Notion logo

Notion

CommunityPopular
Anil-matcha
notion

Work with Notion: search pages, read page properties, query databases, create pages, append blocks, update page properties. Trigger phrases: notion, notion page, notion database.

Overview

PublisherAnil-matcha
Repositoryawesome-muse-connectors
Skill namenotion
Stars
1.4K
Forks
309
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Anil-matcha on GitHub. Read the source before you install it.

Installation

Install the Notion AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/notion
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git /tmp/awesome-muse-connectors
mkdir -p .claude/skills
cp -r /tmp/awesome-muse-connectors/connectors/notion .claude/skills/notion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Notion in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Notion on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Notion is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Notion

Purpose

Work with the user's Notion workspace: search pages and databases, read page properties, query databases, and write: create pages, append blocks to a page, and update page properties. Use when the user mentions Notion or wants something looked up or recorded in their Notion.

Tooling

All commands go through bin/notion.py:

bash
bin/notion.py auth                              # verify the connection (search with page_size 1)
bin/notion.py search --query "roadmap"           # search pages and databases
bin/notion.py page --id PAGE_ID                  # read a page's properties
bin/notion.py query-db --id DATABASE_ID          # query a database (first 20 rows)

# writes: every one requires the exact --confirm string the CLI prints
bin/notion.py page-create --parent-id PAGE_ID --properties '{"title":{"title":[{"text":{"content":"My note"}}]}}'
bin/notion.py page-create --parent-id DB_ID --parent-type database --properties '{"Name":{"title":[{"text":{"content":"New row"}}]}}'
bin/notion.py block-append --block-id PAGE_ID --blocks '[{"object":"block","type":"paragraph","paragraph":{"rich_text":[{"type":"text","text":{"content":"Hello"}}]}}}]'
bin/notion.py page-update --id PAGE_ID --properties '{"Status":{"status":{"name":"Done"}}}'

IDs are the 32-hex-character Notion IDs (with or without dashes). --properties uses the Notion API property object format (e.g. {"title": {"title": [...]}}), not flattened values.

Auth

  • Provider id: notion (credential is collected as custom.notion)
  • Collection: Notion internal integration token via the secure credential flow (credentials.request_api_access); create one at notion.so/my-integrations → New integration → copy the "Internal Integration Secret", then share the pages/databases you need with that integration inside Notion
  • Required scopes: n/a (integration capabilities are set at notion.so/my-integrations)
  • Allowed hosts: api.notion.com
  • Status check: bin/notion.py auth (must return "ok": true)

Operating Rules

  1. Reads need no confirmation. Every write (page-create, block-append, page-update) requires the exact-match --confirm string: run the command once without it, read the refused string from the output, confirm the effect with the user, then re-run with it.
  2. Notion rate-limits to ~3 requests/second; if a call returns 429, wait the Retry-After seconds and continue.
  3. Pages and databases must be explicitly shared with the integration inside Notion, or they will not appear in search results and writes to them will fail: if a known page is missing, tell the user to share it with the integration.
  4. Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/notion.py). Do not print, log, or transmit the token value.

Files

  • SKILL.md
  • bin/notion.py

Maturity

🧪 Draft: written from Notion's public API docs; not yet live-tested end-to-end. The write endpoints (page-create, block-append, page-update) are doc-built only: paths and bodies follow the public docs but have never been run against a real workspace.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Notion AI skill do?

Work with Notion: search pages, read page properties, query databases, create pages, append blocks, update page properties. Trigger phrases: notion, notion page, notion database.

Why use Notion on TypingMind?

Because you install it once and use it with any model. Notion is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Notion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/notion. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Notion?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Notion?

As many as you like. As long as a model supports skills, you can use Notion with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Notion AI skill free?

Yes. It is published on GitHub by Anil-matcha under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