agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/notion/SKILL.md

notion

Skill5 starsChanged 8 months agoMITView on GitHub

Manage Notion pages, databases, and blocks via the Notion API using curl. Use when user wants to create/read/update Notion pages, query databases, add content blocks, or search the Notion workspace.

  • Reads credentials
  • Installs packages
  • Sends data out

100 other projects use a version of this, 32 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use taskflow-inbox-triage, food-order and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • seedprodSkill

    food-order

    Reorder Foodora orders + track ETA/status with ordercli. Never confirm without explicit user approval. Triggers: order food, reorder, track ETA.

    Also in 6 projects that use this

  • seedprodSkill

    voice-call

    Start voice calls via the OpenClaw voice-call plugin.

    Also in 19 projects that use this

  • jiulingyunSkill

    BlueBubbles

    为Clawdbot构建或更新BlueBubbles外部通道插件(扩展包,REST发送/探测,webhook入站)。

    Also in 19 projects that use this

  • hkyutongSkill

    openclaw-release-maintainer

    Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.

    Also in 4 projects that use this

  • AtomicBot-aiSkill

    taskflow

    Also in 6 projects that use this

  • +4 more from seedprod

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 95 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No install needed beyond curl (pre-installed on macOS/Linux).

    line 26
  2. Distinctive:

    Create a new integration → copy the "Internal Integration Token"

    line 35
  3. Very specific:

    Always check that NOTION_API_KEY is set: [ -z "$NOTION_API_KEY" ] && echo "Not set"

    line 149
  4. Distinctive:

    If not set, guide the user to https://www.notion.so/my-integrations and stop

    line 150
  5. Distinctive:

    NEVER log or store the API key in memory or workspace files

    line 151
  6. Very specific:

    Always pipe curl output through jq.

    line 152
  7. Very specific:

    When reading page content, save long content to workspace/notion-<page-id>.md rather than displaying raw

    line 155
  8. Distinctive:

    Keep responses concise: confirm action in 1-2 lines and show the page title/URL

    line 156

“Common” is measured: kept by at least 6 in 10 of the 95 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Notion

Interact with Notion via the REST API using curl. No separate CLI install needed.

Prerequisites

No install needed beyond curl (pre-installed on macOS/Linux).

Set up credentials:

export NOTION_API_KEY="secret_xxxxxxxxxxxx"

Get your key:

  1. Go to https://www.notion.so/my-integrations
  2. Create a new integration → copy the "Internal Integration Token"
  3. Share target pages/databases with the integration (open in Notion → Share → invite integration)

Store in shell profile or in 1Password and inject via op run.

Commands

Base URL: https://api.notion.com/v1 Headers:

Authorization: Bearer $NOTION_API_KEY
Notion-Version: 2022-06-28
Content-Type: application/json

Search

curl -s -X POST "https://api.notion.com/v1/search" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" \
  -H "Content-Type: application/json" \
  -d '{"query": "<search term>"}' | jq '.results[] | {id: .id, title: .properties.title.title[0].plain_text}'

Pages

# Read a page
curl -s "https://api.notion.com/v1/pages/<PAGE_ID>" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28"

# Create a page
curl -s -X POST "https://api.notion.com/v1/pages" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" \
  -H "Content-Type: application/json" \
  -d '{
    "parent": {"page_id": "<PARENT_PAGE_ID>"},
    "properties": {
      "title": {"title": [{"text": {"content": "<Page Title>"}}]}
    }
  }'

# Update page title
curl -s -X PATCH "https://api.notion.com/v1/pages/<PAGE_ID>" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" \
  -H "Content-Type: application/json" \
  -d '{"properties": {"title": {"title": [{"text": {"content": "<New Title>"}}]}}}'

Blocks (Page Content)

# Read page blocks
curl -s "https://api.notion.com/v1/blocks/<PAGE_ID>/children" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" | jq '.results[] | {type: .type, text: .paragraph.rich_text[0].plain_text}'

# Append a paragraph block
curl -s -X PATCH "https://api.notion.com/v1/blocks/<PAGE_ID>/children" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" \
  -H "Content-Type: application/json" \
  -d '{
    "children": [{
      "object": "block",
      "type": "paragraph",
      "paragraph": {
        "rich_text": [{"type": "text", "text": {"content": "<Your text here>"}}]
      }
    }]
  }'

Databases

# Query a database
curl -s -X POST "https://api.notion.com/v1/databases/<DB_ID>/query" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" \
  -H "Content-Type: application/json" \
  -d '{}' | jq '.results[] | .properties'

# Query with filter
curl -s -X POST "https://api.notion.com/v1/databases/<DB_ID>/query" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" \
  -H "Content-Type: application/json" \
  -d '{"filter": {"property": "Status", "select": {"equals": "In Progress"}}}'

Usage Examples

Search for a page:

curl -s -X POST "https://api.notion.com/v1/search" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" \
  -H "Content-Type: application/json" \
  -d '{"query": "meeting notes march"}' | jq '.results[0] | {id, url}'

Create a new note under a parent page: Set PARENT_ID to your workspace page ID, then:

curl -s -X POST "https://api.notion.com/v1/pages" \
  -H "Authorization: Bearer $NOTION_API_KEY" \
  -H "Notion-Version: 2022-06-28" \
  -H "Content-Type: application/json" \
  -d '{"parent": {"page_id": "'$PARENT_ID'"}, "properties": {"title": {"title": [{"text": {"content": "My New Note"}}]}}}'

Rules

  • Always check that NOTION_API_KEY is set: [ -z "$NOTION_API_KEY" ] && echo "Not set"
  • If not set, guide the user to https://www.notion.so/my-integrations and stop
  • NEVER log or store the API key in memory or workspace files
  • Always pipe curl output through jq; install with brew install jq if needed
  • Page IDs are 32-char hex strings (with or without dashes) — extract from Notion URLs
  • Remind the user to share the page/database with the integration if getting 404 errors
  • When reading page content, save long content to workspace/notion-<page-id>.md rather than displaying raw
  • Keep responses concise: confirm action in 1-2 lines and show the page title/URL

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.