agentleFS
Fitz798Fitz798/world-model-skills/CLAUDE.md

world-model-skills

CLAUDE.md4 starsChanged 5 months agoMITView on GitHub

World Model Skills is a reusable skill package for Claude Code agents doing world model research. It covers five method families — Dreamer, JEPA, MuZero, Diffusion World Models, Transformer World Models — and provides a structured skill definition (world-model-research/SKILL.md), metadata indexes, validation/build scripts, and an evaluation benchmark suite. Current version: v1.0.0-alpha — 185 papers, 40-prompt eval at 100% across all 6 metrics. All commands run from repo root. Only Python stdlib is required (3.11+). Output: corpus/code/extracted/{code_id}/ with STRUCTURE.txt tree overview.

  • Installs packages

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All commands run from repo root.

    line 13
  2. Distinctive:

    When answering, always situate work within its family:

    line 177

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project overview

World Model Skills is a reusable skill package for Claude Code agents doing world model research. It covers five method families — Dreamer, JEPA, MuZero, Diffusion World Models, Transformer World Models — and provides a structured skill definition (world-model-research/SKILL.md), metadata indexes, validation/build scripts, and an evaluation benchmark suite.

Current version: v1.0.0-alpha — 185 papers, 40-prompt eval at 100% across all 6 metrics.

Common commands

All commands run from repo root. Only Python stdlib is required (3.11+).

Metadata build and validation

# Build paper catalog from source index
python scripts/build_paper_catalog.py --input metadata/papers_index.csv --output metadata/paper_catalog.csv

# Validate evidence index
python scripts/validate_evidence_index.py --input metadata/evidence_index.csv --check-paths --json eval/results/evidence_index_validation.json

# Check metadata completeness for release gating
python scripts/check_metadata_completeness.py --input metadata/paper_catalog.csv --json eval/results/metadata_completeness_report.json
# Extract code archives for agent-readable source access
python scripts/extract_code.py --all
python scripts/extract_code.py --code ijepa_main

Output: corpus/code/extracted/{code_id}/ with STRUCTURE.txt tree overview.

Storage architecture

corpus/
├── papers/
│   ├── pdf/{family}/     # Original PDFs by method family
│   └── md/               # Converted markdown (flat, paper_id.md + paper_id_brief.md)
├── code/
│   ├── archives/{family}/ # Original zip archives by method family
│   └── extracted/{code_id}/ # Extracted source code + STRUCTURE.txt
└── _duplicates/          # Dedup staging

All corpus/ content is gitignored. Paths in metadata/*.csv reference these locations.

PDF → Markdown conversion

# Convert all PDFs to structured markdown (requires docling)
python scripts/convert_pdfs.py --all --update-evidence

# Convert a specific paper
python scripts/convert_pdfs.py --paper dreamer_v3 --update-evidence

# Dry run to see what would be converted
python scripts/convert_pdfs.py --all --dry-run

Output: corpus/papers/md/{paper_id}.md (full) + {paper_id}_brief.md (abstract+conclusion).

Corpus ingestion pipeline

# Search arXiv and auto-download papers
python scripts/ingest_arxiv.py --query "world model reinforcement learning" --max 30
python scripts/ingest_arxiv.py --ids 2301.04104,1803.10122 --tier core
python scripts/ingest_arxiv.py --query "dreamer world model" --max 50 --resume

# Manually register non-arXiv papers
python scripts/ingest_manual.py --title "World Models" --year 2018 --authors "Ha, Schmidhuber" --tier core --file paper.pdf --method-family transformer

# Link papers to GitHub repositories
python scripts/link_github.py --all-missing --min-stars 10
python scripts/link_github.py --paper dreamer_v3

These scripts require pip install -r requirements.txt (only requests needed).

