skills.rest
vanillaflava
vanillaflavaCOMMUNITY
Explore all skills by this author →
GitHub

wiki-ingest

Converts source files into structured wiki pages with cross-references.

59|8|Updated Apr 13, 2026
Search Tags:#knowledge management#information architecture#knowledge organization#wiki creation#source file processing
One-click install
npx skills add https://github.com/vanillaflava/llm-wiki-skills --skill wiki-ingest-vanillaflava
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wiki-ingest
Source: https://github.com/vanillaflava/llm-wiki-skills/tree/main/wiki-ingest
Command: npx skills add https://github.com/vanillaflava/llm-wiki-skills --skill wiki-ingest-vanillaflava

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdf2image, PyMuPDF, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the process of converting various source files into structured, interlinked wiki pages, enabling efficient knowledge management and easy access to information.

Core Features & Use Cases

  • Source File Processing: Automatically processes files from raw/ to generate wiki pages.
  • Thematic Assessment: Group and process files thematically for better synthesis.
  • Content Classification: Classifies sources as clippings, papers, documentation, articles, data, or notes for accurate archival.
  • Wiki Page Creation: Creates or updates existing wiki pages with extracted knowledge.
  • Backlinks and Cross-Referencing: Adds reciprocal links to related pages for a comprehensive knowledge graph.
  • Security & Privacy: Ensures safe handling of source content and prevents data exfiltration.
  • Use Case: Ideal for professionals and researchers who need to manage and organize their research notes, documentation, and other knowledge resources.

Quick Start

To process new source files into your wiki, run /wiki-ingest followed by the path to your source files, like /wiki-ingest /path/to/sources.

Frequently Asked Questions about wiki-ingest

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

FAQPage Schema
How do I automate converting source files into a structured knowledge wiki?▼

Automating source file ingestion into a structured knowledge wiki involves processing raw documents from a directory and classifying them thematically. The system extracts text from files like PDFs and generates interlinked wiki pages with backlinks for easy access.

What is the best way to organize research notes and documentation into an interlinked knowledge base?▼

Organizing research notes into an interlinked knowledge base requires classifying sources into categories like clippings, papers, or articles. The system then creates structured wiki pages and adds reciprocal cross-referencing links to build a comprehensive knowledge graph.

Do I need filesystem read and write access to process source files into wiki pages?▼

Yes, filesystem read and write access is required to process source files into wiki pages. The system needs to read files from a raw directory, extract content, and write or move the generated wiki pages to organize your knowledge base effectively.

Does wiki-ingest work with PDF documents for text extraction and knowledge organization?▼

Yes, wiki-ingest works with PDF documents for text extraction and knowledge organization by utilizing PyMuPDF and pdf2image dependencies. It can optionally extract text from PDFs and images using available vision tools to create structured wiki pages.

How does content classification help in creating a personal knowledge base from source files?▼

Content classification helps in creating a personal knowledge base by categorizing source files as clippings, papers, documentation, articles, data, or notes. This ensures accurate archival and thematic grouping for better synthesis and interlinked wiki page generation.

What are the limitations when processing images and PDFs for a structured wiki?▼

Limitations when processing images and PDFs for a structured wiki include dependency on available vision tools and PDF extraction utilities like PyMuPDF. Without these specific tools, the system cannot extract text from complex image-based or scanned documents.

Related Skills

Explore More Education & Research Skills→
MLMarioMLMario
8

kb-ingest

Orchestrate a multi-agent pipeline to ingest raw knowledge base materials into structured wiki pages.

Community
Advanced
matthew-johnsonmatthew-johnson

llm-wiki

Ingest and organize knowledge into a persistent, interlinked Markdown wiki.

Community
Advanced
JansenAnalyticsJansenAnalytics
5

ocr-document

Convert unsearchable PDFs and images into searchable text and tables.

Community
Intermediate
MuchunpengMuchunpeng

paper-organizer

Organize research papers and draft structured Feishu knowledge documents.

Community
Intermediate