Token导航 LogoToken导航

Agent Skill · 研究检索

mowenskill-publish(莫文斯基尔出版)

mowenskill-publish 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

mowenskill-publish 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 30,083。

总安装 2,940周安装 125GitHub Stars 公开资料未说明下载 1,030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
1.0.2

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:mowenskill-publish(莫文斯基尔出版)
来源仓库:https://github.com/jacobluo/mowenskill-publish
安装命令:
openclaw skills install mowenskill-publish
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 mowenskill-publish

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。

在 Mowen(墨问)平台上发布或更新笔记,支持富文本与多媒体嵌入。适合需要快速沉淀想法、分享观点或维护知识库的用户场景。用户说出“发布注释”或“写一条 mowen”即可启动发布流程。安装命令:openclaw skills install mowenskill-publish,依赖有效的 OAuth 认证机制。

适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

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 mowenskill-publish;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

mowenskill-publish 怎么安装?

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

mowenskill-publish 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。

mowenskill-publish 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。

mowenskill-publish 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。

mowenskill-publish 用的人多吗?

公开数据是累计安装 2,940 次,近一周安装 125 次,下载 1,030 次。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。

mowenskill-publish 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
mowenskill-publish

莫文斯基尔出版 · 本页

2,940—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
mowen-note-publisher
description
Publish, edit, or configure notes on Mowen (墨问) via Open API. Use when user mentions 墨问, mowen, 发布笔记, publish note, or wants to create social-media-style notes with rich text and images.
dependencies
python>=3

墨问笔记发布 (Mowen Note Publisher)

Overview

Publish rich-text notes (text, images, formatting) to 墨问 via its Open API. This skill covers three operations: creating new notes, editing existing notes (API-created only), and modifying note settings (privacy, sharing, expiration). A Python script (scripts/publish_note.py) handles all API calls, image uploads, and NoteAtom construction with zero third-party dependencies.

Prerequisites

  • API Key: Obtain from 墨问小程序 → 我的 → 设置 → 开放平台 → 创建 API Key
  • Environment: Set MOWEN_API_KEY environment variable, or pass via --api-key argument
  • Python 3: Required for running the publish script (macOS has it pre-installed)

Workflow Decision Tree

User Request
    │
    ├── "发布/创建笔记" or "publish note"
    │   └── ACTION: create
    │       ├── Has images? → Upload images first (see Image Handling)
    │       ├── Build input JSON with paragraphs, tags, autoPublish
    │       └── Run: publish_note.py --action create
    │
    ├── "编辑/修改笔记内容" or "edit note"
    │   └── ACTION: edit (requires noteId from previous create)
    │       ├── ⚠️ Only API-created notes can be edited
    │       ├── Build input JSON with new paragraphs
    │       └── Run: publish_note.py --action edit --note-id <ID>
    │
    └── "修改笔记设置/隐私" or "change note settings"
        └── ACTION: settings (requires noteId)
            └── Run: publish_note.py --action settings --note-id <ID> --privacy <N>

Creating a Note (Step by Step)

1. Gather Content from User

Collect the note content. Identify:

  • Text paragraphs (plain text or rich text with bold/highlight/links)
  • Images (local file paths or URLs)
  • Tags (optional, max 10, each ≤ 30 chars)
  • Whether to auto-publish (default: draft)
  • Privacy setting (default: public)

2. Prepare Input JSON

Build a JSON object following this schema:

{
  "paragraphs": [
    "Plain text paragraph",
    [{"text": "Bold text", "bold": true}, " and normal text"],
    {"type": "heading", "level": 1, "text": "Title"},
    {"type": "image", "src": "https://example.com/photo.jpg"},
    {"type": "image", "src": "/path/to/local/photo.jpg", "width": 1080, "height": 720},
    {"type": "blockquote", "text": "A quote"},
    {"type": "bulletList", "items": ["Item 1", "Item 2"]},
    {"type": "orderedList", "items": ["First", "Second"]}
  ],
  "tags": ["tag1", "tag2"],
  "autoPublish": true,
  "privacyType": 1
}

Paragraph types:

