Xiaohongshu Publish
使用 OpenClaw 浏览器发布小红书笔记(图文/视频)。当用户需要发布小红书笔记时使用此 skill,包括:发布图文笔记、发布视频笔记、批量发布多篇笔记。
Install
Quick install
npx skills add https://github.com/zangqilong198812/openclaw-xiaohongshu-publish-skillnpx skills add zangqilong198812/openclaw-xiaohongshu-publish-skill --agent claude-codenpx skills add zangqilong198812/openclaw-xiaohongshu-publish-skill --agent cursornpx skills add zangqilong198812/openclaw-xiaohongshu-publish-skill --agent codexnpx skills add zangqilong198812/openclaw-xiaohongshu-publish-skill --agent opencodenpx skills add zangqilong198812/openclaw-xiaohongshu-publish-skill --agent github-copilotnpx skills add zangqilong198812/openclaw-xiaohongshu-publish-skill --agent windsurfMore install options
Shorthand — useful for multi-skill repos:
npx skills add zangqilong198812/openclaw-xiaohongshu-publish-skillManual — clone the repo and drop the folder into your agent's skills directory:
git clone https://github.com/zangqilong198812/openclaw-xiaohongshu-publish-skill.gitcp -r openclaw-xiaohongshu-publish-skill ~/.claude/skills/xiaohongshu-publish
使用 OpenClaw 浏览器发布小红书笔记(图文/视频)。当用户需要发布小红书笔记时使用此 skill,包括:发布图文笔记、发布视频笔记、批量发布多篇笔记。
---
name: xiaohongshu-publish
description: 使用 OpenClaw 浏览器发布小红书笔记(图文/视频)。当用户需要发布小红书笔记时使用此 skill,包括:发布图文笔记、发布视频笔记、批量发布多篇笔记。
---
小红书发布 Skill
使用前提
- 账号文件夹:
~/xiaohongshu-<账号名>/
account.md- 账号信息resource.md- 素材列表resources/- 素材文件目录
- 用户已登录小红书
首次登录
openclaw browser --browser-profile openclaw open https://www.xiaohongshu.com/
账号文件夹结构
创建 ~/xiaohongshu-<账号名>/,例如 ~/xiaohongshu-meizhuang/:
~/xiaohongshu-meizhuang/
├── account.md
├── resource.md
└── resources/
├── img1.jpg
├── img2.jpg
└── video1.mp4
account.md 模板
# 账号信息
## 账号定位
美妆博主
## 目标受众
年轻女性
## 内容风格
温柔亲切
## 产品/服务
[描述]
## 其他要求
- 禁止:xxx
- 必须:xxx
resource.md 模板
# 素材列表
## 素材1
- 类型:图文
- 文件:img1.jpg
- 描述:xxx
## 素材2
- 类型:视频
- 文件:video1.mp4
- 描述:xxx
发布流程
Step 1: 询问账号
问用户要发布到哪个账号(哪个文件夹)
Step 2: 读取账号信息
读取 ~/xiaohongshu-<账号名>/account.md
Step 3: 读取素材信息
读取 ~/xiaohongshu-<账号名>/resource.md,让用户选择要发布的素材
Step 4: AI 生成文案
生成标题(≤20字)、正文、话题,提交用户确认
Step 5: 打开发布页
openclaw browser --browser-profile openclaw open https://creator.xiaohongshu.com/publish/publish
Step 6: 上传内容
openclaw browser --browser-profile openclaw snapshotopenclaw browser --browser-profile openclaw click <ref>openclaw browser --browser-profile openclaw upload ~/xiaohongshu-<账号名>/resources/<filename>
Step 7: 填写文案
openclaw browser --browser-profile openclaw type <ref> "文案"
Step 8: 发布
Step 9: 记录历史
更新 ~/xiaohongshu-<账号名>/history.md
注意
- 标题 ≤20 字
- 视频上传慢
- 验证码用户手动处理
---
Source: https://github.com/zangqilong198812/openclaw-xiaohongshu-publish-skill
Author: zangqilong198812
Discovered via: skillsdirectory.com
Genre: tools
SKILL.md source
---
name: xiaohongshu-publish
description: 使用 OpenClaw 浏览器发布小红书笔记(图文/视频)。当用户需要发布小红书笔记时使用此 skill,包括:发布图文笔记、发布视频笔记、批量发布多篇笔记。
