菜单
Query materials databases for structures and properties. Use when asked to get crystal structures, material properties, phase diagrams, or thermodynamic data. Primary source is Materials Project, with NIST, PubChem as secondary.
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
Get fully up to date on a project, or build its weekly / PI-meeting update bundle, from INSIDE the project directory. Use when an agent lands cold in a project and needs the current state (open workstreams, what moved, open PI decisions, blockers), or when asked to "build the weekly update", "prep the PI meeting", or "aggregate the relevant files into the update dir". Mines only THIS repo, driven by its own .sync/manifest.yaml. No dependency on LabSync.
Run Quantum ESPRESSO DFT calculations. Use when asked to perform first-principles calculations, SCF, structural relaxation, band structure, DOS, phonons, or any ab initio quantum mechanical calculation.
Decide where and how to run compute jobs across available backends (HPC, cloud GPUs, local). Use when starting any compute-intensive task, choosing a backend or partition, deciding job parameters (walltime, GPU type, parallelism), or debugging compute infrastructure issues. Embeds the smoke-first iteration pattern — validate cheaply before scaling.
Orchestrate one or more long-running compute campaigns (HPC simulations, multi-stage MD pipelines, ensemble runs) where stages take hours to days and failures must not halt the pipeline. Use when running multiple parallel campaigns that share a stage structure (smoke → equilibration → production → analysis), when waiting on long jobs makes interactive driving impractical, or when designing a self-healing tick-based supervisor for compute work. Reads/writes per-campaign WORKFLOW.md files as durable state.
Analyze simulation data and compute properties. Use when asked to parse LAMMPS/QE output, calculate diffusion coefficients, RDF, MSD, energies, or generate plots and visualizations.
Generate candidate crystal structures from a chemical formula and assess their stability using ggen. Use when you need trial structures for a composition with no known experimental structure, or want stability-ranked polymorph candidates before running MD/DFT.
| name | materials-database |
| description | Query materials databases for structures and properties. Use when asked to get crystal structures, material properties, phase diagrams, or thermodynamic data. Primary source is Materials Project, with NIST, PubChem as secondary. |
| allowed-tools | ["Read","Write","Bash","WebSearch","WebFetch"] |
You are querying materials databases for structures and properties.
import os
from mp_api.client import MPRester
# Initialize with API key from environment
api_key = os.environ.get("MP_API_KEY")
with MPRester(api_key) as mpr:
# Get structure by formula
docs = mpr.materials.summary.search(formula="TiO2")
# Get by material ID
structure = mpr.get_structure_by_material_id("mp-2657")
# Search with properties
results = mpr.materials.summary.search(
band_gap=(1.0, 2.0),
is_stable=True
)
# Search for materials
curl -H "X-API-KEY: YOUR_KEY" \
"https://api.materialsproject.org/materials/summary/?formula=Fe2O3"
# Get specific material
curl -H "X-API-KEY: YOUR_KEY" \
"https://api.materialsproject.org/materials/mp-19770/"
Standard format for crystal structures:
data_TiO2
_cell_length_a 4.5937
_cell_length_b 4.5937
_cell_length_c 2.9587
_cell_angle_alpha 90.000
_cell_angle_beta 90.000
_cell_angle_gamma 90.000
_symmetry_space_group_name_H-M 'P 42/m n m'
...
TiO2 rutile
1.0
4.5937 0.0000 0.0000
0.0000 4.5937 0.0000
0.0000 0.0000 2.9587
Ti O
2 4
Direct
0.0000 0.0000 0.0000
0.5000 0.5000 0.5000
...
Simple atomic coordinates:
6
TiO2 unit cell
Ti 0.000 0.000 0.000
Ti 2.297 2.297 1.479
O 1.396 1.396 0.000
...
from ase.io import read, write
# Read CIF, write POSCAR
atoms = read('structure.cif')
write('POSCAR', atoms, format='vasp')
# Read CIF, write LAMMPS data
write('structure.data', atoms, format='lammps-data')
from pymatgen.core import Structure
from pymatgen.io.lammps.data import LammpsData
# Read CIF
struct = Structure.from_file('structure.cif')
# Write LAMMPS data file
lammps_data = LammpsData.from_structure(struct)
lammps_data.write_file('structure.data')
Search Database
Download Structure
Convert for Simulation
Add Force Field (for MD)
Save database queries to:
workspaces/project-name/
├── structures/
│ ├── mp-19770_Fe2O3.cif
│ ├── mp-19770_Fe2O3.vasp
│ └── mp-19770_Fe2O3.data
├── properties/
│ └── Fe2O3_properties.json
└── README.md # Document sources