notcrawl

SkillWeb & browsing

Lets your agent search and query a local archive of your Notion pages, including read-only SQL and Markdown export.

Then ask your AI: use the notcrawl skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.

No other account needed.

Add it as a step in a pipeline you build on Ahel, or connect Ahel to Claude, ChatGPT, Cursor, Claude Code or Codex and ask your AI to use it.

About this skill

Notion archive: desktop/API sync, Markdown export, page search, read-only SQL.

What this skill tells your AI

The instructions your AI receives, as published by steipete/agent-scripts in skills/notcrawl/SKILL.md and read by Ahel’s review.

Use this for local Notion archive questions. Desktop reads local cache; API sync needs NOTION_TOKEN and page access.

notcrawl doctor
notcrawl status
notcrawl sync --source desktop

Use API only when needed and credentials/page access are available:

notcrawl sync --source api

Check freshness for recent/current Notion questions.
Search pages first; use read-only SQL for exact counts or schema-level analysis.
Use export-md when the user needs Markdown files refreshed.
Report date spans, page/database IDs, counts, and source limits.

Use root or subcommand help for syntax: notcrawl --help, notcrawl search --help, notcrawl sql --help.

Common commands:

notcrawl search --limit 20 "query"
notcrawl databases
notcrawl sql "select count(*) from pages;"
notcrawl export-md

Advanced