Skip to content
Back to skills

Web World Models

ASecurity

Bridge deterministic web code and generative LLMs via hybrid world models. State and physics defined by TypeScript code, LLMs generate narrative/aesthetics on top. Uses typed interfaces, deterministic hashing, graceful degradation—enabling scalable interactive environments from travel atlases to fictional worlds without databases.

  • 6 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 9, 2026
developmenttypescriptpythondatabase

Security analysis

A100/100

Scanned September 9, 2026

npx -y skills add ADu2021/skillXiv --skill web-world-models --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Web World Models?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Web World Models
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/adu2021-web-world-models/badge)](https://www.skillsdirectory.com/skills/adu2021-web-world-models)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: web-world-models
title: "Web World Models"
version: 0.0.2
engine: skillxiv-v0.0.2-claude-opus-4.6
license: MIT
url: https://arxiv.org/abs/2512.23676
keywords: [world-models, simulation, language-models, web-technologies]
description: "Bridge deterministic web code and generative LLMs via hybrid world models. State and physics defined by TypeScript code, LLMs generate narrative/aesthetics on top. Uses typed interfaces, deterministic hashing, graceful degradation—enabling scalable interactive environments from travel atlases to fictional worlds without databases."
---

## Overview

Web World Models combine structured code for invariant state with LLM-driven narrative generation.

## Core Technique

**Two-Layer Architecture:**

```python
# Physics layer (deterministic code)
class Physics:
    inventories: dict  # Code enforces consistency
    coordinates: XYZ

# Imagination layer (LLM-driven)
class Narrative:
    descriptions = llm.generate(physics_state)
    dialogue = llm.generate(context)
```

## References

- Physics layer as TypeScript code
- Imagination layer for aesthetics
- Deterministic hashing for consistency

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.