Skip to content

BuilderIO/agent-native / templates/analytics/.builder/skills/notion

notion

Verified

Access the Notion content calendar and page data for editorial planning. Use this skill when the user asks about the content calendar, blog planning, or editorial schedule.

FileKindSize
SKILL.mdskill md1.7 KB
---
name: notion
description: >
  Access the Notion content calendar and page data for editorial planning.
  Use this skill when the user asks about the content calendar, blog planning, or editorial schedule.
---

# Notion Integration

## Connection

- **Base URL**: `https://api.notion.com/v1`
- **Auth**: `Authorization: Bearer $NOTION_API_KEY`, `Notion-Version: 2022-06-28`
- **Env vars**: `NOTION_API_KEY`
- **Caching**: 10-minute cache for content calendar and individual pages
- **Content DB**: `db4ae46c822443ba96e51a6a352e0fbe` (hard-coded)

## Server Lib

- **File**: `server/lib/notion.ts`

### Exported Functions

| Function                     | Description                                          |
| ---------------------------- | ---------------------------------------------------- |
| `getContentCalendar()`       | Fetch all entries from the content calendar database |
| `getNotionPage(pageId)`      | Fetch a page with its block content (recursive)      |
| `getContentCalendarSchema()` | Get the database schema/properties                   |

## Agent Actions

- `content-calendar` — fetch content calendar entries
- `content-calendar-schema` — fetch the database schema/properties
- `notion-page --pageId <id>` — fetch a page with block content

Do not call `/api/notion/*` directly from the agent.

## Key Patterns & Gotchas

- Content calendar paginates via POST `/databases/:id/query` with `page_size: 100` and `start_cursor`
- `extractProp` handles all Notion property types (title, rich_text, select, multi_select, date, people, rollup, formula, etc.)
- `fetchBlocks` recurses to fetch children when `has_children` is true — can be expensive for deeply nested pages
- Database ID and API version are hard-coded
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall