メニュー
GNN machine learning integration and model training. Use when training ML models on GNN data, checking ML framework availability, or integrating GNN pipeline outputs with machine learning workflows.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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 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.
| name | gnn-ml-integration |
| description | GNN machine learning integration and model training. Use when training ML models on GNN data, checking ML framework availability, or integrating GNN pipeline outputs with machine learning workflows. |
Integrates machine learning capabilities with the GNN pipeline, enabling feature extraction from parsed models, ML model training on GNN data, and framework availability checking.
# Run ML integration
python src/14_ml_integration.py --target-dir input/gnn_files --output-dir output --verbose
# As part of pipeline
python src/main.py --only-steps 14 --verbose
from ml_integration import process_ml_integration, check_ml_frameworks
# Process ML integration step (used by pipeline)
result = process_ml_integration(target_dir, output_dir, verbose=True)
# Check available ML frameworks
frameworks = check_ml_frameworks()
# Returns: {'pytorch': {'available': True, 'version': '2.x'},
# 'tensorflow': {'available': False},
# 'jax': {'available': True, 'version': '0.4.x'},
# 'sklearn': {'available': True, 'version': '1.x'}}
process_ml_integration — main pipeline processing functioncheck_ml_frameworks — checks availability of PyTorch, TensorFlow, JAX, scikit-learn| Framework | Check Key | Purpose |
|---|---|---|
| PyTorch | pytorch | Deep learning, CUDA support detection |
| TensorFlow | tensorflow | Neural network training |
| JAX | jax | Differentiable computing |
| scikit-learn | sklearn | Classical ML algorithms |
# ML framework deps
uv sync --extra ml-ai
# Includes: torch, transformers, datasets
output/14_ml_integration_output/This module registers tools with the GNN MCP server (see mcp.py):
check_ml_frameworksget_ml_module_infolist_ml_integration_targetsprocess_ml_integration