TypeFormatDescription
Plain text"string"Simple text paragraph
Rich text[{...}, ...]Array of text items with optional bold, highlight, link
Heading{"type":"heading", "level":1, "text":"..."}h1-h6 heading
Image{"type":"image", "src":"..."}Image (URL, local path, or fileId)
Quote{"type":"blockquote", "text":"..."} or {"type":"quote", "text":"..."}Block quote
Bullet list{"type":"bulletList", "items":["..."]}Unordered list
Ordered list{"type":"orderedList", "items":["..."]}Numbered list
Raw node{"type":"raw", "node":{...}}Direct NoteAtom node passthrough

Privacy types: public = public, private = self-only, rule = custom rules (with noShare/expireAt)

3. Save Input and Run Script

Save the JSON to a temporary file and execute:

python {SKILL_DIR}/scripts/publish_note.py --action create --input /tmp/note_input.json

Or pipe directly via stdin:

echo '<json>' | python {SKILL_DIR}/scripts/publish_note.py --action create

The script outputs a JSON result with noteId on stdout. Save this noteId — it is needed for subsequent edit or settings operations.

4. Report Result

Inform the user of the created note's ID and status (draft vs published).

Editing a Note

⚠️ Limitation: Only notes created via the API can be edited. Notes created in the 墨问 mini-program cannot be edited through this API.

To edit, provide the noteId (from a previous create) and new content:

python {SKILL_DIR}/scripts/publish_note.py --action edit --note-id <NOTE_ID> --input /tmp/note_edit.json

The input JSON format is identical to creation (the paragraphs field). The entire note content will be replaced.

Modifying Note Settings

To change privacy, sharing, or expiration settings:

# Set to private
python {SKILL_DIR}/scripts/publish_note.py --action settings --note-id <NOTE_ID> --privacy private

# Set to public
python {SKILL_DIR}/scripts/publish_note.py --action settings --note-id <NOTE_ID> --privacy public

# Set custom rule: forbid sharing with expiration
python {SKILL_DIR}/scripts/publish_note.py --action settings --note-id <NOTE_ID> --privacy rule --no-share --expire-at 1735689600

Image Handling

The script automatically handles images found in paragraphs:

  • URL images (http:// or https://): Uploaded via remote upload API (< 30MB)
  • Local file paths: Uploaded via local upload API (< 50MB, formats: gif/jpeg/jpg/png/webp)
  • Existing fileId: Passed through directly (no upload needed)

Image upload is automatic — simply include image entries in the paragraphs array and the script handles the rest. Optionally provide width and height for better rendering.

Rate limiting (1 req/sec) is automatically enforced between API calls.

API Reference

For complete API documentation including endpoint details, NoteAtom structure specification, request/response examples, and error codes, refer to:

📄 references/mowen_api.md

Key search patterns for the reference file:

  • ## 1. 笔记创建 — Create endpoint details
  • ## 2. 笔记编辑 — Edit endpoint details
  • ## 3. 笔记设置 — Settings endpoint details
  • ## 4. NoteAtom 结构定义 — Full NoteAtom schema with all node types
  • ## 5. 图片上传 — Image upload (local + remote) procedures
  • ## 7. 限频与配额汇总 — Rate limits and daily quotas

Common Use Cases

Publish a simple text note

{
  "paragraphs": [
    "今天天气真好,适合出门散步 ☀️"
  ],
  "tags": ["日常", "心情"],
  "autoPublish": true
}

Publish a note with images and formatting

{
  "paragraphs": [
    {"type": "heading", "level": 1, "text": "周末探店记录"},
    "今天去了一家超棒的咖啡店!",
    {"type": "image", "src": "https://example.com/coffee.jpg"},
    [{"text": "拿铁", "bold": true}, "味道超赞,推荐指数 ⭐⭐⭐⭐⭐"],
    {"type": "image", "src": "/Users/me/photos/cake.jpg", "width": 1080, "height": 1080},
    {"type": "blockquote", "text": "生活需要一点甜"},
    {"type": "bulletList", "items": ["环境优雅", "咖啡好喝", "甜品精致"]}
  ],
  "tags": ["探店", "咖啡", "美食"],
  "autoPublish": true
}

Edit a previously created note

# Original creation returned noteId = "note_abc123"
python publish_note.py --action edit --note-id note_abc123 --input updated_content.json

Make a note private

python publish_note.py --action settings --note-id note_abc123 --privacy private

平台分布

OpenClaw

89.14%
按下载量换算918

安全审计

VirusTotal

通过

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