activeinferenceinstitute/gnn-llm-analysis
src/llm/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add activeinferenceinstitute/generalizednotationnotation gnn-llm-analysisInstall 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, 3:37 AM39.7s28 files scanned
SKILL.md
- name:
- gnn-llm-analysis
- description:
- 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 LLM Analysis (Step 13)
Purpose
Provides LLM-enhanced analysis of GNN models including natural language interpretation, model summarization, structural analysis, and AI-assisted insights using multiple provider backends.
Key Commands
# Run LLM analysis
python src/13_llm.py --target-dir input/gnn_files --output-dir output --verbose
# As part of pipeline
python src/main.py --only-steps 13 --verbose
Provider Recovery Chain
The LLM module supports multiple providers with automatic recovery:
- Ollama (local) — Preferred for privacy and speed
- OpenAI — GPT-4/3.5 API
- Anthropic / OpenRouter — Additional providers
API
from llm import (
process_llm, LLMProcessor, LLMAnalyzer,
analyze_gnn_file_with_llm, extract_variables, extract_connections,
perform_semantic_analysis, generate_model_insights,
generate_documentation, generate_llm_summary,
get_available_providers, get_module_info
)
# Process LLM step (used by pipeline)
process_llm(target_dir, output_dir, verbose=True)
# Use the LLMProcessor class
processor = LLMProcessor()
result = processor.analyze(gnn_content)
description = processor.generate_description(gnn_content)
# Use the LLMAnalyzer class
analyzer = LLMAnalyzer()
insights = analyzer.analyze_content(gnn_content)
# Analyze a file with LLM
result = await analyze_gnn_file_with_llm(content)
# Extract model components
variables = extract_variables(content)
connections = extract_connections(content)
# Check available providers
providers = get_available_providers() # e.g., ['ollama', 'openai']
Key Exports
LLMProcessor— class withanalyze(),analyze_model(),generate_description()LLMAnalyzer— class withanalyze_content(),extract_insights()analyze_gnn_file_with_llm— async full analysisextract_variables,extract_connections,extract_sections— component extractiongenerate_model_insights,generate_documentation,generate_llm_summaryUnifiedLLMProcessor,AnalysisType,ProviderType— advanced provider API
Dependencies
# LLM PyPI packages are core dependencies (uv sync)
uv sync
# Optional: uv sync --extra llm (compatibility; same pins)
# Install Ollama CLI separately for local inference: https://ollama.com
Output
- LLM analysis reports in
output/13_llm_output/ - Natural language model summaries
- AI-generated insights and recommendations
MCP Tools
This module registers tools with the GNN MCP server (see mcp.py):
process_llmanalyze_gnn_with_llmgenerate_llm_documentation
References
- AGENTS.md — Module documentation
- README.md — Usage guide
- SPEC.md — Module specification
- providers/ — Provider-specific implementations
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