Citation candidate generation

python world-model-research/scripts/make_citation_candidates.py --metadata metadata/paper_catalog.csv --query "dreamer,atari,planning" --topk 20 --output eval/results/candidates.csv

Eval workflow

# Extract one mode's prompts
python eval/filter_eval_by_mode.py --input eval/test_prompts_v1.jsonl --mode research_qa --output eval/results/qa_prompts.jsonl

# Summarize judged results
python eval/summarize_eval.py --input eval/results/<scored>.jsonl --output eval/results/<summary>.md

# Check evidence/mapping coverage
python eval/check_evidence_coverage.py --responses eval/results/<responses>.md --output eval/results/<coverage>.json

Architecture

Three-layer design (same as JEPA-skills)

  1. Skill layer (world-model-research/) — 4 modes, evidence-binding contract, method family taxonomy
  2. Metadata layer (metadata/) — papers_index, paper_catalog, evidence_index, code_index, benchmark_index (new)
  3. Eval layer (eval/) — prompts, rubric (6 dimensions incl. benchmark_accuracy), results

What's different from JEPA-skills

FeatureJEPA-skillsworld-model-skills
Method families1 (JEPA)5 (Dreamer, JEPA, MuZero, Diffusion, Transformer)
Eval dimensions56 (+ benchmark_accurate)
Metadata fieldsmodality, task, evidence_level+ method_family, benchmark_family
Benchmark indexN/Ametadata/benchmark_index.csv
Min evidence (QA)2 paper3 paper
Min evidence (repro)1 paper + 1 code1 paper + 1 code + 1 benchmark
MVP paper count148185

Eval benchmark reference (v1.0.0-alpha)

40 prompts (10 per mode), all metrics at 100%:

MetricScoreN
Factual correctness100.0%40
Citation hit100.0%40
Executability100.0%10
Debug hit100.0%10
Benchmark accuracy100.0%5
Hallucination rate0.0%40

Results in eval/results/v1_0_0_baseline_scored.jsonl and v1_0_0_baseline_summary.md.

Current state

Papers

FamilyCountCode repos
Dreamer5512
JEPA764
MuZero201
Diffusion163
Transformer185
Total18525

Data assets

  • 185 papers indexed in papers_index.csv and paper_catalog.csv
  • 0 unclassified — all 185 papers have method_family, modality, task, evidence_level
  • 25 confirmed code repositories (13.5% coverage)
  • 200+ papers converted to markdown via docling (full + brief versions)
  • 8 benchmarks in benchmark_index.csv
  • 17 evidence rows in evidence_index.csv
  • 6 local code archives in code_index.csv

Key papers covered

  • Dreamer lineage: PlaNet, DreamerV1/V2/V3, DayDreamer, TD-MPC2, Dreamer-CDP
  • MuZero lineage: MuZero, EfficientZero, Sampled MuZero, VQ Planning
  • JEPA lineage: I-JEPA, V-JEPA-2, MC-JEPA, Var-JEPA, LeJEPA, ThinkJEPA
  • Diffusion: DIAMOND (NeurIPS 2024), AVID, Nano World Models
  • Transformer: IRIS (ICLR 2023), TECO, Decision Transformer
  • Benchmarks: Atari 100k (SimPLe), DMControl, Crafter, Meta-World
  • All canonical papers: 28/33 (85%)
  1. Action/Claim list with IDs
  2. Evidence table with source type and pointer
  3. Mapping line: C# -> E# or A# -> E#
  4. Confidence: high | medium | low

Minimum evidence: research_qa ≥ 3 papers; reproduction_plan ≥ 1 paper + 1 code + 1 benchmark; debug_triage ≥ 1 code; writing_citation every claim → at least one paper.

Method family taxonomy

When answering, always situate work within its family:

FamilyCoreKey signal
DreamerRSSM + actor-critic in latent space"dreamer", "rssm", "imagination"
JEPAPredictive latent, no decoder"jepa", "joint embedding predictive"
MuZeroMCTS + learned dynamics"muzero", "mcts", "tree search"
Diffusion WMDiffusion-based dynamics prediction"diffusion" + "world model"
Transformer WMAutoregressive transformer over latents"transformer" + "world model" + "tokenizer"

Relationship to JEPA-skills

Independent sibling repo. JEPA-skills covers the JEPA family in detail; world-model-skills references JEPA work as one of five families without duplicating metadata.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.