Py3Dmol
Use when creating 3D molecular visualizations with py3Dmol (3Dmol.js). Covers PDB/SDF/SMILES loading, cartoon/stick/sphere styles, protein-ligand complexes, docking pose viewers, selection language, PNG/HTML export, and NGLview for MD trajectories.
Binding Kinetics
Use when analyzing or predicting drug-target binding kinetics: kon, koff, KD, residence time, SPR data fitting (Langmuir/two-state), ITC thermodynamics, tau-RAMD and funnel metadynamics for unbinding, or kinetic QSAR models.
Active Learning
Use when designing active learning or closed-loop molecular optimization (DMTA cycles). Covers query strategies (UCB/EI/BALD/QBC), batch DPP selection, docking oracles (Vina/Gnina), BEDROC/EF metrics, and Design-Make-Test-Analyze campaign management.
Torchdrug
Use when working with TorchDrug for graph-based drug discovery and molecular ML. Covers molecular property prediction, protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, and GNN architectures on chemical data.
Lit Rescue
Last-resort skill. Invoke when no obvious or coherent solution is available and hallucination risk is high. Searches peer-reviewed literature and validated sources (Perplexity, bioRxiv, PubMed) before attempting an answer. Generalist — applies to any domain.
Free Energy
Use when computing free energy differences for drug discovery. Covers FEP/TI/BAR/MBAR theory, alchemical transformations with OpenMMTools, relative binding free energy (RBFE) protocols, absolute binding free energy (ABFE), pymbar analysis, convergence diagnostics, and standard state corrections.
Mdanalysis
Use when analyzing molecular dynamics trajectories with MDAnalysis. Covers Universe/AtomGroup, RMSD/RMSF/alignment, contacts and hydrogen bonds, dihedral/secondary structure/PCA analysis, and protein-ligand binding analysis.
Mmpa
Use when performing Matched Molecular Pair Analysis (MMPA) for SAR extraction, property cliff identification, bioisostere discovery, or analogue generation. Covers MMP theory and fragmentation schemes, mmpdb 4 CLI workflow (fragment/index/loadprops/transform), RDKit programmatic MMP generation, statistical SAR delta analysis, and applying transforms to generate focused libraries.
Fbdd
Use for fragment-based drug design (FBDD): Rule of 3 filtering, ligand efficiency metrics (LE/LLE/BEI/LELP), fragment library design, fragment docking (Vina/Gnina), fragment growing/linking/merging strategies, and Abad-Zapatero efficiency plots.
Rdkit
Use when working with RDKit for cheminformatics in Python. Covers molecular I/O, property calculation, Lipinski filters, fingerprints, similarity, 3D conformer generation, reactions, fragmentation, substructure search, MCS, stereochemistry, and tautomers.
Organic Mechanisms
Use when reasoning about polar organic reaction mechanisms, arrow pushing, SN1/SN2/E1/E2, nucleophile/electrophile identification, Zaitsev/Hofmann selectivity, HSAB rules, or retrosynthesis. Applies the EASE framework step-by-step.
Docking
Use when performing protein-ligand docking, virtual screening, or structure-based drug design. Covers receptor preparation (protonation, pocket definition), AutoDock Vina/Gnina docking engines, high-throughput virtual screening pipelines, pose analysis with interaction fingerprints, and ensemble docking for protein flexibility.
Coarse Grained
Use when running coarse-grained (CG) molecular dynamics with MARTINI 3. Covers protein CG with martinize2, membrane assembly with insane.py (POPC/POPE/CHOL bilayers), GROMACS CG workflows, backmapping CG to all-atom, and CG membrane analysis.
Qm Dft
Use when working with quantum chemistry (QM) and DFT calculations. Covers DFT functional/basis set selection, ORCA input/output, xTB semi-empirical methods (GFN2, CREST), PySCF Python-native QM, and standard workflows (geometry opt, frequencies, NMR, TD-DFT, reaction barriers, RESP charges).
Nextflow
Use when writing, debugging, or optimizing Nextflow pipelines for computational chemistry, bioinformatics, or HPC workflows. Covers DSL2 syntax, process/channel/workflow composition, configuration, containers, and execution on HPC/cloud.
Pepflex
Use when working with PepFlex for in silico peptide screening and evolutionary optimization. Handles peptide population management, mutation, crossover, custom evaluation pipelines, and multi-round evolutionary simulation.
Pharmacophore
Use when working with pharmacophore modeling for drug discovery. Covers feature types (HBD/HBA/AR/HYD/POS/NEG), RDKit 2D/3D pharmacophore fingerprints and matching (Pharm2D, Pharm3D, ChemicalFeatures), structure-based pharmacophore from protein-ligand complexes, ligand-based pharmacophore from active sets, and pharmacophore-based virtual screening workflows.
Force Fields
Use when working with molecular mechanics force fields for MD simulations. Covers force field theory (AMBER/CHARMM/OPLS/SMIRNOFF), OpenMM simulation setup, OpenFF/SMIRNOFF parameterization of small molecules, GAFF2/antechamber, partial charge methods (AM1-BCC, RESP), energy decomposition, and water models.
Ase
Use when working with ASE (Atomic Simulation Environment) for atomistic simulations. Covers structure building, geometry optimization, molecular dynamics, NEB/transition states, vibrational analysis, and calculator interfaces (ORCA, xTB, GPAW, LAMMPS).
Chem Brainstorm
Use at the start of any computational chemistry task to structure thinking, map available tools, and generate concrete hypotheses. Covers molecule evaluation, hypothesis building, reaction assessment, and pipeline design. Flexible guide — adapt depth to problem complexity.
Openbabel
Use when converting molecular file formats, generating 3D coordinates, searching conformers, computing descriptors/fingerprints, or filtering chemical libraries with OpenBabel. Covers both pybel Python API and obabel command-line tool.
Synkit
Use when working with SynKit for graph-based reaction informatics: ITS/MTG graph construction, reaction canonicalization, AAM validation, DPO rule extraction and composition, chemical reaction network (CRN) analysis, subgraph matching, and synthesis planning primitives.
Deepchem
Use when working with DeepChem for molecular machine learning, drug discovery, quantum chemistry, materials science, or bioinformatics. Handles molecular datasets, featurization strategies, model training/evaluation, and predictions on chemical data.
Homology Modeling
Use when building a 3D protein structure from sequence (no experimental structure available). Covers comparative homology modeling (MODELLER), AI-based prediction (AlphaFold2/ColabFold/ESMFold), model quality assessment (DOPE, pLDDT, Ramachandran), template search (HHblits, BLAST, Biopython), and structure preparation for MD or docking.
Generative Design
Use when designing or evaluating generative models for de novo drug/molecule design. Covers molecular generation theory and evaluation (MOSES/GuacaMol), SELFIES + language models, RL-based optimization with REINVENT 4, JT-VAE and graph-based generation, and structure-based 3D generation (DiffSBDD, Pocket2Mol, DiffLinker).
Daylight Theory
Use when working with SMILES, SMARTS, SMIRKS, molecular fingerprints, or cheminformatics fundamentals. Covers the complete Daylight theory: molecular graph representation, SMILES specification, SMARTS query language, SMIRKS reaction transforms, and fingerprint-based similarity. Based on the Daylight Theory Manual.
Uncertainty Qsar
Use when building QSAR/ML models that need calibrated uncertainty estimates. Covers epistemic vs aleatoric uncertainty theory, conformal prediction with MAPIE (guaranteed coverage), Gaussian processes with Tanimoto kernel, deep uncertainty (MC dropout, deep ensembles, Laplace), and applicability domain (AD) assessment. Critical for active learning and reliable property prediction.