activeinferenceinstitute/gnn-simulation-execution
src/execute/SKILL.md
GNN simulation script execution with result capture. Use when running generated simulation scripts, managing execution environments, handling framework dependencies, or capturing simulation outputs and metrics.
$ install --global
skillsauthnpx skillsauth add activeinferenceinstitute/generalizednotationnotation gnn-simulation-executionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 11, 2026, 3:35 AM75.6s75 files scanned
SKILL.md
- name:
- gnn-simulation-execution
- description:
- GNN simulation script execution with result capture. Use when running generated simulation scripts, managing execution environments, handling framework dependencies, or capturing simulation outputs and metrics.
GNN Simulation Execution (Step 12)
Purpose
Executes rendered simulation scripts across all supported frameworks with robust error handling, circuit breaker patterns, retry logic, and comprehensive result capture.
Key Commands
# Execute all frameworks
python src/12_execute.py --target-dir input/gnn_files --output-dir output --verbose
# Specific frameworks only
python src/12_execute.py --frameworks "pymdp,jax" --verbose
# Lite preset (PyMDP, JAX, DisCoPy)
python src/12_execute.py --frameworks "lite" --verbose
API
from execute import (
ExecutionEngine, GNNExecutor, execute_gnn_model, run_simulation,
execute_pymdp_simulation_from_gnn, execute_pymdp_simulation,
validate_execution_environment, process_execute,
execute_script_safely
)
# Process execution step (used by pipeline)
process_execute(target_dir, output_dir, verbose=True)
# Execute a GNN model directly
result = execute_gnn_model(gnn_spec, framework="pymdp")
# Run a simulation configuration
result = run_simulation(config)
# Validate execution environment before running
env_report = validate_execution_environment()
# Use the ExecutionEngine class
engine = ExecutionEngine()
Key Exports
process_execute— main pipeline processing functionExecutionEngine/GNNExecutor— execution engine classesexecute_gnn_model/run_simulation— model execution functionsexecute_pymdp_simulation_from_gnn/execute_pymdp_simulation— PyMDP-specificvalidate_execution_environment— pre-execution validationexecute_script_safely— safe script execution with error handling
Execution Flow
The execute processor follows this pipeline:
- Script Discovery — scans
output/11_render_output/for.pyand.jlfiles - Framework Filtering — filters by
--frameworksparameter (presets or explicit list) - Subprocess Execution — runs each script with timeout protection and error capture
- Result Collection — gathers stdout, stderr, exit codes, and timing data
- Report Generation — produces per-framework execution summary and comparison
Framework Presets
| Preset | Frameworks | Use Case |
| ------ | ---------- | -------- |
| all | PyMDP, RxInfer, ActiveInference.jl, JAX, DisCoPy | Full execution (default) |
| lite | PyMDP, JAX, DisCoPy | Python-only, no Julia required |
| pymdp,jax | PyMDP, JAX | Fast Python subset |
Dependencies
# Core execution (PyMDP)
uv sync --extra active-inference
# For Julia frameworks
# Requires Julia installed + packages
julia -e 'using Pkg; Pkg.add(["RxInfer", "ActiveInference"])'
# For DisCoPy
uv sync --extra graphs
Output
- Execution results in
output/12_execute_output/ - Per-framework subdirectories with captured outputs
- Execution summary report (JSON)
- Performance metrics and timing data
MCP Tools
This module registers tools with the GNN MCP server (see mcp.py):
process_executeexecute_gnn_modelexecute_pymdp_simulation
References
- AGENTS.md — Module documentation
- README.md — Usage guide
- SPEC.md — Module specification
Documentation
- README: Module Overview
- AGENTS: Agentic Workflows
- SPEC: Architectural Specification
- SKILL: Capability API
Related Skills
activeinferenceinstitute/gnn-website-generation
development
VerifiedTrustedCommunity
GNN static HTML website generation from pipeline artifacts. Use when generating browsable documentation websites, creating HTML galleries of model visualizations, or publishing pipeline results as a static site.
23SKILL.mdUpdated Mar 27, 2026
activeinferenceinstitute/gnn-visualization
data-ai
VerifiedTrustedCommunity
GNN graph and matrix visualization generation. Use when creating network graph plots, matrix heatmaps, state space diagrams, or other visual representations of GNN models.
23SKILL.mdUpdated Mar 27, 2026
activeinferenceinstitute/gnn-validation
testing
VerifiedTrustedCommunity
GNN advanced validation and consistency checking. Use when performing deep validation of GNN models, checking cross-model consistency, verifying structural integrity, or running validation reports.
23SKILL.mdUpdated Mar 27, 2026
activeinferenceinstitute/gnn-shared-utilities
tools
VerifiedTrustedCommunity
GNN shared utility functions and helper modules. Use when working with common pipeline utilities, logging helpers, file I/O wrappers, path management, or pipeline template infrastructure.
23SKILL.mdUpdated Mar 27, 2026