catgo-LRG

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.

Compute adsorption/reaction Gibbs free energies, free-energy diagrams, and electrochemical overpotentials (HER/ORR/OER/CO2RR/NRR) with VASP. The per-species pipeline is geo_opt → freq → Gibbs; CHE references; ΔG → η. Use whenever a study's target is a FREE energy (not raw DFT energy) — overpotential, free-energy diagram, ΔG of adsorption/reaction, limiting potential. Pairs with the catgo-campaign skill for orchestration.

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 — tells the user how to start the backend instead of pretending to fix one that is down.

Validate an HPC/cluster configuration against the live cluster BEFORE submitting a VASP workflow, or diagnose why a remote job produced no output. Reads the user's submit script / run config, then calls the validate_hpc_config tool to probe the real cluster over SSH (POTCAR directories, per-element pseudopotentials, and VASP binary resolution under the real module-load + conda environment). Use whenever the user asks to "test my cluster config", "check if VASP will run", "verify my HPC setup", or after a job silently failed for environment/path reasons.

Routes troubleshooting requests to vasp_errors, convergence_issues, or workflow_errors sub-skills based on the type of problem.

Generate ORCA input files for IRC (Intrinsic Reaction Coordinate) calculations and post-process the results. Use this skill whenever the user asks about IRC calculations, reaction path following, confirming transition state connectivity, or tracing a minimum energy path from a TS in ORCA. Also trigger when the user mentions IRC endpoints, forward/backward reaction paths, or needs to verify that a TS connects to expected reactants and products.

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.

Use when the user asks to analyze DOS, band structure, COHP bonding, d-band center, or MD trajectory properties (RDF, RMSD, RMSF, hydrogen bonds, clustering, dimensionality reduction, dihedral angles, planar density).

Use when the user asks to load, fetch, build, modify, or transform crystal/molecular structures. Covers database import, supercell, defects, doping, intercalation, nanotubes, and atom-level editing.

Use when the user asks about surface slabs, Miller indices, adsorbate placement, adsorption sites, water layers, passivation, heterostructures, lattice matching, moire bilayers, or catalysis workflows.

Use when the user asks to create, build, inspect, validate, or run computational workflows, DAG pipelines, relaxation→static chains, NEB/IRC workflows, or HPC job submission flows.

Generate and manage ABINIT DFT calculations. Use when the user requests ABINIT, or needs DFPT phonons, GW calculations, or BSE optical spectra.

Use when the user asks for adsorption energy, binding energy, or wants to compare how strongly a molecule binds to a surface.

Use AmberTools antechamber for molecular force field parameterization. Generates GAFF/GAFF2 parameters and AM1-BCC or RESP charges for use in AMBER or LAMMPS classical MD simulations.

Use when the user asks about Bader charge analysis, charge transfer, oxidation states from DFT, or electron density partitioning.

Use when the user asks about CO2 reduction reaction (CO2RR), CO2 electroreduction intermediates, Faradaic efficiency, or selectivity toward CO, methanol, methane, formic acid, etc.

Use when the user asks about COHP (Crystal Orbital Hamilton Population), chemical bonding analysis, LOBSTER output, orbital-resolved bonding, or bonding/antibonding character between atoms.

Use when the user asks to test ENCUT convergence, k-point convergence, or any parameter sweep to determine converged computational settings.

CP2K geometry optimization. Handles bulk, slab, and molecular systems with GPW method. Efficient for large systems (200+ atoms).

CP2K single point energy calculation. Uses GTH pseudopotentials, Gaussian-plane-wave (GPW) method, and DZVP basis sets for periodic DFT.

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

Train DeePMD-kit machine learning potentials. Covers DPA-3 (recommended), se_e2_a (legacy), and fine-tuning from pretrained models.

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.

Use when the user asks about density of states (DOS), projected DOS (PDOS), d-band center, spin-resolved DOS, or electronic structure analysis from completed DFT calculations.

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

Use when the user asks to generate a reaction energy diagram, free energy profile, potential energy surface plot, or pathway comparison diagram for catalysis or reaction mechanism studies.

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.

Use when the user asks for Gibbs free energy, zero-point energy (ZPE), thermal corrections, or thermodynamic properties from DFT + frequency data.

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.

Use when the user asks about HER (hydrogen evolution reaction), hydrogen adsorption free energy, or volcano plot descriptor for HER catalysts.

Automatically logs new discoveries to CLAUDE.md files. Triggers when fixing bugs, discovering pitfalls, finding performance issues, or learning new patterns in the codebase.

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

Run LAMMPS molecular dynamics with ReaxFF reactive force field. Use when the user needs reactive MD for combustion, oxidation, corrosion, or bond breaking/forming.

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

Use when the user asks about NRR (nitrogen reduction reaction), ammonia synthesis, N2 fixation, or the electrochemical reduction of N2 to NH3 on a catalyst surface.