Import Wizard

Scan source folders and ingest PDFs, images, and text into the iNNfo hierarchical model.

Updated May 12, 2025
One-click install
npx skills add https://github.com/innV0/innV0.com --skill import-wizard
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Import Wizard
Source: https://github.com/innV0/innV0.com/tree/main/public/iNNfo/app/0-1-1/skills/import-wizard
Command: npx skills add https://github.com/innV0/innV0.com --skill import-wizard

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Import Wizard streamlines bringing external knowledge into the iNNfo hierarchical model, automating source discovery, ingestion, and traceability.

Core Features & Use Cases

  • Automated scanning of source folders to identify new files and compare with existing _source instances.
  • Creation of source instances, extraction of content, and storage in a standardized .iNNfo.md structure.
  • Establishment of traceable relationships between sources and generated artifacts for auditability.
  • Use Case: Import a new PDF and automatically create a source instance, index content, and link to a district artifact.

Quick Start

Tell the Import Wizard to scan sources/raw and start importing new files.

Frequently Asked Questions about Import Wizard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate data ingestion for PDFs and images into a hierarchical knowledge model?

Automated data ingestion scans source folders to identify new files, extracts content from PDFs, images, and text, and stores it in a standardized hierarchical structure. This eliminates manual file processing while building traceable source instances.

What is artifact linking and how does it ensure traceability for imported data?

Artifact linking establishes explicit relationships in the root graph between imported sources and generated outputs. This maintains provenance and auditability by tracking exactly where each piece of extracted content originated within the knowledge model.

How do I import external files and organize them into dedicated instance folders?

Importing external files involves scanning a specified source directory, creating unique source instances, and automatically storing extracted content in dedicated instance folders. This folder-based organization ensures clear auditability and structured data management.

Does automated source management compare new files against existing source instances?

Yes, automated source management scans directories and compares newly identified files against existing source instances. This prevents duplicate ingestion and updates the hierarchical model only with genuinely new content.

Can I use centralized metamodel definitions for importing text inputs and PDFs?

Yes, you can use centralized metamodel definitions when importing text inputs, images, and PDFs. The ingestion process satisfies technical requirements by applying these standardized definitions to structure content within the hierarchical model.

What are the limitations of folder-based organization for data ingestion automation?

Folder-based organization for data ingestion requires files to be placed in designated source directories before scanning begins. It does not pull from arbitrary locations, meaning source management depends on consistent directory structure maintenance.