Development

Use when the user asks to build a heterostructure, interface, van der Waals stack, substrate-film system, or lattice-matched bilayer from two different materials.

Use when the user asks to dope a material, substitute one element for another, create alloy surfaces, or introduce heteroatoms into a structure.

Use when the user asks to create point defects such as vacancies, substitutional defects, or interstitial atoms in a crystal structure.

Use when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate model for DFT.

Use when the user asks to build, modify, or prepare atomic structures: slabs, adsorbates, supercells, doping, defects, or fetching from databases.

Generate and manage Quantum ESPRESSO (pw.x) DFT calculations. Use when the user requests QE, Quantum ESPRESSO, pw.x, or plane-wave pseudopotential calculations outside VASP.

ORCA geometry optimization. Handles method/basis selection, dispersion corrections, solvent models, and convergence settings.

ORCA NEB-TS transition state search. Requires reactant and product structures. Handles NEB parameters, image count, and CI-NEB settings.

ORCA frequency calculation. Computes vibrational frequencies, IR intensities, zero-point energy, and thermochemistry at specified temperature/pressure.

Routes ORCA calculation requests to opt, neb_ts, or freq sub-skills. Enforces ORCA-specific policies for method, basis set, charge, and multiplicity.

Run LAMMPS molecular dynamics with DeePMD-kit machine learning potentials. Use when the user wants MD simulations driven by a trained DP model.

Route LAMMPS molecular dynamics requests to force-field-specific sub-skills. Use when the user requests LAMMPS with a specific potential type (DeePMD, ReaxFF).

Generate and manage GPAW Python-based DFT calculations. Use when the user requests GPAW, Python DFT, real-space grid DFT, or LCAO-DFT with ASE integration.

Generate and manage Gaussian calculations. Use when the user requests Gaussian, G16, GJF files, or needs hybrid functionals (B3LYP), MP2, CCSD(T), or molecular quantum chemistry with Gaussian basis sets.

Generate and manage DFTB+ calculations. Use when the user requests DFTB+, tight-binding DFT, SCC-DFTB, or needs fast approximate DFT for large systems or MD.

Run DeePMD-kit inference to predict energies, forces, and stresses using a trained DP model. Also covers model evaluation and testing.

Generate initial configurations for molecular simulations using Packmol. Build liquid boxes, mixtures, solutions, and solvated systems by packing molecules into a defined region.

Convert molecular file formats using Open Babel. Handles SMILES, mol2, sdf, pdb, xyz, cif, and 100+ other formats. Also performs 3D coordinate generation and hydrogen addition.

Convert between computational chemistry data formats using dpdata. Handles VASP, QE, CP2K, Gaussian, LAMMPS, and DeePMD formats. Essential for preparing ML potential training data.

Route data processing requests to the appropriate tool. Covers format conversion (dpdata, OpenBabel), structure packing (Packmol), and data manipulation.

Run a CatGo file-first md-orchestration "campaign" — a multi-step / high-throughput computational-materials study (e.g. SAA HER screening) driven from a human-readable folder + markdown tree, not the DB workflow engine. Use when the user says "跑一个 campaign", "md 模式跑", "high-throughput screening", or wants an agent-in-the-loop study with stages/funnel/analysis/report. Requires `catgo` on PATH.

Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species (pipeline, not barrier), and resume a campaign from disk after context compaction / new session. Use when driving or resuming a campaign's job-watch loop. Pairs with catgo-campaign.

Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB). Use when the user opts out of the visual workflow engine.

Diagnose and fix the CatGo backend. Use whenever the user asks to "check the backend", "diagnose the backend", "fix the backend", "why isn't X working", reports connection problems, a blank/failing UI, "router not loaded", "deps missing", or "can't reach the server". Reads GET /api/diagnostics, explains each issue from its fix_hint, auto-applies SAFE fixes (reconnect HPC, pip install a missing dep via the terminal), confirms risky actions first, and — if diagnostics itself is unreachable — te...