skills.rest
00PZ
00PZCOMMUNITY
Explore all skills by this author →
GitHub

web-article-adapter

Ingest web articles from RSS feeds into knowledge-base markdown with provenance metadata.

Updated Apr 18, 2026
Search Tags:#automation#readability#ingestion#deduplication#knowledge-base#rss#web-article
One-click install
npx skills add https://github.com/00PZ/oopz-inc --skill web-article-adapter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-article-adapter
Source: https://github.com/00PZ/oopz-inc/tree/main/companies/shoshin/skills/web-article-adapter
Command: npx skills add https://github.com/00PZ/oopz-inc --skill web-article-adapter

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingests blog posts, news articles, and long-form web content into a niche's knowledge base, enabling automated curation and up-to-date context.

Core Features & Use Cases

  • Ingest content from configured RSS feeds and URL patterns
  • Respect robots.txt and deduplicate by canonical URL
  • Output knowledge-base-ready markdown with provenance metadata
  • Use case: keep a niche knowledge base refreshed with the latest articles without manual copying

Quick Start

Enable the web-article adapter in your niche profile (knowledge_sources.web-article.enabled: true) and run the ingestion script to ingest articles.

Frequently Asked Questions about web-article-adapter

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

FAQPage Schema
How do I ingest web articles into a knowledge base automatically?▼

To ingest web articles automatically, configure RSS feeds and URL patterns in your niche profile, then run the ingestion script to pull content into your knowledge base with provenance metadata.

What is the best way to structure blog posts for a knowledge base?▼

Structuring blog posts for a knowledge base is done by ingesting long-form web content and outputting knowledge-base-ready markdown with provenance metadata, enforcing robots.txt and deduplicating by canonical URL.

Does web article ingestion respect robots.txt and handle deduplication?▼

Yes, web article ingestion enforces robots.txt rules and deduplicates content by canonical URL to prevent redundant entries in your niche knowledge base.

Can I use RSS feeds to keep a niche knowledge base refreshed with news content?▼

You can use configured RSS feeds to keep a niche knowledge base refreshed with the latest news content, enabling automated curation and up-to-date context without manual copying.

Do I need to configure URL patterns to ingest long-form web content?▼

You need to configure RSS feeds and URL patterns to ingest long-form web content, ensuring the ingestion script targets the correct sources for your knowledge base.

What format does ingested web content output as for a knowledge base?▼

Ingested web content outputs as knowledge-base-ready markdown with provenance metadata, ensuring structured and traceable articles for automated curation.

Related Skills

Explore More Data & Analytics Skills→
Varnan-TechVarnan-Tech
581

podcast-transcript-fetcher

Fetch, search, and analyze podcast transcripts via RSS feeds and APIs.

Official
Intermediate
rijnbrijnb
3

wiki-ingest

Convert raw notes, VTT, EML, and HTML files into Markdown with provenance metadata.

Community
Advanced
hepai-labhepai-lab
21

ragflow-knowledge

Ingest PDFs into a RAGFlow dataset with chunking and metadata enrichment.

Community
Advanced
zbyzby
82

cp-skill-ingest

Ingests URLs or Markdown files into a knowledge base and generates reports.

Community
Intermediate