skills.rest
YesIamGodt
YesIamGodtCOMMUNITY
Explore all skills by this author →
GitHub

knowledge-pipline

Convert multimodal documents into a persistent knowledge wiki with graph visualization.

38|12|Updated Apr 11, 2026
Search Tags:#wiki#knowledge-graph#cross-source#ppt-generation#contradiction-detection#knowledge-pipeline#multimodal-ingestion
One-click install
npx skills add https://github.com/YesIamGodt/knowledge-pipline --skill knowledge-pipline
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: knowledge-pipline
Source: https://github.com/YesIamGodt/knowledge-pipline/tree/main
Command: npx skills add https://github.com/YesIamGodt/knowledge-pipline --skill knowledge-pipline

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, openai, requests, networkx, pypdf, python-docx, openpyxl, python-pptx, beautifulsoup4, lxml, trafilatura, pillow, opencv-python, and includes scripts (resource) components.

What problem does it solve?

This Skill converts multimodal documents into a persistent, reasoning-ready wiki, enabling cross-document analysis, automatic contradiction detection, and a navigable knowledge graph.

Core Features & Use Cases

  • Multimodal ingestion: PDF, images, videos, Word, Excel, PPT, HTML, Markdown
  • Knowledge fusion: merges new content into existing entity/concept pages while preserving history and flagging contradictions
  • Cross-source contradiction detection and multi-source aggregation: surface divergences with evidence across documents
  • Knowledge graph visualization: interactive graph to explore concepts, entities, and relations
  • PPT generation and export: generate editable Live PPT decks from wiki knowledge

Quick Start

立即摄入一个文档（如 PDF），让 wiki 自动建立实体和概念并生成知识图谱。

Frequently Asked Questions about knowledge-pipline

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

FAQPage Schema
How do I build a knowledge graph from multiple PDF and Word documents?▼

You build a knowledge graph from PDFs and Word files by ingesting multimodal documents to automatically establish entities and concepts, then generating an interactive graph visualization for navigation.

How does cross-source contradiction detection work when merging new content into an existing wiki?▼

Contradiction detection works by merging new multimodal ingestion into existing entity pages while preserving history, automatically flagging divergences with evidence across multiple documents.

What is the best way to generate a PPT presentation from a knowledge base?▼

Generating a PPT from a knowledge base uses the PPT generation slash command, which exports editable Live PPT decks directly from the wiki's fused cross-source knowledge.

Can I ingest images and videos alongside text files for knowledge fusion?▼

Yes, multimodal ingestion supports images and videos alongside PDF, Word, Excel, PPT, HTML, and Markdown files to merge content into a persistent reasoning-ready wiki.

What formats are supported for multimodal document ingestion into a reasoning graph?▼

Supported multimodal ingestion formats include PDF, images, videos, Word, Excel, PPT, HTML, and Markdown, turning diverse documents into a persistent, reasoning-ready knowledge base.

Related Skills

Explore More Content & Communication Skills→
beyonaibeyonai
45

by-doc-to-markdown

Convert PDF, Word, Excel, and PowerPoint documents into Markdown files.

Community
Intermediate
MRWillisTMRWillisT
7

frontend-slides

Generate zero-dependency HTML presentations and convert PPT/PPTX decks for browser viewing.

Community
Advanced
papachongpapachong
2

ai-ppt-generator

Generates PPT slides from a topic using Baidu AI APIs and templates.

Community
Intermediate
YesIamGodtYesIamGodt
38

data-pipeline

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

Community
Advanced