wiki-ingest-external-docs

Ingest external documents into an LLM-Wiki with SHA-256 deduplication.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/thisisqubika/ai-mast-challenge-promptazo --skill wiki-ingest-external-docs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wiki-ingest-external-docs
Source: https://github.com/thisisqubika/ai-mast-challenge-promptazo/tree/main/.claude/skills/wiki-ingest-external-docs
Command: npx skills add https://github.com/thisisqubika/ai-mast-challenge-promptazo --skill wiki-ingest-external-docs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the ingestion of external documents into the LLM-Wiki, ensuring that the knowledge base is continuously updated and enriched with external information.

Core Features & Use Cases

  • External Document Ingestion: Automates the process of ingesting documents like PDFs, DOCX, HTML, and more into the LLM-Wiki.
  • Content Addressing: Utilizes SHA-256 for content addressing to ensure immutability and deduplication.
  • Metadata Extraction: Extracts metadata such as subject, service, and authoritativeness to enrich the knowledge base.
  • Use Case: For a software development team, this Skill can automatically ingest technical specifications and documentation, keeping the team's knowledge base up-to-date.

Quick Start

Use the wiki-ingest-external-docs skill to ingest a new document 'new-spec.pdf' into the LLM-Wiki.

Frequently Asked Questions about wiki-ingest-external-docs

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

FAQPage Schema
How do I automate external document ingestion into a knowledge base?

Automating external document ingestion into a knowledge base requires a structured pattern to handle various document types, extract metadata, and ensure content immutability. This Skill automates that entire process for the LLM-Wiki.

What is the best way to ingest PDFs and DOCX files into an LLM-Wiki?

The best way to ingest PDFs and DOCX files into an LLM-Wiki is using an automated ingestion pattern that handles document conversion and extracts metadata like subject and authoritativeness to enrich the knowledge base.

How does content addressing work for document deduplication in a knowledge base?

Content addressing for document deduplication uses SHA-256 hashes to ensure content immutability. This mechanism prevents duplicate documents from being ingested into the LLM-Wiki knowledge base.

Can I extract metadata like subject and authoritativeness during document ingestion?

Yes, you can extract metadata like subject, service, and authoritativeness during document ingestion. This Skill automatically extracts these metadata fields to enrich the LLM-Wiki knowledge base.

Do I need specific tools for document conversion to ingest external docs?

Yes, you need specific tools for document conversion and metadata extraction to ingest external docs. This Skill requires these tools to successfully automate the ingestion process into the LLM-Wiki.

Why should I use content addressing for my knowledge base updates?

You should use content addressing for knowledge base updates to ensure content immutability and deduplication. By utilizing SHA-256 hashing, the LLM-Wiki prevents duplicate entries and maintains data integrity.