菜单
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).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | electronic-analysis |
| description | 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). |
| Tool | Purpose |
|---|---|
catgo_dos_total | Total DOS |
catgo_dos_compute | Projected DOS (PDOS) for atom groups |
catgo_dos_dband | D-band center, width, filling (catalysis) |
catgo_dos_from_dir | Load DOS from remote HPC directory |
session_id from file upload or catgo_dos_from_dir{"groups": [{"atoms": [0,1,2], "channels": "d", "label": "Surface Pt d"}]}catgo_dos_compute with session_id and groupsChannel syntax: "d", "s,p", "dxy,dz2"
catgo_dos_dband(session_id, atoms=[surface_indices]) — Returns d-band center, width, filling.
occupied_only_center=True (default) for occupied d-band center| Tool | Purpose |
|---|---|
catgo_bands_data | Band energies, k-path, band gap |
catgo_bands_projections | Projected (fat) bands with orbital weights |
Report: direct/indirect gap, gap value, high-symmetry labels.
catgo_cohp_data — Crystal Orbital Hamilton Population from LOBSTER output.
bond_indices: 1-based bond numbersAll MD tools accept trajectory_b64 (base64-encoded file) and format (pdb, xyz, extxyz, lammpstrj).
| Tool | Purpose | Key Parameters |
|---|---|---|
catgo_md_rdf | Radial distribution g(r) | pairs, r_range, n_bins |
catgo_md_rmsd | RMSD over time (stability) | ref_frame, atom_indices |
catgo_md_rmsf | Per-atom fluctuation | atom_indices |
catgo_md_dihedrals | Dihedral angle evolution | atom_quartets |
| Tool | Purpose |
|---|---|
catgo_md_hbonds | Detect H-bonds per frame |
catgo_md_hbond_lifetime | H-bond lifetime autocorrelation |
Methods: baker_hubbard or wernet_nilsson. Default: D-A 3.5 A, D-H-A angle 150 deg.
| Tool | Purpose |
|---|---|
catgo_md_clustering | Cluster frames by structural similarity (kmeans/dbscan) |
catgo_md_dimreduce | PCA/t-SNE/UMAP embedding |
catgo_md_planar_density | 2D density map (diffusion analysis) |
catgo_dos_from_dir(remote_path="...") → 2. catgo_dos_total →catgo_dos_dband(atoms=[surface]) → 4. catgo_dos_compute(groups=[...])catgo_md_rdf(pairs=[["O","H"],["O","O"]]) → 2. catgo_md_hbonds →catgo_md_hbond_lifetime → 4. catgo_md_planar_density(plane="xy")