skills.rest
zby
zbyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ingest

Ingest URLs or local files into a knowledge base with structured reports.

20|5|Updated Nov 18, 2025
Search Tags:#information retrieval#knowledge base#web scraping#ingestion#document analysis#content classification
One-click install
npx skills add https://github.com/zby/llm-do --skill ingest-zby
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ingest
Source: https://github.com/zby/llm-do/tree/main/project_claw/skills/ingest
Command: npx skills add https://github.com/zby/llm-do --skill ingest-zby

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of bringing external information (from URLs or files) into your knowledge base, classifying it, and identifying valuable connections.

Core Features & Use Cases

  • Automated Ingestion: Snapshots web pages, GitHub repos, or X/Twitter posts.
  • Knowledge Connection: Uses /connect to link new information to your existing knowledge graph.
  • Analysis & Reporting: Generates a structured .ingest.md report detailing classification, summary, connections, and actionable insights.
  • Use Case: You find an interesting research paper online. Use this Skill to ingest it, understand how it relates to your existing notes on AI ethics, and identify key findings you can use.

Quick Start

Ingest the web page at https://example.com/research-paper.

Frequently Asked Questions about ingest

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

FAQPage Schema
How do I ingest web pages and PDFs into a knowledge base for analysis?▼

To ingest web pages and PDFs into a knowledge base, snapshot the external source content, classify its type, and analyze semantic connections to generate a structured ingestion report detailing insights and relationships.

Can I snapshot GitHub repositories and X/Twitter posts for document classification?▼

Yes, you can snapshot GitHub repositories and X/Twitter posts for document classification. The ingestion process captures this external content, categorizes the source type, and identifies keyword connections to existing knowledge graph documents.

What is the best way to connect ingested external sources to an existing knowledge graph?▼

The best way to connect ingested external sources to an existing knowledge graph is by using a connect skill after snapshotting. This analyzes semantic and keyword relationships, linking the new information directly to your stored documents.

Does automated web scraping identify semantic connections to existing documents?▼

Yes, automated web scraping identifies semantic connections to existing documents. After snapshotting the external source, the ingestion process analyzes the content and links it to your knowledge base to generate a structured report.

How do I generate a structured ingestion report from external URLs?▼

You generate a structured ingestion report from external URLs by snapshotting the web content, classifying the source type, and analyzing semantic connections. This produces a detailed markdown file summarizing classification and actionable insights.

What file formats are supported for local file ingestion and analysis?▼

Supported file formats for local file ingestion include PDFs and web page content. The system snapshots these external data sources, classifies them, and identifies semantic connections to generate a structured ingestion report.

Related Skills

Explore More Content & Communication Skills→
lemonlqflemonlqf

summarize

Summarize content from URLs, local files, and YouTube videos.

Community
Intermediate
GodSpeedAIGodSpeedAI
1

knowledge-graph-query

Query SEA-Forge's Knowledge Graph via SPARQL to retrieve concepts and relationships.

Official
Intermediate
aivos-xieaivos-xie
1

llm-wiki

Parse Markdown documents into a structured knowledge base for cross-referencing and queries.

Community
Advanced
gatovillanogatovillano

retrieval-augmented-generation

Retrieve user-specific information via semantic search and knowledge graph analysis.

Community
Advanced