菜单
GNN environment setup and dependency management. Use when configuring the development environment, installing dependencies, managing virtual environments, or troubleshooting dependency issues for the GNN pipeline.
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
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-environment-setup |
| description | GNN environment setup and dependency management. Use when configuring the development environment, installing dependencies, managing virtual environments, or troubleshooting dependency issues for the GNN pipeline. |
Manages environment configuration, virtual environment creation, and dependency installation for the GNN pipeline. Supports both core and optional dependency groups via uv or pip.
# Run setup step
python src/1_setup.py --target-dir input/gnn_files --output-dir output --verbose
# As part of pipeline
python src/main.py --only-steps 1 --verbose
# Using uv (recommended)
uv sync # Core dependencies (includes Step 12 Python backends: jax, numpyro, discopy)
uv sync --extra dev # Development tools
uv sync --all-extras # Everything
uv pip install torch # Optional PyTorch backend while no patched torch release exists
These groups match [project.optional-dependencies] in pyproject.toml:
| Group | Key Packages | Purpose |
|---|---|---|
Core uv sync | pymdp, jax, numpyro, discopy, LLM clients, visualization | Standard pipeline runtime |
audio | librosa, soundfile, pedalboard, pydub | Audio generation |
gui | gradio, streamlit | GUI interface |
ml-ai | transformers, scipy, scikit-learn | Machine learning extensions |
| Manual install | torch, bnlearn | Optional backends excluded from the lock while Torch has no patched advisory release |
graphs | graphviz | Graphviz bindings |
dev | pytest-*, mypy, ruff | Development tools |
research | jupyterlab, sympy, numba, cython | Research tools |
scaling | dask, distributed, ray | Parallel processing |
all | Named optional groups above | Full optional installation |
| Issue | Solution |
|---|---|
uv: command not found | curl -LsSf https://astral.sh/uv/install.sh | sh |
| PyMDP import fails | uv sync |
| matplotlib missing | uv sync |
| CUDA not detected | Install PyTorch manually, then check torch.cuda.is_available() |
This module registers tools with the GNN MCP server (see mcp.py):
check_uv_project_statusensure_directory_existsfind_project_gnn_filesget_standard_output_pathsget_uv_environment_infoinstall_uv_dependencysetup_uv_project_structuresync_uv_dependencies