skills.rest
evolution-foundation
evolution-foundationOFFICIAL
Explore all skills by this author →
WebsiteGitHub

knowledge-ingest

Ingest documents and URLs into a knowledge base with parsing, chunking, and embedding.

520|175|Updated Apr 8, 2026
Search Tags:#pdf#chunking#embedding#knowledge-base#document-ingestion#async-classification#url-indexing
One-click install
npx skills add https://github.com/evolution-foundation/evo-nexus --skill knowledge-ingest-evolution-foundation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: knowledge-ingest
Source: https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/knowledge-ingest
Command: npx skills add https://github.com/evolution-foundation/evo-nexus --skill knowledge-ingest-evolution-foundation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of turning documents and links into searchable, classified knowledge without manual indexing work.

Core Features & Use Cases

  • Automated ingestion pipeline: Uploads PDFs, DOCX, PPTX, XLSX, HTML, EPUB, images, or a URL, then runs parsing, chunking, embedding, and asynchronous classification.
  • Space + unit targeting: Places the ingested document into a specific knowledge space, optionally associating it to a unit_id and adding tags.
  • Operational feedback: Returns a document id and guides you through polling until the document is ready, including classification results when available.
  • Common use cases: Index course materials into Academy, add a web page to the knowledge base, or ingest a file path/URL after a user indicates ingestion intent.

Quick Start

Upload a file or URL to the knowledge base by running the knowledge-ingest skill with your file path or URL and the target space slug.

Frequently Asked Questions about knowledge-ingest

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

FAQPage Schema
How do I auto-index PDFs and webpages into a knowledge base?▼

Document ingestion supports PDFs, DOCX, PPTX, XLSX, HTML, EPUB, and images. You can also index webpages directly by providing a URL for asynchronous classification and embedding.

How does asynchronous classification work during URL indexing?▼

Asynchronous classification runs after URL indexing parses and chunks the webpage content. You poll the document status endpoint until completion, then retrieve the available classification results.

Can I index course materials into a specific knowledge space?▼

Yes, you can index course materials into a specific knowledge space by specifying the target space slug during upload. Optionally associate the content with a unit_id and add tags for organization.

What is the best way to add an ebook to a searchable knowledge base?▼

The best way to add an ebook to a searchable knowledge base is uploading the EPUB file to the documents endpoint in your target space. The pipeline handles parsing, chunking, and embedding automatically.

Does document ingestion support adding tags to indexed files?▼

Yes, document ingestion supports adding tags to indexed files. When uploading your document or URL to a specified space, you can include tags and optionally associate it with a unit_id for structured organization.

Related Skills

Explore More Education & Research Skills→
hendrax5hendrax5

bkend-storage

Manage backend file storage with RESTful endpoints and presigned URL workflows.

Community
Advanced
whiteboardevwhiteboardev

memory-retrieve

Classify user queries to retrieve memories via recent, keyword, or semantic search.

Community
Advanced
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced
Maximilien-aiMaximilien-ai

weave-ingest

Ingests PDFs, text files and images into vector databases via weave-cli pipelines with optional backup and chunking recommendations.

Official
Advanced