Skip to main content

notion-doc-reader

Use when a user provides Notion page links and asks to read page content, recursively read child pages, or verify Notion API access using official Notion API endpoints. This skill is read-only by default and portable across repositories.

설치로 이동

소스 정보

저장소
lexmount/website-skills
최근 소스 활동
2026년 5월 21일 13:27
감지된 SKILL.md 언어
영어
스타
1
포크
0

설치 방법

기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.

소스 파일 검토

설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.

파일 탐색기
3 개 파일

SKILL.md 표시 중

SKILL.md
소스 지침 · 읽기 전용 미리보기
name
notion-doc-reader
description
Use when a user provides Notion page links and asks to read page content, recursively read child pages, or verify Notion API access using official Notion API endpoints. This skill is read-only by default and portable across repositories.
# Notion Doc Reader Read Notion page content through official Notion API endpoints. This skill is portable: copying this directory to another repository preserves the workflow, scripts, and tests. ## Scope Use this skill for: - Reading a user-provided Notion page as markdown. - Recursively reading direct child pages. - Verifying that a local Notion internal integration token can read a page. - Producing a compact page tree summary for agent context. Do not use this skill for: - Deleting, trashing, archiving, erasing, or moving Notion content. - Updating Notion pages unless a separate write-oriented workflow is designed. - Replacing official Notion API / SDK surfaces with a custom runtime client. ## Requirements - `NOTION_ACCESS_TOKEN` in the environment or in a local `.env`. - Optional `NOTION_VERSION`; defaults to `2026-03-11`. - The Notion integration must have `Read content`. - The target page or a parent page must be shared with the integration. ## Read Workflow 1. Load token from local environment or `.env`. 2. Extract the page id from the user-provided Notion URL. 3. Read page markdown with: `GET /v1/pages/{page_id}/markdown`. 4. List page children with: `GET /v1/blocks/{page_id}/children?page_size=100`. 5. For every direct `child_page` block, repeat the same read flow until `--max-depth` or `--max-pages` is reached. Default traversal follows page hierarchy only. It does not deep-scan every non-page nested block because large pages can contain many nested blocks and make smoke tests slow or noisy. `--max-pages` defaults to `50` to avoid accidentally crawling a very wide workspace tree. ## Smoke Command ```bash python3 .ai/skills/notion-doc-reader/scripts/notion_read_smoke.py \ --env-file /path/to/.env \ --max-depth 3 \ --max-pages 50 \ "<notion-page-url>" ``` Output is JSON with page ids, titles, markdown character counts, Notion markdown truncation flags, optional `truncated_at_page_limit` page-limit flags, unknown block ids, and discovered child pages. The script does not print tokens or full page markdown. ## Verification Run the bundled unit tests: ```bash python3 .ai/skills/notion-doc-reader/scripts/test_notion_read_smoke.py ``` Run live read-only smoke only when a token and user-approved Notion page links are available: ```bash python3 .ai/skills/notion-doc-reader/scripts/notion_read_smoke.py \ --env-file /path/to/.env \ --max-depth 3 \ --max-pages 50 \ "<notion-page-url-1>" \ "<notion-page-url-2>" ```
GitHub에서 보기