lammps-simulation
π―Skillfrom fl-sean03/agentic-science-worker
Autonomously configures, runs, and analyzes molecular dynamics simulations using LAMMPS with literature-sourced parameters and scientific methodology.
Installation
npx skills add https://github.com/fl-sean03/agentic-science-worker --skill lammps-simulationSkill Details
Overview
# Agentic Science Worker
An autonomous AI agent system for computational materials science research. Designed to work with multiple coding agents ([Claude Code](https://claude.com/claude-code), [Aider](https://aider.chat), [OpenAI Codex](https://openai.com/codex), [Cursor](https://cursor.com)), this system enables AI to conduct scientific research like a PhD-level computational scientist.
Overview
The Agentic Science Worker can:
- Run molecular dynamics simulations (LAMMPS) with literature-sourced parameters
- Perform DFT calculations (Quantum ESPRESSO) for electronic structure
- Search scientific literature and extract methodology/parameters
- Query materials databases (Materials Project) for structures and properties
- Analyze results and compare with published values
- Execute on HPC clusters for large-scale computations
The agent operates autonomously: given a scientific question, it researches the methodology, finds parameters, runs simulations, verifies results against literature, and iterates until achieving physically reasonable results.
Architecture
```
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Coding Agent β
β Claude Code β Aider β OpenAI Codex β Cursor β
β (AGENTS.md defines researcher behavior and methodology) β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Skills β
β ββββββββββββ ββββββββββββ ββββββββββββ ββββββββββββ β
β β LAMMPS β β QE β β HPC β β MLIP β β
β β Skill β β Skill β β Skill β β Skill β β
β ββββββββββββ ββββββββββββ ββββββββββββ ββββββββββββ β
β ββββββββββββ ββββββββββββ ββββββββββββ β
β βLiteratureβ βMaterials β β Data β β
β β Search β β Database β β Analysis β β
β ββββββββββββ ββββββββββββ ββββββββββββ β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β External Tools β
β LAMMPS β Quantum ESPRESSO β Python β HPC Cluster β Web β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
```
Supported Agents
| Agent | Status | Configuration |
|-------|--------|---------------|
| [Claude Code](https://claude.com/claude-code) | Full Support | AGENTS.md, .claude/ |
| [Aider](https://aider.chat) | Full Support | AGENTS.md, configs/aider/ |
| [OpenAI Codex](https://openai.com/codex) | Planned | AGENTS.md |
| [Cursor](https://cursor.com) | Full Support | AGENTS.md, .cursorrules |
All agents read AGENTS.md (the [industry standard](https://github.com/AgenticAI-Foundation/AGENTS.md)) as their primary context file.
Quick Start
Prerequisites
- A supported coding agent:
- [Claude Code CLI](https://claude.com/claude-code) with subscription, OR
- [Aider](https://aider.chat) with API key, OR
- [Cursor](https://cursor.com)
- Python 3.10+
- LAMMPS (with GPU support recommended)
- Quantum ESPRESSO (optional, for DFT)
- Materials Project API key
Installation
- Clone the repository:
```bash
git clone https://github.com/yourusername/agentic-science-worker.git
cd agentic-science-worker
```
- Copy and configure settings:
```bash
cp config.example.yaml config.yaml
cp .claude/settings.json.example .claude/settings.json
cp .mcp.json.example .mcp.json
```
- Edit configuration files with your paths and API keys:
```yaml
# config.yaml
binaries:
lammps: "/path/to/your/lammps/bin/lmp"
qe_cpu: "/path/to/qe/bin"
api_keys:
materials_project: "YOUR_MP_API_KEY"
```
- Verify infrastructure:
```bash
cd benchmarks/evaluation