data-pipeline

Ingest multimodal documents into a structured knowledge wiki with graph visualization.

38|12|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/YesIamGodt/knowledge-pipline --skill data-pipeline-yesiamgodt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-pipeline
Source: https://github.com/YesIamGodt/knowledge-pipline/tree/main/packages/create-data-pipeline/skill
Command: npx skills add https://github.com/YesIamGodt/knowledge-pipline --skill data-pipeline-yesiamgodt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingests documents from multiple modalities into a persistent structured knowledge wiki, enabling automatic knowledge fusion, cross-source contradiction detection, multi-source queries, and knowledge graph visualization.

Core Features & Use Cases

  • Multimodal ingestion: PDF, images, videos, Word, Excel, PPT, HTML, and more into wiki sources.
  • Knowledge fusion: new content merges with existing entity/concept pages instead of overwriting.
  • Active contradiction detection: automatically flags cross-source inconsistencies and preserves sources.
  • Cross-source aggregation and multi-view queries: compare perspectives from multiple sources and reveal consensus and disagreements.
  • Knowledge graph: automatically builds and visualizes an interactive graph of wiki pages.

Quick Start

Ingest a sample document to populate wiki sources and trigger initial knowledge graph construction.

Frequently Asked Questions about data-pipeline

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

FAQPage Schema
How do I ingest multimodal documents into a structured knowledge wiki?

To ingest multimodal documents into a knowledge wiki, this Skill processes PDFs, images, videos, Word, Excel, PPT, and HTML files into persistent, structured wiki sources with metadata frontmatter.

What is cross-source contradiction detection in a knowledge graph?

Cross-source contradiction detection automatically flags inconsistencies between ingested documents. It preserves original sources while merging new content into existing entity pages to highlight disagreements.

Can I merge new content with existing wiki pages without overwriting data?

Yes, knowledge fusion merges new content with existing entity and concept pages instead of overwriting them. This ensures previous data is preserved during multimodal document ingestion.

How do I visualize a knowledge graph from multiple ingested documents?

You can visualize a knowledge graph from ingested documents by using the automatic graph construction feature, which builds and displays an interactive graph of structured wiki pages.

Does this knowledge wiki support cross-source aggregation and multi-view queries?

Yes, cross-source aggregation supports multi-view queries to compare perspectives from multiple sources. This reveals consensus and disagreements across ingested multimodal documents.