Token导航 LogoToken导航

Agent Skill · 研究检索

notion-enhanced-markdown(Notion enhanced Markdown 搜索)

用于处理 Notion 页面、数据库、工作区内容和结构化记录。它适合让 Agent 查询知识库、整理页面内容、创建记录或把外部信息同步到 Notion。使用时需要确认集成是否已被授权到目标页面或数据库,并区分读取、追加和覆盖更新;涉及批量写入或修改数据库属性时,应先核对字段名称、属性类型和目标页面。

notion-enhanced-markdown 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 32,766。

总安装 2,471周安装 104GitHub Stars 1下载 865核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:notion-enhanced-markdown(Notion enhanced Markdown 搜索)
来源仓库:https://github.com/fental/notion-enhanced-markdown
安装命令:
openclaw skills install notion-enhanced-markdown
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install notion-enhanced-markdown

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

notion-enhanced-markdown 扩展了 Notion API 对 Markdown 的支持,支持块级内容管理。适用于 OpenClaw 中需要混合使用 Markdown 语法与 Notion 原生块结构的场景。通过 clawhub 安装后,Agent 可利用其解析和渲染增强型 Markdown 内容。

使用前应确认目标页面支持富文本格式,避免兼容性问题。建议结合模板使用,确保输出符合 Notion 的块模型规范。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install notion-enhanced-markdown;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

notion-enhanced-markdown 怎么安装?

在终端执行 openclaw skills install notion-enhanced-markdown。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

notion-enhanced-markdown 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

notion-enhanced-markdown 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

notion-enhanced-markdown 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

notion-enhanced-markdown 用的人多吗?

公开数据是累计安装 2,471 次,近一周安装 104 次,下载 865 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

notion-enhanced-markdown 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
notion-enhanced-markdown

Notion enhanced Markdown 搜索 · 本页

2,4711接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
notion
description
Notion API for creating and managing pages, databases, blocks and enhanced markdown.
homepage
https://developers.notion.com
metadata

notion

Use the Notion API to create/read/update pages, data sources (databases), and blocks.

Setup

  1. Create an integration at https://notion.so/my-integrations
  2. Copy the API key (starts with ntn_ or secret_)
  3. Store it:
mkdir -p ~/.config/notion
echo "ntn_your_key_here" > ~/.config/notion/api_key
  1. Share target pages/databases with your integration (click "..." → "Connect to" → your integration name)

API Basics

All requests need:

NOTION_KEY=$(cat ~/.config/notion/api_key)
curl -X GET "https://api.notion.com/v1/..." \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json"
Note: The Notion-Version header is required. This skill uses 2026-03-11 (latest). In this version, databases are called "data sources" in the API.

Common Operations

Search for pages and data sources:

curl -X POST "https://api.notion.com/v1/search" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{"query": "page title"}'

Get page:

curl "https://api.notion.com/v1/pages/{page_id}" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11"

Get page content (blocks):

For simple content access, prefer the Markdown API (GET /v1/pages/{page_id}/markdown). Use the blocks API only when you need low-level block data or unsupported block types.
curl "https://api.notion.com/v1/blocks/{page_id}/children" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11"

Create page in a data source:

curl -X POST "https://api.notion.com/v1/pages" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{
    "parent": {"database_id": "xxx"},
    "properties": {
      "Name": {"title": [{"text": {"content": "New Item"}}]},
      "Status": {"select": {"name": "Todo"}}
    }
  }'

Query a data source (database):

curl -X POST "https://api.notion.com/v1/data_sources/{data_source_id}/query" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{
    "filter": {"property": "Status", "select": {"equals": "Active"}},
    "sorts": [{"property": "Date", "direction": "descending"}]
  }'

Create a data source (database):

curl -X POST "https://api.notion.com/v1/data_sources" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{
    "parent": {"page_id": "xxx"},
    "title": [{"text": {"content": "My Database"}}],
    "properties": {
      "Name": {"title": {}},
      "Status": {"select": {"options": [{"name": "Todo"}, {"name": "Done"}]}},
      "Date": {"date": {}}
    }
  }'

Update page properties:

curl -X PATCH "https://api.notion.com/v1/pages/{page_id}" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{"properties": {"Status": {"select": {"name": "Done"}}}}'

Add blocks to page:

curl -X PATCH "https://api.notion.com/v1/blocks/{page_id}/children" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{
    "children": [
      {"object": "block", "type": "paragraph", "paragraph": {"rich_text": [{"text": {"content": "Hello"}}]}}
    ]
  }'

Markdown Page Operations

Use the Markdown API to read and write page content as plain Markdown — no need to construct block JSON.

