skills.rest
States-Media
States-MediaOFFICIAL
Explore all skills by this author →
GitHub

ingest

Extracts, classifies, and stores web articles as Markdown notes in Obsidian vaults.

Updated Apr 9, 2026
Search Tags:#article#knowledge#classification#web#ingest#obdian
One-click install
npx skills add https://github.com/States-Media/claude-code-starter --skill ingest-states-media
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ingest
Source: https://github.com/States-Media/claude-code-starter/tree/main/skills/ingest
Command: npx skills add https://github.com/States-Media/claude-code-starter --skill ingest-states-media

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of capturing and organizing external web content such as articles, papers, and blog posts directly into a structured Obsidian vault.

Core Features & Use Cases

  • Content Fetching: Retrieves webpage content via Jina AI Reader or Playwright fallback, ensuring reliable extraction.
  • Intelligent Classification: Determines the appropriate vault category based on the content’s business unit and domain for accurate filing.
  • Note Creation: Generates a rich, atomic Markdown note with detailed metadata, links, and summaries suitable for research or ongoing projects.
  • Update Knowledge Base: Integrates new notes into the corresponding namespace index, maintaining an organized knowledge ecosystem.
  • Use Case: Save a lengthy technical article to the vault, classify it correctly under tools/knowledge for future reference and context.

Quick Start

Give the URL of an article you want to save, such as "https://example.com/article", and I will fetch, classify, and add it to your Obsidian vault automatically.

Frequently Asked Questions about ingest

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

FAQPage Schema
How do I save web articles directly into my Obsidian vault for research?▼

Saving web articles into an Obsidian vault involves fetching the URL content, classifying it by domain, generating an atomic Markdown note with metadata, and updating the namespace index for organized research retrieval.

Does this web content ingestion tool work with Jina AI Reader and Playwright?▼

Web content ingestion uses Jina AI Reader for primary webpage extraction, with Playwright configured as a fallback fetcher to ensure reliable content retrieval when fetching articles for your Obsidian vault.

What is the best way to organize external research papers and blog posts in Markdown?▼

Organizing external research papers in Markdown is achieved through intelligent classification, which files content into appropriate vault categories and generates detailed metadata, links, and summaries for easy retrieval.

Can I automatically classify and file web content into specific knowledge categories?▼

You can automatically classify and file web content by determining the appropriate vault category based on the article's business unit and domain, ensuring accurate filing into namespaces like tools/knowledge.

How does the tool handle updating the namespace index when adding new notes?▼

When adding new notes, the tool updates the knowledge base by integrating the generated atomic Markdown note into the corresponding namespace index, maintaining an organized knowledge ecosystem for ongoing learning projects.

Related Skills

Explore More Education & Research Skills→
Matymatyk-businessMatymatyk-business
61

obsidian-vault-location

Locate Obsidian vault paths and retrieve notes and journal files.

Community
Intermediate
susamnsusamn

obsidian

Manage Obsidian vault notes and refactor links automatically.

Community
Intermediate
swaruplabswaruplab
94

markitdown

Convert PDFs, DOCX, PPTX, XLSX, HTML, and more into Markdown.

Community
Intermediate
fanguyunfanguyun

pake

Convert web pages into standalone desktop applications using Pake.

Community
Intermediate