メニュー
Use when the user asks to generate DFT input files (VASP, Quantum ESPRESSO, LAMMPS), optimize structures with ML potentials (MACE, CHGNet, M3GNet), compute energy, or set up any computational chemistry calculation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Create and manage computational chemistry workflows with CatGo. Supports VASP, CP2K, ORCA, MLP, LAMMPS. Build OER/HER/CO2RR workflows, geometry optimization, frequency analysis, Gibbs energy calculations.
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.
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.
Route computational chemistry requests to the correct software and task skill. Entry point for all CatGo agent interactions.
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.
Authoring conventions for CatGo md-orchestration campaigns — progressive markdown, README+INDEX pairs and keeping them current, logging interventions to LESSONS, human-readable (never-hash) names, and the progressive (top→stage→calc) plan. Use when creating/editing any campaign markdown (plan/README/INDEX/STATUS/LESSONS) so the file tree stays navigable and resumable. Pairs with catgo-campaign.
| name | computational-input |
| description | Use when the user asks to generate DFT input files (VASP, Quantum ESPRESSO, LAMMPS), optimize structures with ML potentials (MACE, CHGNet, M3GNet), compute energy, or set up any computational chemistry calculation. |
| Task | Tool |
|---|---|
| VASP input (INCAR/POSCAR/KPOINTS) | catgo_vasp_generate |
| Quantum ESPRESSO pw.x input | catgo_qe_generate |
| LAMMPS input + data file | catgo_lammps_generate |
| Multi-stage LAMMPS simulation | catgo_lammps_sequential |
| ML potential relaxation | catgo_optimize |
| Single-point energy/forces | catgo_energy |
| List available calculators | catgo_calculators |
catgo_vasp_generateopt, scf, freq, bader, dos, ddec, elfencut (default 450 eV), gga ("PE"=PBE), ispin (2=spin-polarized),
ivdw (12=D3-BJ), kspacing, fixed_indices/fixed_z_belowCommon patterns:
calculation_type="opt", isif=3 (relax cell+ions)calculation_type="opt", isif=2, fixed_z_below=Zcalculation_type="dos", dense k-meshCall catgo_vasp_calc_types to list all available types with defaults.
catgo_qe_generatescf, relax, vc-relax, nscf, bandsecutwfc (default 60 Ry), ecutrho (default 480 Ry),
kspacing, occupations, smearing ("mv"=Marzari-Vanderbilt), nspinCall catgo_qe_templates for recommended settings per calculation type.
catgo_lammps_generateminimize, nve, nvt, nptpair_style, pair_coeff, potential_file, temperature, pressurecatgo_lammps_sequential — Multi-stage MD protocol:{"stages": [
{"name": "minimize", "simulation_type": "minimize"},
{"name": "heat", "simulation_type": "nvt", "temperature": 300, "run_steps": 10000},
{"name": "equilibrate", "simulation_type": "npt", "temperature": 300, "run_steps": 50000},
{"name": "production", "simulation_type": "nvt", "temperature": 300, "run_steps": 100000}
]}
Call catgo_lammps_pair_styles for available force fields.
Call catgo_lammps_validate before generating to check configuration.
catgo_optimizeQuick relaxation using ML interatomic potentials:
mace: Best accuracy for most systemschgnet: Good for oxidesm3gnet: General purposeemt: Fast, metals only (testing)Params: fmax (default 0.05 eV/A), max_steps (200), relax_cell (True to relax lattice)
catgo_energy — Single-point energy + forces without optimization.catgo_optimize(calculator="mace", fmax=0.05) → 2. catgo_vasp_generate(calculation_type="opt")catgo_vasp_generate(calculation_type="opt", isif=2, fixed_z_below=Z, encut=520)