantum-chemistry/dft-gpaw/SKILL.md) | Route GPAW DFT requests to task-specific subskills based on user intent. Use when the user asks for GPAW workflows and you must decide between static SCF, relaxation, DOS, or band-structure task preparation. This orchestration skill dispatches to the correct GPAW subskill and enforces consistent handoff to submission skills. | 0.1.0 | Requires a user-provided structure and a runnable GPAW Python environment (with ASE/GPAW) in the target runtime. |
| [dft-qe](quantum-chemistry/dft-qe/SKILL.md) | Generate Quantum ESPRESSO DFT input tasks from a user-provided structure plus user-specified DFT settings. Use when the user wants to prepare QE calculations such as SCF, NSCF, relax, vc-relax, MD, bands, DOS, or phonons starting from a structure file or coordinates together with pseudopotentials, functional choice, cutoffs, k-point settings, smearing, spin/charge, and convergence parameters. This skill prepares the QE task only; use a separate submission skill such as dpdisp-submit to submit the generated task. | 1.0 | Requires a user-provided initial structure and enough DFT parameters to build a scientifically meaningful QE input. |
| [dft-siesta](quantum-chemistry/dft-siesta/SKILL.md) | Route SIESTA requests to task-specific subskills based on user intent. Use when the user asks for SIESTA workflows and you must decide between static, relaxation, molecular dynamics, or electronic-analysis preparation. This orchestration skill dispatches to the correct SIESTA subskill and enforces consistent handoff to submission skills. | 0.1.0 | Requires a runnable SIESTA environment and compatible pseudopotential/basis setup for target elements. |
| [dft-vasp](quantum-chemistry/dft-vasp/SKILL.md) | Route VASP DFT requests to task-specific subskills based on user intent. Use when the user asks for VASP workflows and you must decide between static SCF, relaxation, DOS, or band-structure task preparation. This orchestration skill does not own detailed input generation logic; it dispatches to the correct VASP subskill and enforces consistent handoff to submission skills. | 0.2.0 | Requires a user-provided structure and valid VASP pseudopotential resources/license in the target environment. |
| [dftbplus](quantum-chemistry/dftbplus/SKILL.md) | Route DFTB+ requests to task-specific subskills based on user intent. Use when the user asks for DFTB+ workflows and you must decide between static, relaxation, molecular dynamics, or electronic-structure post-ground-state preparation. This orchestration skill dispatches to the correct subskill and enforces consistent handoff to submission skills. | 0.1.0 | Requires a runnable DFTB+ environment with suitable Slater-Koster parameter sets for the target elements. |
| [gjf-flux](quantum-chemistry/gjf-flux/SKILL.md) | Assemble and extract Gaussian .gjf input file sections (directives, route, title, molecule blocks, appendices) and build single- or multi-step Link1 jobs from modular component files. USE WHEN needed for generating, refactoring, templating, or scripting Gaussian job files. | 0.1.0 | Requires `uv` installed and available in PATH. |
| [run-gauss](quantum-chemistry/run-gauss/SKILL.md) | Acts as a knowledge base providing environment checklists, directory/scratch management, and bash command templates. USE WHEN you need to guide the execution of Gaussian computational chemistry jobs (.gjf) on local or remote/HPC environments. | 0.1.0 | - |
| [xtb](quantum-chemistry/xtb/SKILL.md) | Prepare and explain xTB semiempirical quantum-chemistry workflows for single-point energy, forces, charges, dipole, geometry optimization, and molecular dynamics. Use when the user asks for xTB calculations directly, or wants to use xTB through Python/ASE/dpdata bridges while keeping xTB as the primary method rather than as an ASE-only backend. | 1.0 | Requires a runnable xTB environment. Python-based workflows can use the `xtb` package; for reproducible ad hoc runs with uv, prefer `uv run --no-project --with ase --with xtb --with typing_extensions python ...` when using the ASE bridge. |
| [xtbloom-integrate-ase-dpdata](quantum-chemistry/xtbloom-integrate-ase-dpdata/SKILL.md) | Integrate xTBloom with ASE or dpdata for molecular energy, force, charge, labeling, relaxation, optimizer, or dynamics workflows. Use when an AI coding agent needs to attach the xTBloom ASE calculator, configure dpdata's xtbloom driver or batch minimizer, preserve the adapters' eV/angstrom conventions, choose reproducible versus warm-started execution, or diagnose unsupported periodic inputs. | - | - |
| [xtbloom-run-python-inference](quantum-chemistry/xtbloom-run-python-inference/SKILL.md) | Write, review, and run high-level xTBloom Python GFN2-xTB inference with `Calculator`, `Structure`, and `BatchCalculator`, including single systems, repeated geometry updates, heterogeneous ragged batches, backend selection, units, finite-temperature meaning, and peer-local failure handling. Use for ordinary NumPy-based energy, force, and charge workflows; use a dedicated integration skill instead for Array API/DLPack/PyTorch zero-copy, ASE/dpdata, the native C API, or QM/MM coupling. | - | - |
| [dpdata-driver](tools/dpdata-driver/SKILL.md) | Use dpdata Python Driver plugins to label systems (energies/forces/virials) via System.predict(), list available drivers, and build Driver objects (ase/deepmd/gaussian/sqm/hybrid). Use when working with dpdata Python API (not CLI) and you need driver-based energy/force prediction, plugin registration keys, or examples of using dpdata with ASE calculators or DeePMD models. | 1.0 | Requires dpdata or uv for running dpdata |
| [dpdata-minimizer](tools/dpdata-minimizer/SKILL.md) | Minimize geometries with dpdata minimizer plugins via System.minimize(), including how minimizers relate to drivers (ASEMinimizer needs a dpdata Driver) and how to list supported minimizers (ase/sqm). Use when doing geometry optimization/minimization through dpdata Python API. | - | - |
| [dpdisp-submit](tools/dpdisp-submit/SKILL.md) | Run Shell commands as computational jobs, on local machines or HPC clusters, through Shell, Slurm, PBS, LSF, Bohrium, etc. USE WHEN the user needs to submit batch jobs to a cluster, run commands on a remote server, execute tasks via job schedulers (Slurm, PBS, LSF), or safely run long-term/background shell commands that require state tracking and auto-recovery. | 1.0 | Requires uv and access to the internet. |
| [search-species](tools/search-species/SKILL.md) | USE WHEN requesting core chemical structural data (SMILES, formula, mass, 2D images) via IUPAC, common, or multilingual names. You MUST actively retrieve the data using this skill; DO NOT hallucinate or generate structures yourself. DO NOT USE WHEN asking for physical properties (melting point, solubility), safety/toxicity data (MSDS), or synthesis pathways. | 0.1.0 | Requires `uv` installed. |

## License

This project is licensed under GNU [LGPLv3.0](LICENSE).

computational-chemistry-agent-skills

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README