Create page with markdown:

curl -X POST "https://api.notion.com/v1/pages" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{
    "parent": {"page_id": "xxx"},
    "markdown": "# Meeting Notes\
\
Content here.\
\
- item 1\
- item 2"
  }'

Constraints:

  • markdown and children are mutually exclusive in the same request
  • If properties.title is omitted, the first # h1 heading becomes the page title
  • Requires insert_content capability on the parent
  • Only works for pages under a parent page (not a database)

Read page as markdown:

curl "https://api.notion.com/v1/pages/{page_id}/markdown" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11"

Response: { "object": "page_markdown", "id": "...", "markdown": "...", "truncated": false, "unknown_block_ids": [] }

  • Add ?include_transcript=true to include meeting transcripts
  • If truncated: true, fetch remaining blocks using the IDs in unknown_block_ids

Update page markdown:

# Search-and-replace (recommended)
curl -X PATCH "https://api.notion.com/v1/pages/{page_id}/markdown" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{
    "command": {
      "type": "update_content",
      "old_str": "old text",
      "new_str": "new text"
    }
  }'

# Full replacement
curl -X PATCH "https://api.notion.com/v1/pages/{page_id}/markdown" \
  -H "Authorization: Bearer $NOTION_KEY" \
  -H "Notion-Version: 2026-03-11" \
  -H "Content-Type: application/json" \
  -d '{
    "command": {
      "type": "replace_content",
      "new_str": "# New Title\
\
Replaced content."
    }
  }'

Two command types:

  • update_content — search-and-replace (old_str → new_str); fails with validation_error if old_str appears multiple times (add "replace_all_matches": true to override)
  • replace_content — replaces all page content with new_str

Both commands return the full updated page markdown. Constraints:

  • Matching is case-sensitive
  • Operations that would delete child pages/databases are rejected unless "allow_deleting_content": true is set
  • Synced pages cannot be updated

Supported Block Types (Markdown)

Block TypeMarkdown Syntax
Paragraphplain text
Heading 1–4# through ####
Bulleted list item- item
Numbered list item1. item
To-do- [ ] / - [x]
Toggle<details><summary>…</summary>…</details>
Quote> quote
Callout<callout>…</callout>
Divider---
Code block `language … `
Equation$$ equation $$
Table<table><tr><td>…</td></tr></table>
Image![caption](url)
File / Video / Audio / PDF<file src="url">caption</file>
Child page<page url="…">title</page>
Columns<columns><column>…</column></columns>

Unsupported block types render as <unknown url="..." alt="block_type"/> placeholder tags.

Property Types

Common property formats for database items:

  • Title: {"title": [{"text": {"content": "..."}}]}
  • Rich text: {"rich_text": [{"text": {"content": "..."}}]}
  • Select: {"select": {"name": "Option"}}
  • Multi-select: {"multi_select": [{"name": "A"}, {"name": "B"}]}
  • Date: {"date": {"start": "2024-01-15", "end": "2024-01-16"}}
  • Checkbox: {"checkbox": true}
  • Number: {"number": 42}
  • URL: {"url": "https://..."}
  • Email: {"email": "a@b.com"}
  • Relation: {"relation": [{"id": "page_id"}]}

Key Differences in 2026-03-11

  • Databases → Data Sources: Use /data_sources/ endpoints for queries and retrieval
  • Two IDs: Each database now has both a database_id and a data_source_id

- Use database_id when creating pages (parent: {"database_id": "..."}) - Use data_source_id when querying (POST /v1/data_sources/{id}/query)

  • Search results: Databases return as "object": "data_source" with their data_source_id
  • Parent in responses: Pages show parent.data_source_id alongside parent.database_id
  • Finding the data_source_id: Search for the database, or call GET /v1/data_sources/{data_source_id}

Notes

  • Page/database IDs are UUIDs (with or without dashes)
  • The API cannot set database view filters — that's UI-only
  • Rate limit: ~3 requests/second average, with 429 rate_limited responses using Retry-After
  • Append block children: up to 100 children per request, up to two levels of nesting in a single append request
  • Payload size limits: up to 1000 block elements and 500KB overall
  • Use is_inline: true when creating data sources to embed them in pages
  • markdown field in create/update is mutually exclusive with children
  • Markdown pages exceeding ~20,000 blocks will have truncated: true; fetch remaining content using block IDs in unknown_block_ids
  • All string matching in update_content is case-sensitive
  • In-page `\

` must be actual newlines in JSON; use single quotes in cURL

平台分布

OpenClaw

76.92%
按下载量换算665

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills