菜单
GNN graph and matrix visualization generation. Use when creating network graph plots, matrix heatmaps, state space diagrams, or other visual representations of GNN models.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ActiveInferenceInstitute/GeneralizedNotationNotation --skill gnn-visualization命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
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 comprehensive test suite execution and management. Use when running tests, writing new test cases, checking coverage, debugging test failures, or validating pipeline correctness across all 25 GNN modules.
GNN advanced statistical analysis and result aggregation. Use when performing statistical analysis on simulation results, cross-simulation aggregation, computing information-theoretic metrics, or creating analytical visualizations of pipeline outputs.
| name | gnn-visualization |
| description | GNN graph and matrix visualization generation. Use when creating network graph plots, matrix heatmaps, state space diagrams, or other visual representations of GNN models. |
Generates static visualizations of GNN models including network graphs, matrix heatmaps, state space diagrams, and connection maps using matplotlib and networkx.
# Run visualization
python src/8_visualization.py --target-dir input/gnn_files --output-dir output --verbose
# As part of pipeline
python src/main.py --only-steps 8 --verbose
from pathlib import Path
from visualization import (
GNNVisualizer,
MatrixVisualizer,
generate_graph_visualization,
generate_matrix_visualization,
generate_visualizations,
process_visualization,
)
# Use the GNNVisualizer class
viz = GNNVisualizer(output_dir="output/")
viz.generate_graph_visualization(graph_data)
viz.generate_matrix_visualization(matrix_data)
# Standalone functions
generate_graph_visualization(graph_data, output_dir="output/")
generate_matrix_visualization(matrix_data, output_dir="output/")
# Run full visualization step (used by pipeline)
process_visualization(
Path("input/gnn_files"), Path("output/8_visualization_output"), verbose=True
)
GNNVisualizer — main visualization classMatrixVisualizer — matrix-specific visualizationgenerate_graph_visualization — network graph plotsgenerate_matrix_visualization — matrix heatmapsprocess_visualization — pipeline processing (JSON-first when step-3 *_parsed.json exists)Visualization uses a four-tier recovery system:
# matplotlib + networkx (included in core)
uv sync
# For additional viz backends
uv sync
output/8_visualization_output/This module registers tools with the GNN MCP server (see mcp.py):
get_visualization_module_infoget_visualization_optionslist_visualization_artifactsprocess_visualization