gbrain-idea-ingest

Ingests web articles and links into gbrain with entity extraction and cross-linking.

1|Updated Jun 21, 2026
One-click install
npx skills add https://github.com/tapway/shogun-os --skill gbrain-idea-ingest-tapway
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gbrain-idea-ingest
Source: https://github.com/tapway/shogun-os/tree/main/skills/gbrain/gbrain-idea-ingest
Command: npx skills add https://github.com/tapway/shogun-os --skill gbrain-idea-ingest-tapway

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? External articles, tweets, and research papers often end up as isolated bookmarks that are never rediscovered. This Skill turns shared links into structured, summarized knowledge pages inside a gbrain knowledge graph, connected to the people, companies, and projects they mention. ## Core Features & Use Cases - Structured 8-step pipeline: Fetches content via web extraction, summarizes key points, extracts entities, deduplicates against the brain, and writes a formatted reference page. - Entity cross-linking: Searches gbrain for every mentioned person, company, or project and adds bidirectional links so new content is discoverable through the graph. - Use Case: A user shares a link to an article about AI pricing strategies. The Skill fetches the page, extracts the title, author, and key points, finds existing brain pages for the mentioned companies, writes a summary under references/pricing/, and links it from each entity page. ## Quick Start Save this article to the brain and link it to any people or companies it mentions: https://example.com/ai-pricing

Frequently Asked Questions about gbrain-idea-ingest

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

FAQPage Schema
How do I save a web article into a gbrain knowledge base?

Share the link and ask the agent to save or ingest it. The Skill fetches the page with web extraction, summarizes key points, writes a reference page under a topic folder, and cross-links mentioned entities.

How does entity cross-linking work when ingesting articles?

The pipeline scans content for people, companies, and projects, searches each against gbrain, then adds links from each matching entity page to the new reference page. Unknown entities get a minimal stub page first.

When should I use idea ingest instead of capture or media ingest?

Use idea ingest for external links, articles, and research papers. Use capture for the user's own original thoughts, gbrain-media-ingest for video, audio, or PDF files, and gbrain-ingest for bulk file imports.

Does the ingestion pipeline check for duplicate content?

Yes, the pipeline searches gbrain before writing to avoid duplicate entries. Skipping this dedup check is listed as a pitfall because it creates redundant pages in the brain.

What are the limitations of link-based knowledge ingestion?

It requires web extraction capability and gbrain MCP tools to be available. It does not handle media files like video or PDFs, and long copy-pastes without summarization are discouraged since the brain prefers condensed knowledge.