ml-generative-diffcsp

Official

Generate symmetric crystals with exact composition.

Authorlearningmatter-mit
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps researchers generate novel crystal structures with exact chemical composition while enforcing space-group symmetry constraints, avoiding slow manual structure design.

Core Features & Use Cases

  • Symmetry-constrained generation: Use DiffCSP++ to generate candidate crystals conditioned on space group and Wyckoff positions.
  • Composition control: Specify atom types per Wyckoff site for composition-exact sampling.
  • Multiple generation modes: Support symmetry-constrained sampling (composition control) and unconditional sampling from trained distributions.

Quick Start

Use the Skill to generate 5 symmetry-constrained crystal CIFs for space group 58 with Wyckoff positions "2a,2d,4g" and atom types "Mn,Li,O" by calling mcp_diffcsp_generate_structures_with_symmetry(spacegroup=58, wyckoff_letters="2a,2d,4g", atom_types="Mn,Li,O", model_name="mp_csp", num_samples=5, step_lr=1e-5, output_dir="research/my_project").

Dependency Matrix

Required Modules

None required

Components

scriptsassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ml-generative-diffcsp
Download link: https://github.com/learningmatter-mit/AtomisticSkills/archive/main.zip#ml-generative-diffcsp

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.