knowledge-ingest

Name: knowledge-ingest
Availability: InStock
Author: Heretek-AI

Collect and structure knowledge from RSS feeds, webhooks, and APIs into SQLite.

Updated Mar 24, 2026

Search Tags:#github #webhooks #tagging #rss #data-ingestion #searxng #knowledge-ingest

Ready to run

npx skills add https://github.com/Heretek-AI/heretek-skills --skill knowledge-ingest

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: knowledge-ingest
Source: https://github.com/Heretek-AI/heretek-skills/tree/main/skills/knowledge-ingest
Command: npx skills add https://github.com/Heretek-AI/heretek-skills --skill knowledge-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates gathering and structuring external knowledge from RSS feeds, webhooks, SearXNG, GitHub, npm, and ClawHub into a centralized store, reducing manual curation for teams.

Core Features & Use Cases

Ingests data from multiple sources (SearXNG, GitHub Releases, npm Registry, ClawHub, arXiv, GHSA Advisories, and custom RSS) into a unified SQLite database
Parses, tags, scores relevance, and deduplicates entries to enable fast retrieval and downstream processing
Use cases include knowledge triage, proactive release monitoring, and trend analysis across sources

Quick Start

Initialize the knowledge ingest pipeline by connecting your sources and starting the fetch-parse-tag-score-store cycle.

Frequently Asked Questions about knowledge-ingest

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

FAQPage Schema

How do I automate RSS feed and GitHub release ingestion into a SQLite database?▼

Yes, knowledge ingestion from SearXNG, GitHub releases, npm, and custom RSS feeds is supported. The pipeline fetches, parses, tags, scores, and stores entries into a centralized SQLite database, covering GHSA advisories and ClawHub as well.

How does auto-tagging and scoring work for ingested knowledge entries?▼

You need a local SQLite database schema to initialize the knowledge ingest pipeline. Once configured, you connect your data sources and start the fetch-parse-tag-score-store cycle to automate gathering knowledge.

Can I monitor GHSA advisories and npm registry updates via webhooks?▼

Knowledge ingestion is best for knowledge triage, proactive release monitoring, and trend analysis across sources. It reduces manual curation for teams by automating the collection and structuring of data from RSS feeds, webhooks, and APIs.

Does this data ingestion pipeline deduplicate entries from arXiv and ClawHub?▼

The pipeline collects and structures knowledge from RSS feeds, webhooks, and APIs into a centralized SQLite store. It covers SearXNG, GitHub releases, npm registry, ClawHub, arXiv, and GHSA advisories to reduce manual curation.

What is the best way to aggregate arXiv and npm registry feeds for trend analysis?▼

The best way to aggregate arXiv and npm registry feeds for trend analysis is using an automated ingestion pipeline. It fetches, parses, tags, scores, and stores entries into a unified SQLite database, enabling fast retrieval and trend monitoring.