菜单
Generalized Notation Notation (GNN) processing pipeline for Active Inference generative models. Use when working with GNN files, running the 25-step pipeline, parsing model specifications, generating simulations, or producing visualizations and reports from GNN model definitions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | gnn-pipeline |
| description | Generalized Notation Notation (GNN) processing pipeline for Active Inference generative models. Use when working with GNN files, running the 25-step pipeline, parsing model specifications, generating simulations, or producing visualizations and reports from GNN model definitions. |
GNN (Generalized Notation Notation) is a text-based specification language for Active Inference generative models. This repository implements a 25-step processing pipeline (steps 0–24) that transforms GNN specifications into executable simulations, visualizations, analysis reports, and more.
.md GNN model files# Using just (recommended task runner)
just # List all 21 recipes
just test # Fast test suite
just pipeline # Full 25-step pipeline
just render-health # Check all 8 renderer backends
# Run full pipeline directly
python src/main.py --target-dir input/gnn_files --verbose
# Run specific steps only
python src/main.py --only-steps "3,5,11,12" --verbose
# Run a single step directly
python src/3_gnn.py --target-dir input/gnn_files --output-dir output --verbose
# Run tests
pytest src/tests/ -v
# Setup environment
uv sync && uv run python src/main.py --target-dir input/gnn_files --verbose
Every pipeline step follows the same pattern:
src/N_module.py → Thin orchestrator (<150 lines): CLI args, logging, delegation
src/module/ → Module directory: all domain logic
├── __init__.py → Public API exports
├── processor.py → Core processing logic
├── mcp.py → MCP tool registration (if applicable)
├── AGENTS.md → Module documentation
├── README.md → Usage guide
├── SPEC.md → Module specification
└── SKILL.md → This skill format (Claude Code activation)
| Phase | Steps | Purpose |
|---|---|---|
| Core (0–9) | Template, Setup, Tests, GNN Parse, Registry, Type Check, Validation, Export, Viz, Advanced Viz | Parse GNN files, validate, export, visualize |
| Simulation (10–16) | Ontology, Render, Execute, LLM, ML, Audio, Analysis | Generate and run simulations, analyze results |
| Output (17–24) | Integration, Security, Research, Website, MCP, GUI, Report, Intelligent Analysis | Produce deliverables and reports |
GNN files are Markdown documents with structured sections:
## GNNSection
ActInfPOMDP
## ModelName
My Model
## StateSpaceBlock
A[3,3,type=float] # Likelihood matrix
B[3,3,3,type=float] # Transition matrix
s[3,1,type=float] # Hidden state
## Connections
D>s # D feeds into s (directed)
s-A # s connects to A (undirected)
## InitialParameterization
A={(0.9,0.05,0.05), (0.05,0.9,0.05), (0.05,0.05,0.9)}
## ActInfOntologyAnnotation
A=LikelihoodMatrix
s=HiddenState
# Execute specific frameworks
python src/12_execute.py --frameworks "pymdp,jax" --verbose
# Lite preset (PyMDP, JAX, DisCoPy)
python src/12_execute.py --frameworks "lite" --verbose
# All frameworks (default)
python src/12_execute.py --frameworks "all" --verbose
Each src/module/ directory contains its own SKILL.md with module-specific instructions. See src/AGENTS.md for the complete module registry.
# Full test suite; refresh collect/pass counts before publishing them
uv run --extra dev python -m pytest src/tests/ -q --tb=no \
--ignore=src/tests/llm/test_llm_ollama.py \
--ignore=src/tests/llm/test_llm_ollama_integration.py
# Test a specific module
pytest src/tests/gnn/test_gnn_overall.py -v
# With coverage
pytest src/tests/ --cov=src -v
GNN command-line interface dispatch and health checks. Use when invoking the `gnn` CLI, validating subcommand availability, or checking command-line access to pipeline modules.
GNN LLM-enhanced analysis and model interpretation. Use when generating natural language descriptions of GNN models, getting AI-assisted model explanations, or performing LLM-powered analysis of Active Inference specifications.
GNN Language Server Protocol integration. Use when starting editor diagnostics, checking hover behavior, or validating LSP support for GNN files.
GNN Model Context Protocol processing and tool registration. Use when registering GNN operations as MCP tools, building MCP server configurations, or integrating GNN capabilities with LLM tool-use workflows.
GNN pipeline orchestration and configuration management. Use when configuring pipeline execution, setting step inclusion/exclusion, managing pipeline state, or customizing the 25-step execution flow.
GNN code generation for simulation frameworks. Use when generating PyMDP, RxInfer.jl, ActiveInference.jl, JAX, DisCoPy, PyTorch, NumPyro, Stan, or bnlearn code from GNN model specifications.