Stats
Actions
Available In
Tags
More by william-dawson
bigdft
1·
Skills for working with the BigDFT electronic structure code - setup, input generation, output parsing, and PyBigDFT workflows.
2mo
william-dawsonQM cluster model extraction and ONIOM calculation setup from protein-ligand PDB files. Includes three skills: cluster extraction with PyMOL, ONIOM input generation for XTB/ORCA, and SLURM batch script preparation. Requires PyMOL on $PATH; XTB and ORCA optional.
Set up a two-layer ONIOM calculation using XTB or ORCA. Guides method, charge, multiplicity, and inner region decisions. Use after running the pymol skill.
Extract a QM cluster model from a protein-ligand PDB file. Guides ligand identification, residue selection, amide capping, and charge determination. Use when preparing a cluster for QM or QM/MM calculations.
Generate SLURM batch scripts for HPC job submission. Ask the user about partition, resources, and software environment one question at a time.
A Claude Code plugin for setting up QM and QM/MM calculations from protein-ligand PDB files. The protein file you are working on should be in CHARMM format (generate with CHARMM-GUI)
/plugin marketplace add william-dawson/oniom-skills
/plugin marketplace update oniom-skills
/plugin install pymol@oniom-skills
/reload-plugins
This plugin provides three skills that guide you through the full workflow from raw PDB to a running calculation on your cluster:
/pymol:pymol — Extract a QM cluster model. Normalizes CHARMM PDBs, identifies the ligand, selects residues within a cutoff, applies amide capping, handles metal coordination shells, and determines the cluster charge.
/pymol:oniom — Set up a two-layer ONIOM calculation. Three approaches: XTB built-in ONIOM, 3-point manual (three separate calculations you control), or ORCA native QM/XTB. Walks you through method, cutoff, charge, and multiplicity one question at a time.
/pymol:slurm — Generate a SLURM batch script. Asks about partition, account, CPUs, memory, wall time, and how your software is installed (module, conda, or custom path). Produces a ready-to-submit script.
The skills are conversational — they inspect your structure, ask about ambiguous chemistry (ligand charge, protonation states, metal oxidation states, open-shell character), and write scripts tailored to your specific system.
$PATHSay something like:
Using your pymol skills, prepare an oniom calculation with XTB on the pdb file in this directory
You can install these skills directly into Codex from GitHub.
For a project-local install:
mkdir -p .codex/skills
python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo william-dawson/oniom-skills \
--path skills/pymol skills/oniom skills/slurm \
--dest "$PWD/.codex/skills"
PyMOL is developed by Schrödinger, LLC. XTB is developed by the Grimme group. ORCA is developed by the Neese group. This plugin provides only the Claude Code skill layer on top of these tools.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub william-dawson/oniom-skills --plugin pymolSkills for working with the BigDFT electronic structure code - setup, input generation, output parsing, and PyBigDFT workflows.
william-dawsonChemical structure validation, QSAR-ready curation, structure filtering, dataset auditing, and cross-database integration tools for cheminformatics workflows. Bundles 8 skills that coordinate ChemAudit's REST API, MCP server, and CLI for single-molecule validation, batch processing, generative-chemistry filtering (REINVENT 4-compatible), dataset health auditing with contradictory-label detection, ChEMBL-compatible standardization with provenance, SMILES/InChI diagnostics, and lookups across PubChem, ChEMBL, COCONUT, Wikidata, and SureChEMBL.
KohulanMCP server for Slurm workload management and HPC job scheduling
iowarpAccess to the ChEMBL Database. The ChEMBL Connector gives Claude access to the ChEMBL Database, a manually curated resource of bioactive drug-like compounds with quantitative binding and functional data against biological targets.
anthropicsLife sciences computational skills for scientific AI agents — 197 skills covering genomics, proteomics, drug discovery, biostatistics, scientific computing, and scientific writing
jaechang-hitsSubmit GPU compute jobs to a Slurm cluster: sbatch script generation, GPU type selection, log management.
QuantumBFSBioinformatics skills
brunoasm