Skip to content

Repository files navigation

World Model Skills

A reusable skill package for Claude Code, Codex, and similar coding/research agents focused on world model research workflows. Covers five method families: Dreamer, JEPA, MuZero, Diffusion World Models, and Transformer World Models.

Current version: v1.0.0-alpha — 187 papers, 20-prompt eval at 100% across all metrics.

Eval results (v1.0.0-alpha)

Metric Score
Factual correctness 100.0%
Citation hit 100.0%
Executability 100.0%
Debug hit 100.0%
Benchmark accuracy 100.0%
Hallucination rate 0.0%

What this project provides

  • world-model-research/SKILL.md: World model research skill definition (4 modes, method family taxonomy).
  • metadata/: structured indexes for papers, code, evidence, and benchmarks.
  • scripts/: metadata build, evidence validation, and completeness checking.
  • eval/: multi-mode eval suite with scoring rubric.
  • docs/: roadmap, evidence schema, paper-code linking policy, release workflow.
  • CLAUDE.md: project rules for Claude Code agents working in this repo.

What this project does not bundle by default

  • Full paper PDFs and full third-party codebases should usually stay local.
  • For open-source publishing, share metadata + scripts; fetch source artifacts on demand.

Repository layout

.
├── world-model-research/
│   ├── SKILL.md
│   ├── references/
│   └── scripts/
├── metadata/
├── scripts/
├── eval/
└── corpus/                   # local cache; large files ignored by default

Method families covered

Family Core idea Representative papers
Dreamer RSSM + actor-critic in latent space DreamerV1, DreamerV2, DreamerV3
JEPA Predictive latent, no decoder I-JEPA, V-JEPA-2, Var-JEPA
MuZero MCTS + learned dynamics MuZero, EfficientZero
Diffusion WM Diffusion-based dynamics prediction AVID, UniPi
Transformer WM Autoregressive transformer over latents TWM, IRIS, STORM

Quick start

  1. Put your local paper/code assets under corpus/ (optional for public repo users).
  2. Build the paper catalog:
python scripts/build_paper_catalog.py --input metadata/papers_index.csv --output metadata/paper_catalog.csv
  1. Validate data integrity:
python scripts/validate_evidence_index.py --input metadata/evidence_index.csv
python scripts/check_metadata_completeness.py --input metadata/paper_catalog.csv
  1. Use the skill — ask about world model methods, reproduction, debugging, or drafting.

Environment

  • Python stdlib only. No pip dependencies.
  • Python 3.11+. Tested with Python 3.13.5.
  • Run commands from repo root.

Relationship to JEPA-skills

This repo is an independent sibling of JEPA-skills. JEPA-skills covers the JEPA method family in detail; world-model-skills references JEPA as one of five families. The two repos share architecture but maintain separate metadata and eval suites.

License

MIT. Users are responsible for third-party paper/code licenses.

About

An AI copilot for world model research — answer questions, plan reproductions, debug training, and draft papers backed by traceable evidence.

Resources

Contributing

Stars

4 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages