notion-ingest

Crawl Notion pages, databases, and blocks into structured knowledge and raw markdown.

16|7|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/ai-analyst-lab/ai-analyst-plus --skill notion-ingest
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: notion-ingest
Source: https://github.com/ai-analyst-lab/ai-analyst-plus/tree/main/.claude/skills/notion-ingest
Command: npx skills add https://github.com/ai-analyst-lab/ai-analyst-plus --skill notion-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Crawls a Notion workspace to extract business terms, metrics, product documentation, and team structure, then populates the organization knowledge system. Use this skill whenever the user mentions importing from Notion, connecting to a Notion workspace, syncing Notion docs, extracting business context from Notion, pulling in team documentation, ingesting company knowledge, importing glossaries or metrics from Notion, or wants to bootstrap the knowledge system from existing Notion pages. Also trigger when the user asks about organizational context and mentions they use Notion for documentation. This skill handles full workspace crawls, specific database or page tree crawls, and incremental updates. It automatically classifies pages into glossary terms, metrics, products, objectives, or teams, and saves all content as structured knowledge plus raw markdown for query archaeology. Use this even if the user doesn't explicitly say "/notion-ingest" — any request to "import our team's Notion docs", "sync our product roadmap from Notion", "pull in our metric definitions from Notion", or "I have all our context in Notion, can you use it?" should trigger this skill.

Core Features & Use Cases

  • Crawls Notion workspaces to surface glossary terms, metrics, products, objectives, and teams, storing both structured knowledge and raw markdown for archaeology.
  • Automatically classifies pages into knowledge categories and populates the organization knowledge system, enabling faster context retrieval and onboarding.
  • Supports full workspace crawls, targeted page or database crawls, and incremental updates to keep knowledge fresh with minimal overhead.

Quick Start

Run /notion-ingest to start crawling your Notion workspace and populate your organization knowledge system.

Frequently Asked Questions about notion-ingest

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

FAQPage Schema
How do I automatically extract and classify business metrics from a Notion workspace?

You can automatically extract and classify business metrics from Notion by crawling workspace pages, databases, and blocks to convert them into structured knowledge plus raw markdown. The system automatically categorizes pages into glossary terms, metrics, products, objectives, or teams.

Can I import specific Notion databases into my knowledge system instead of a full workspace crawl?

Yes, you can import specific Notion databases or page trees instead of a full workspace crawl. The ingestion process supports targeted page or database crawls to selectively populate your organization knowledge system with relevant content.

What is the best way to keep my organizational knowledge base synced with updates in Notion?

The best way to keep knowledge synced with Notion updates is by using incremental updates. This feature crawls modified Notion content and updates glossary terms, metrics, products, objectives, and teams with minimal overhead to maintain freshness.

Does crawling Notion pages preserve the raw markdown for future reference?

Yes, crawling Notion pages preserves raw markdown for future reference. The system saves all ingested content as structured knowledge classifications alongside the original raw markdown format within the .knowledge hierarchy for query archaeology.

How do I bootstrap a knowledge system from existing company documentation stored in Notion?

To bootstrap a knowledge system from company documentation in Notion, run a full workspace crawl to extract team structure, product documentation, and business terms. This populates the organization knowledge system automatically by classifying pages into defined categories.