skills/bltgv/notion-api/SKILL.md
This skill should be used when the user asks to "search Notion", "find in Notion", "search my Notion workspace", "create Notion page", "make a Notion page", "update Notion page", "edit Notion page", "query Notion database", "get Notion database", "read Notion page", "get page content from Notion", "list Notion pages", or mentions Notion integration, Notion workspace, or Notion API access.
npx skillsauth add aiskillstore/marketplace notion-apiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Access Notion pages, databases, and content through TypeScript scripts executed via Bun.
This skill provides access to the Notion API for:
All scripts return JSON and require a NOTION_TOKEN environment variable.
All scripts output JSON with a consistent structure:
{"status": "success", "data": {...}}
{
"status": "auth_required",
"message": "Set NOTION_TOKEN environment variable with your integration token...",
"setupUrl": "https://www.notion.so/my-integrations"
}
When you receive auth_required, display to the user:
To access Notion, you need to set up an integration:
1. Go to: https://www.notion.so/my-integrations
2. Create a new integration for your workspace
3. Copy the "Internal Integration Secret"
4. Set the NOTION_TOKEN environment variable with this token
5. Share your pages/databases with the integration (click "..." menu > "Add connections")
Let me know when you've completed setup.
{"status": "error", "error": "Error description"}
Search for pages and databases across your Notion workspace.
All scripts are located at ${CLAUDE_PLUGIN_ROOT}/skills/notion/scripts/.
# Search for pages/databases matching a query
bun run ${CLAUDE_PLUGIN_ROOT}/skills/notion/scripts/search.ts --query "meeting notes"
# Search only pages
bun run search.ts --query "project" --filter page
# Search only databases
bun run search.ts --filter database --top 20
# List all accessible items (no query)
bun run search.ts --top 10
Get, create, and update Notion pages.
bun run ${CLAUDE_PLUGIN_ROOT}/skills/notion/scripts/pages.ts get --id <page-id>
# Create as child of another page
bun run pages.ts create --parent-id <page-id> --title "New Page"
# Create as child of another page with icon
bun run pages.ts create --parent-id <page-id> --title "New Page" --icon "📝"
# Create as database entry
bun run pages.ts create --parent-id <database-id> --parent-type database --title "New Entry"
# Create database entry with properties
bun run pages.ts create --parent-id <db-id> --parent-type database --title "Task" \
--properties '{"Status": {"select": {"name": "To Do"}}, "Priority": {"select": {"name": "High"}}}'
# Update title
bun run pages.ts update --id <page-id> --title "Updated Title"
# Update icon
bun run pages.ts update --id <page-id> --icon "🎉"
# Archive page
bun run pages.ts update --id <page-id> --archived true
# Restore archived page
bun run pages.ts update --id <page-id> --archived false
# Update database page properties
bun run pages.ts update --id <page-id> --properties '{"Status": {"select": {"name": "Done"}}}'
Query and get information about Notion databases.
bun run ${CLAUDE_PLUGIN_ROOT}/skills/notion/scripts/databases.ts get --id <database-id>
Returns the database title, description, and all property definitions.
# Query all entries
bun run databases.ts query --id <database-id>
# Query with limit
bun run databases.ts query --id <db-id> --top 20
# Query with filter
bun run databases.ts query --id <db-id> --filter '{"property": "Status", "select": {"equals": "Done"}}'
# Query with multiple conditions (AND)
bun run databases.ts query --id <db-id> --filter '{"and": [
{"property": "Status", "select": {"equals": "In Progress"}},
{"property": "Priority", "select": {"equals": "High"}}
]}'
# Query with sorting
bun run databases.ts query --id <db-id> --sorts '[{"property": "Created", "direction": "descending"}]'
# Sort by last edited time
bun run databases.ts query --id <db-id> --sorts '[{"timestamp": "last_edited_time", "direction": "descending"}]'
# Text contains
--filter '{"property": "Name", "rich_text": {"contains": "project"}}'
# Checkbox is checked
--filter '{"property": "Done", "checkbox": {"equals": true}}'
# Date is after
--filter '{"property": "Due Date", "date": {"after": "2024-01-01"}}'
# Number greater than
--filter '{"property": "Score", "number": {"greater_than": 80}}'
# OR conditions
--filter '{"or": [
{"property": "Status", "select": {"equals": "Done"}},
{"property": "Status", "select": {"equals": "Archived"}}
]}'
Read page content as blocks.
# Get blocks from a page
bun run ${CLAUDE_PLUGIN_ROOT}/skills/notion/scripts/blocks.ts list --id <page-id>
# Get blocks with limit
bun run blocks.ts list --id <page-id> --top 100
# Get blocks recursively (includes nested content)
bun run blocks.ts list --id <page-id> --recursive
bun run blocks.ts get --id <block-id>
Blocks can be: paragraph, heading_1, heading_2, heading_3, bulleted_list_item, numbered_list_item, to_do, toggle, code, quote, callout, divider, table, image, bookmark, and more.
Each block includes:
id: Block identifiertype: Block typecontent: Text content (if applicable)hasChildren: Whether block has nested blockschildren: Nested blocks (when using --recursive)export NOTION_TOKEN=secret_xxxxx
| Script | Purpose |
|--------|---------|
| search.ts | Search pages and databases across workspace |
| pages.ts | Get, create, update pages |
| databases.ts | Get database schema, query entries |
| blocks.ts | Read page content as blocks |
For detailed API reference, see:
references/notion-api.md - Notion API endpoints and parametersdevelopment
Apple Human Interface Guidelines for content display components. Use this skill when the user asks about charts component, collection view, image view, web view, color well, image well, activity view, lockup, data visualization, content display, displaying images, rendering web content, color pickers, or presenting collections of items in Apple apps. Also use when the user says how should I display charts, what's the best way to show images, should I use a web view, how do I build a grid of items, what component shows media, or how do I present a share sheet. Cross-references: hig-foundations for color/typography/accessibility, hig-patterns for data visualization patterns, hig-components-layout for structural containers, hig-platforms for platform-specific component behavior.
tools
Automate HelpDesk tasks via Rube MCP (Composio): list tickets, manage views, use canned responses, and configure custom fields. Always search tools first for current schemas.
testing
Expert Haskell engineer specializing in advanced type systems, pure functional design, and high-reliability software. Use PROACTIVELY for type-level programming, concurrency, and architecture guidance.
tools
GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo/urql. Key insight: GraphQL is a contract. The schema is the API documentation. Design it carefully.