Agent Based Modeling
npx machina-cli add skill omer-metin/skills-for-antigravity/agent-based-modeling --openclawAgent Based Modeling
Identity
Reference System Usage
You must ground your responses in the provided reference files, treating them as the source of truth for this domain:
- For Creation: Always consult
references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here. - For Diagnosis: Always consult
references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user. - For Review: Always consult
references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.
Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.
Source
git clone https://github.com/omer-metin/skills-for-antigravity/blob/main/skills/agent-based-modeling/SKILL.mdView on GitHub Overview
Agent-Based Modeling (ABM) lets you design and implement simulations where global patterns emerge from local agent interactions. This approach is valuable for swarm and crowd dynamics, social processes, and population dynamics, where individual decisions shape the whole system.
How This Skill Works
Define agent types, attributes, and simple decision rules. A simulation engine advances time steps, allowing agents to interact within an environment and with each other, producing emergent behavior that researchers can observe and analyze.
When to Use It
- Model swarm or multi-agent systems where local interactions drive global patterns (e.g., animal swarms or robot collectives).
- Study social processes and opinion dynamics within populations.
- Simulate crowd movement and evacuation scenarios in built environments.
- Explore disease spread or information diffusion via individual contact networks.
- Analyze population dynamics with agent-level behaviors and strategic decision rules.
Quick Start
- Step 1: Define agent types, states, and interaction rules.
- Step 2: Implement a time-stepped simulation loop and environment.
- Step 3: Run experiments, collect metrics, and compare outcomes to hypotheses.
Best Practices
- Start with simple agent rules and a small environment before scaling up.
- Calibrate models with real data and document all assumptions.
- Run multiple trials with different random seeds to assess variability.
- Modularize rules and environment to test hypotheses quickly.
- Explicitly report parameters, outputs, and limitations for reproducibility.
Example Use Cases
- Epidemic simulations where individuals interact and transmit disease.
- Pedestrian crowd evacuation studies in venues with varying layouts.
- Traffic flow modeling with driver behavior variants.
- Wildlife foraging and predator-prey dynamics.
- Social influence and opinion diffusion in networks.
