メニュー
GNN pipeline template and initialization system. Use when creating new pipeline steps, bootstrapping project structure, or understanding the thin orchestrator pattern for GNN module development.
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-template-init |
| description | GNN pipeline template and initialization system. Use when creating new pipeline steps, bootstrapping project structure, or understanding the thin orchestrator pattern for GNN module development. |
Initializes the pipeline environment and provides the canonical template for creating new pipeline steps. This is the entry point for the 25-step GNN pipeline.
# Run template initialization
python src/0_template.py --target-dir input/gnn_files --output-dir output --verbose
# Use as part of full pipeline
python src/main.py --only-steps 0 --verbose
from template import (
process_template_standardized, process_single_file,
validate_file, generate_correlation_id,
safe_template_execution, demonstrate_utility_patterns,
get_version_info
)
# Process template step (used by pipeline)
result = process_template_standardized(target_dir, output_dir, logger)
# Process a single file
result = process_single_file(file_path, output_dir, logger)
# Validate a file
is_valid = validate_file(file_path)
# Generate correlation ID for tracing
corr_id = generate_correlation_id()
process_template_standardized — main pipeline processing functionprocess_single_file — process individual filevalidate_file — file validationgenerate_correlation_id — unique ID for pipeline tracingsafe_template_execution — execution with error handlingget_version_info — module version metadata# N_module.py — Thin orchestrator (<150 lines)
from utils.pipeline_template import create_standardized_pipeline_script
run_script = create_standardized_pipeline_script("N_module.py", process_func, "Description")
src/module/processor.pyThis module registers tools with the GNN MCP server (see mcp.py):
template.get_infotemplate.process_directorytemplate.process_file