$ loading_
Manage Notion pages, content, data, and workflows via CLI and API.
This skill is classified as prompt-only and comes from a high-trust open-source GitHub repository, so the overall risk is low. The main caveat is that its README describes use of the official Notion CLI/API, login state, API tokens, and calls to official Notion endpoints; if implemented externally, those should be managed with standard least-privilege controls.
The README explicitly mentions `ntn login` and `NOTION_API_TOKEN`, indicating that the external tool may use Notion access tokens in practice. Although this skill itself is marked prompt-only and its metadata says 'no keys', the documentation conflicts with that metadata, so any token should be treated as sensitive and scoped minimally.
The documentation shows calls to the official Notion API at `https://api.notion.com/v1/...`, including files, search, comments, and Workers operations. The prompt-only skill itself does not automatically exfiltrate data, but if a user follows the documentation externally, page content, queries, files, and related data would be sent to Notion's official endpoints.
The system flags this skill as `prompt-only`, so the skill itself does not have permission to spawn local processes, execute scripts, or directly invoke system capabilities. Commands such as `npm install -g ntn` and `curl` in the README are third-party documentation only and should not be treated as actions automatically performed by the skill.
Based on the system checks, the skill itself does not directly read or write local files or account data. The README describes operations on Notion pages, data sources, file uploads, comments, and search, but those are capabilities of the external CLI/API and do not mean this prompt-only skill already has actual data-access privileges.
The source is an open-source GitHub repository with very high community adoption (about 377k stars), which materially lowers supply-chain risk and improves auditability. Minor caveats remain: the license is unspecified, maintenance status is unknown, and the repository name `openclaw/openclaw` does not exactly match the 'notion' skill name, so a final verification of repository-to-artifact correspondence is advisable before deployment.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "notion" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/skills/notion/SKILL.md 2. Save it as ~/.claude/skills/notion/SKILL.md 3. Reload skills and tell me it's ready
Use the Notion API to bulk-create pages in the 'Product Requirements' database for Project A, Project B, and Project C. Each page should include a title, owner, due date, and a Markdown-formatted requirement summary.
Multiple Notion pages are created automatically with structured properties and formatted body content.
Search the Notion workspace for pages, comments, and attachments related to 'quarterly review', extract key conclusions, and compile them into a one-page English summary.
A list of relevant content is returned, along with a readable one-page summary for quick review.
Sync external form submission data into a Notion database: create a record if it does not exist, or update status, notes, and uploaded file links if it does, then add a processing comment on the page.
Form data is automatically inserted or updated in Notion, with collaborative processing notes preserved.
Prefer official ntn CLI. Use curl only when ntn is unavailable or a raw request is clearer.
npm install -g ntn
ntn --version
ntn login
Script/headless auth:
export NOTION_API_TOKEN=secret_or_ntn_token
export NOTION_API_VERSION=2026-03-11
ntn api sets Authorization and Notion-Version automatically. It uses CLI login by default, or NOTION_API_TOKEN when set.
ntn doctor
ntn api ls
ntn api ls --json
ntn api v1/comments --help
ntn api v1/comments --spec -X POST
ntn api v1/comments --docs -X POST
Markdown-first helpers:
ntn pages get <page-id>
ntn pages get <page-id> --json
ntn pages create --parent page:<page-id> --content '# Title\n\nBody'
ntn pages create --parent data-source:<data-source-id> < page.md
ntn pages update <page-id> --content '# Updated'
ntn pages update <page-id> < page.md
ntn pages trash <page-id> --yes
Notes:
pages get prints Markdown with page properties as frontmatter.--content, stdin, or editor in a TTY.page:<id>, database:<id>, data-source:<id>.ntn api v1/pages.ntn datasources resolve <database-id>
ntn datasources resolve <database-id> --json
ntn datasources query <data-source-id>
ntn datasources query <data-source-id> --limit 50 --json
ntn datasources query <data-source-id> --sort 'Date desc'
ntn datasources query <data-source-id> --filter '{"property":"Done","checkbox":{"equals":true}}'
Use resolve when you have a database ID. Query needs a data source ID.
ntn api v1/users/me
ntn api v1/search query=roadmap page_size:=10
ntn api v1/pages 'parent[data_source_id]='"$DS_ID" 'properties[Name][title][0][text][content]=New item'
ntn api "v1/pages/$PAGE_ID" -X PATCH in_trash:=true
ntn api "v1/blocks/$PAGE_ID/children" -X PATCH \
'children[0][type]=paragraph' \
'children[0][paragraph][rich_text][0][text][content]=Hello'
Input syntax:
path=value: string body field.path:=json: typed JSON body field.name==value: query parameter.Header:Value: request header.--data '<json>' or stdin JSON for larger bodies.ntn files create < image.png
ntn files create --filename photo.png --content-type image/png < /tmp/photo
ntn files create --external-url https://example.com/photo.png
ntn files get <upload-id>
ntn files list
ntn workers new
ntn workers deploy
ntn workers list --json
ntn workers runs list --json
ntn workers runs logs <run-id>
Workers may require Business/Enterprise plan and workspace enablement.
curl -sS "https://api.notion.com/v1/users/me" \
-H "Authorization: Bearer $NOTION_API_TOKEN" \
-H "Notion-Version: 2026-03-11" \
-H "Content-Type: application/json"
2026-03-11.in_trash, not archived.position, not flat after.transcription block renamed to meeting_notes.data_source_id.Verify an OpenClaw release is fully published and working across all channels.
Fetch GitHub issues, create fixes, open PRs, and handle reviews.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Regenerate OpenClaw release changelog sections from Git history before releases.
Prepare and verify OpenClaw stable or beta releases and release notes.
Create and review technical docs and agent instruction files in repositories.
Connect to Notion to query databases, create pages, and manage workspace content in bulk.
Turn Notion task databases into an automated intelligent task management system.
Use natural language to manage Notion pages, calendars, and expense tracking.
Research across Notion sources and produce cited, structured briefs and reports.
Use natural language to search, update, and manage Notion workspace content.
Turn chats and decisions into structured Notion wiki pages and linked documentation.