---
# xiaohongshu-publish
使用 OpenClaw 浏览器发布小红书笔记(图文/视频)。当用户需要发布小红书笔记时使用此 skill,包括:发布图文笔记、发布视频笔记、批量发布多篇笔记。
---
name: xiaohongshu-publish
description: 使用 OpenClaw 浏览器发布小红书笔记(图文/视频)。当用户需要发布小红书笔记时使用此 skill,包括:发布图文笔记、发布视频笔记、批量发布多篇笔记。
---
# 小红书发布 Skill
## 使用前提
1. **账号文件夹**:`~/xiaohongshu-<账号名>/`
- `account.md` - 账号信息
- `resource.md` - 素材列表
- `resources/` - 素材文件目录
2. **用户已登录小红书**
## 首次登录
```bash
openclaw browser --browser-profile openclaw open https://www.xiaohongshu.com/
```
## 账号文件夹结构
创建 `~/xiaohongshu-<账号名>/`,例如 `~/xiaohongshu-meizhuang/`:
```
~/xiaohongshu-meizhuang/
├── account.md
├── resource.md
└── resources/
├── img1.jpg
├── img2.jpg
└── video1.mp4
```
### account.md 模板
```markdown
# 账号信息
## 账号定位
美妆博主
## 目标受众
年轻女性
## 内容风格
温柔亲切
## 产品/服务
[描述]
## 其他要求
- 禁止:xxx
- 必须:xxx
```
### resource.md 模板
```markdown
# 素材列表
## 素材1
- 类型:图文
- 文件:img1.jpg
- 描述:xxx
## 素材2
- 类型:视频
- 文件:video1.mp4
- 描述:xxx
```
## 发布流程
### Step 1: 询问账号
问用户要发布到哪个账号(哪个文件夹)
### Step 2: 读取账号信息
读取 `~/xiaohongshu-<账号名>/account.md`
### Step 3: 读取素材信息
读取 `~/xiaohongshu-<账号名>/resource.md`,让用户选择要发布的素材
### Step 4: AI 生成文案
生成标题(≤20字)、正文、话题,提交用户确认
### Step 5: 打开发布页
```bash
openclaw browser --browser-profile openclaw open https://creator.xiaohongshu.com/publish/publish
```
### Step 6: 上传内容
1. `openclaw browser --browser-profile openclaw snapshot`
2. `openclaw browser --browser-profile openclaw click <ref>`
3. `openclaw browser --browser-profile openclaw upload ~/xiaohongshu-<账号名>/resources/<filename>`
### Step 7: 填写文案
`openclaw browser --browser-profile openclaw type <ref> "文案"`
### Step 8: 发布
### Step 9: 记录历史
更新 `~/xiaohongshu-<账号名>/history.md`
## 注意
- 标题 ≤20 字
- 视频上传慢
- 验证码用户手动处理
---
**Source**: https://github.com/zangqilong198812/openclaw-xiaohongshu-publish-skill
**Author**: zangqilong198812
**Discovered via**: skillsdirectory.com
**Genre**: tools
Related skills 6
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
secure-linux-web-hosting
Use when setting up, hardening, or reviewing a cloud server for self-hosting, including DNS, SSH, firewalls, Nginx, static-site hosting, reverse-proxying an app, HTTPS with Let's Encrypt or ACME clients, safe HTTP-to-HTTPS redirects, or optional post-launch network tuning such as BBR.
readme-i18n
Use when the user wants to translate a repository README, make a repo multilingual, localize docs, add a language switcher, internationalize the README, or update localized README variants in a GitHub-style repository.
lark-shared
Use when first setting up lark-cli, running auth login, switching user/bot identity (--as), handling permission denied or scope errors, needing to update lark-cli, or seeing _notice in JSON output.
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
paper-context-resolver
Optional RigorPilot helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacin...