Agent skill

Weixin Channels Publish

by aAAaqwq in aAAaqwq/AGI-Super-Team

微信视频号助手网页版视频发布全流程。通过浏览器自动化操控 channels.weixin.qq.com 完成登录检测、扫码登录、上传视频、填写描述和短标题、截图确认后发布或保存草稿。触发场景:用户需要发布视频到视频号、视频号发布、视频号上传视频、发视频号。

MITAuto-check passedProductivity & Automation

Install Weixin Channels Publish

skills CLI
$ npx skills add aAAaqwq/AGI-Super-Team --skill weixin-channels-publish -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aAAaqwq/AGI-Super-Team weixin-channels-publish --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/weixin-channels-publish .claude/skills/weixin-channels-publish && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
weixin-channels-publish
GitHub stars
105
Used in
1 other repo
Token cost
~1.6k tokens
SKILL.md length
280 words
Files
1
Skills in repo
167
Repo updated
First seen
Licence
MIT

At a glance

微信视频号助手网页版视频发布全流程。通过浏览器自动化操控 channels.weixin.qq.com 完成登录检测、扫码登录、上传视频、填写描述和短标题、截图确认后发布或保存草稿。触发场景:用户需要发布视频到视频号、视频号发布、视频号上传视频、发视频号。

  • Works in 8 steps: :导航到视频号助手 → :登录检测 → :扫码登录 → …
  • Productivity & Automation work in your project
  • SKILL.md covers 概述, 前置条件, 完整流程 and 默认配置, plus 4 more sections
  • Reaches channels.weixin.qq.com

What it does

Weixin Channels Publish is an agent skill from aAAaqwq/AGI-Super-Team. 微信视频号助手网页版视频发布全流程。通过浏览器自动化操控 channels.weixin.qq.com 完成登录检测、扫码登录、上传视频、填写描述和短标题、截图确认后发布或保存草稿。触发场景:用户需要发布视频到视频号、视频号发布、视频号上传视频、发视频号。

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation. It works with WeChat. The repository describes itself as: An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters. The licence is MIT.

When your agent uses it

  • Productivity & Automation work in your project

Example prompts

  • “/weixin-channels-publish”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. :导航到视频号助手
  2. :登录检测
  3. :扫码登录
  4. :导航到发表视频页面
  5. :上传视频文件
  6. :填写视频信息
  7. :截图确认
  8. :执行发布 / 保存草稿

What it can do on your machine

Read from SKILL.md and the folder at commit 7cefd81. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • channels.weixin.qq.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Weixin Channels Publish loads about 1.6k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 280 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aAAaqwq/AGI-Super-Team at commit 7cefd81, republished under its MIT licence (© aAAaqwq). 280 words, ~1,621 tokens.

Download SKILL.mdSave it as .claude/skills/weixin-channels-publish/SKILL.md (or your agent's skills folder).
name
weixin-channels-publish
description
微信视频号助手网页版视频发布全流程。通过浏览器自动化操控 channels.weixin.qq.com 完成登录检测、扫码登录、上传视频、填写描述和短标题、截图确认后发布或保存草稿。触发场景:用户需要发布视频到视频号、视频号发布、视频号上传视频、发视频号。
author
Daniel Li

微信视频号助手 — 视频发布

概述

通过浏览器自动化(profile=openclaw)操控视频号助手网页版(channels.weixin.qq.com),完成从登录到视频发布的全流程闭环。

前置条件

  1. 浏览器已启动:browser start profile=openclaw
  2. 待发布的视频文件已准备好(通常由 video-merge-send skill 合并输出)
  3. 视频描述文案(可由 AI 根据分镜脚本自动生成)

完整流程

Step 1:导航到视频号助手
browser navigate url=https://channels.weixin.qq.com

等待页面加载完成(2-3秒)。

Step 2:登录检测

根据 URL 和页面内容判断登录状态:

判断方法:

  • 未登录:URL 跳转到 channels.weixin.qq.com/login.html,页面显示二维码
  • 已登录:URL 为 channels.weixin.qq.com/platform/post/list 或其他非 login 页面,左侧有导航菜单
javascript
() => {
  return {
    url: window.location.href,
    isLoginPage: window.location.pathname.includes('login'),
    title: document.title
  };
}

已登录 → 跳到 Step 4

未登录 → 继续 Step 3

Step 3:扫码登录
3.1 截取二维码

登录页面的二维码位于一个 iframe 中。

方法A:直接截图整个页面(推荐,最简单)

browser screenshot profile=openclaw

截图会包含右侧的二维码区域,用户可以直接用微信扫码。

方法B:定位二维码 iframe 并截图

javascript
// 二维码在 iframe 内,结构:
// iframe → generic → img (二维码图片)
// snapshot 中 ref 前缀 f8 表示 iframe 内的元素
// 二维码图片 ref 类似 f8e7
3.2 发送二维码截图给用户
message action=send channel=feishu message="📱 请用微信扫码登录视频号助手" filePath=<截图路径>

发送截图后告知用户:

"请打开微信 → 扫一扫 → 扫描屏幕上的二维码,然后在手机上确认登录。"

3.3 等待登录完成

轮询检测登录状态(每 5 秒检查一次,最多等待 2 分钟):

javascript
() => {
  return {
    url: window.location.href,
    isLoginPage: window.location.pathname.includes('login'),
    title: document.title
  };
}

登录成功标志:

  • URL 不再包含 login
  • 页面跳转到管理后台(通常是 /platform/post/list)

二维码过期处理:

  • 如果 iframe 中出现"二维码已过期,点击刷新"文本(snapshot 中 ref=f8e16)
  • 点击刷新链接,重新截图发送
browser act kind=click ref=f8e16  # "二维码已过期,点击刷新"
3.4 登录态持久化

登录成功后,cookie 自动保存在:

~/.openclaw/browser/openclaw/user-data

下次打开浏览器自动保持登录。

Step 4:导航到发表视频页面

登录后导航到"发表视频"页面。有两种方式:

方式A:直接 URL 导航(推荐)

browser navigate url=https://channels.weixin.qq.com/platform/post/create

方式B:通过菜单导航

  1. snapshot 找到左侧菜单
  2. 点击"内容管理"展开子菜单
  3. 点击"视频"进入视频列表
  4. 点击"发表视频"按钮
# 依次查找并点击:
# 1. "内容管理" 菜单项
# 2. "视频" 子菜单
# 3. "发表视频" 按钮
Step 5:上传视频文件

发表视频页面会有一个上传区域(通常是拖拽区 + 点击上传按钮)。

5.1 查找上传入口

做 snapshot 找到上传相关元素:

  • 通常有"选择文件"或"点击上传"按钮
  • 或者一个 input[type="file"] 隐藏元素
javascript
// 查找文件上传 input
() => {
  const inputs = document.querySelectorAll('input[type="file"]');
  const results = [];
  inputs.forEach((input, i) => {
    results.push({
      index: i,
      accept: input.accept,
      id: input.id,
      className: input.className,
      parentClass: input.parentElement?.className
    });
  });
  return results;
}
5.2 上传视频
browser upload selector="input[type='file']" paths=["<视频文件路径>"]

或使用 snapshot 中找到的具体选择器。

视频文件路径通常为:

  • 单镜头:/tmp/openclaw/jimeng-videos/01_xxx.mp4
  • 合并后:/tmp/openclaw/jimeng-videos/final_merged.mp4
5.3 等待上传完成

视频上传需要时间,取决于文件大小。

轮询检查上传进度(每 5 秒截图/snapshot 一次):

  • 上传中:显示进度条或百分比
  • 上传完成:进度消失,显示视频预览缩略图
javascript
() => {
  // 检查是否有上传进度元素
  const progress = document.querySelector('[class*="progress"]');
  const percent = document.querySelector('[class*="percent"]');
  return {
    hasProgress: !!progress,
    progressText: progress?.textContent || '',
    percentText: percent?.textContent || ''
  };
}
Step 6:填写视频信息
6.1 添加描述(正文描述)

找到描述输入区域并填写爆火文案。

# snapshot 找到描述文本框(通常是 textarea 或 contenteditable div)
browser act kind=click ref=<描述输入框_ref>
browser act kind=type text="<描述文案>"

描述文案生成规则:

根据视频内容(分镜脚本的主题)自动生成爆款描述:

  1. Hook 开头:用提问或痛点吸引注意
  2. 核心价值:一句话说清视频讲了什么
  3. 话题标签:加 3-5 个相关话题 #标签
  4. 行动号召:引导点赞/关注/收藏

示例模板:

🔥 [痛点问题]?看完这条视频你就懂了!

[一句话核心价值]

💡 关键要点:
1. [要点1]
2. [要点2]
3. [要点3]

👇 觉得有用就点赞收藏,关注我学更多干货!

#企业数字化 #创业干货 #门店经营 #中小企业 #田泽湘
6.2 填写短标题(6-16个字符)

找到短标题输入框并填写。短标题显示在视频封面上,要求 6-16个字符。

# snapshot 找到短标题输入框
browser act kind=click ref=<短标题输入框_ref>
browser act kind=type text="<短标题>"

短标题生成规则:

  • 6-16个字符(中文算1个字符)
  • 简短有力,概括视频核心
  • 带数字更吸引点击
  • 示例:3万搞定门店数字化、利润翻倍的3个秘诀、老板必学的获客公式
6.3 其他可选设置

根据页面情况,可能还有:

  • 封面选择:默认自动截取,或可上传自定义封面
  • 位置:可选添加定位
  • 合集:可选加入已有合集
  • 定时发布:可设置发布时间
  • 谁可以看:公开/私密/部分可见

一般保持默认即可,除非用户特别指定。

Step 7:截图确认

发布前截图整个页面,发送给用户确认:

browser screenshot profile=openclaw
message action=send channel=feishu message="📋 视频已准备好,请确认以下信息后告诉我:\n1️⃣ 立即发布\n2️⃣ 保存草稿\n3️⃣ 修改内容\n\n描述:[已填写的描述]\n短标题:[已填写的短标题]" filePath=<截图路径>

等待用户回复指令。

Step 8:执行发布 / 保存草稿

根据用户指令执行:

发布
# snapshot 找到"发表"按钮
browser act kind=click ref=<发表按钮_ref>

发布后可能出现确认弹窗,点击确认。

截图确认发布成功:

browser screenshot profile=openclaw
message action=send channel=feishu message="✅ 视频已成功发布到视频号!" filePath=<截图路径>
保存草稿
# snapshot 找到"存草稿"按钮
browser act kind=click ref=<存草稿按钮_ref>

默认配置

在 TOOLS.md 中维护:

markdown
### 视频号助手 (weixin-channels-publish)

- **默认话题标签**: #企业数字化 #创业干货 #门店经营 #中小企业 #田泽湘
- **默认描述模板**: 爆款描述(hook+价值+标签+CTA)
- **短标题风格**: 数字+痛点,6-16字

关键技术细节

要素说明
浏览器 profileopenclaw
登录页 URLhttps://channels.weixin.qq.com/login.html
后台首页 URLhttps://channels.weixin.qq.com/platform/post/list
发表视频 URLhttps://channels.weixin.qq.com/platform/post/create
二维码位置登录页右侧 iframe 内(img 元素)
登录方式微信扫码(无账号密码登录选项)
登录态存储~/.openclaw/browser/openclaw/user-data(cookie 自动持久化)
视频上传限制最大 4GB,时长 1 秒 ~ 60 分钟
支持格式mp4, mov, avi, wmv, flv, mkv, webm
短标题要求6-16 个字符
描述长度限制最多 1000 字

完整工作流(端到端)

1. jimeng-storyboard skill    → 生成分镜脚本
2. jimeng-digital-human skill → 逐镜头生成 + 下载视频
3. video-merge-send skill     → 合并视频片段
4. weixin-channels-publish    → 发布到视频号 ← 本 skill
   ├── Step 1-3: 登录检测/扫码
   ├── Step 4: 导航到发表页
   ├── Step 5: 上传合并视频
   ├── Step 6: 填写描述+短标题
   ├── Step 7: 截图确认
   └── Step 8: 发布/草稿

常见问题

问题解决方案
二维码过期点击"二维码已过期,点击刷新"链接,重新截图发给用户
扫码后未跳转确认手机端已点确认,等待 5-10 秒后刷新页面
上传进度卡住检查文件大小是否超限(4GB),网络是否稳定
找不到上传按钮重新 snapshot,视频号助手可能改版,用 JS 搜索 input[type="file"]
短标题字数不符严格控制 6-16 字符,中文算 1 个字符
发布按钮灰色/disabled检查必填项是否都已填写(描述、短标题、视频上传完成)
登录后又跳回登录页cookie 可能过期,需重新扫码登录
描述含敏感词被拦截避免使用"最"、"第一"、"保证赚"等绝对化用语

注意事项

  1. 合规先行:描述中避免夸大承诺和绝对化用语("最好"、"保证"、"100%")
  2. 发布前必须用户确认:永远不要自动点击发布,必须截图让用户确认
  3. 草稿优先:如果用户犹豫,默认保存草稿而非发布
  4. 每个 snapshot 都要重新获取 ref:视频号助手 SPA 页面会频繁重渲染

© aAAaqwq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/weixin-channels-publish of aAAaqwq/AGI-Super-Team.

Open the folder on GitHubat commit 7cefd81

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in aAAaqwq/AGI-Super-Team, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Weixin Channels Publish next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Weixin Channels Publish compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Weixin Channels Publish this skillaAAaqwq/AGI-Super-Team1051 repos~1.6kAutomated safety check: PassMIT
She Love Me863401402/she-love-me9311 repos~1.3kAutomated safety check: PassMIT
Wechat Article Extractorfreestylefly/wechat-article-extractor-skill1361 repos~1kAutomated safety check: PassNone
Wechat Miniprogram Builderchenjin-cmd/wechat-miniprogram-builder356—~634Automated safety check: PassMIT
Skill Wechat PublisherZJU-REAL/Easel3.4k—~1.8kAutomated safety check: PassApache-2.0
Wechat Mp Writerth3ee9ine/wechat-claw-skill207—~1.4kAutomated safety check: PassMIT

Similar skills

  • She Love Me

    863401402/she-love-me

    Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics…

    931 GitHub starsUsed in 1 repo~1.3k tokens
    Productivity & AutomationAuto-check passed
  • Wechat Article Extractor

    freestylefly/wechat-article-extractor-skill

    Extract metadata and content from WeChat Official Account articles.

    136 GitHub starsUsed in 1 repo~1k tokens
    Productivity & AutomationAuto-check passed
  • Wechat Miniprogram Builder

    chenjin-cmd/wechat-miniprogram-builder

    This skill should be used when the user wants to build, launch, monetize, or promote a WeChat mini-program with AI (vibe coding) — including topic selection, account registration & ICP filing…

    356 GitHub stars~634 tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • 微信公众号文章自动创作与发布工具。给定参考文章、文字或文档,自动搜索整理全网相关信息、生成图文并茂的公众号文章,并发布到微信公众号草稿箱。特别强调反 AI 检测写作。

    3.4k GitHub stars~1.8k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Wechat Mp Writer

    th3ee9ine/wechat-claw-skill

    微信公众号文章全自动写作与发布。从信息搜集、AI配图规划、报刊级 HTML 排版、到草稿创建和发布的完整流程。适用于 AI 日报、财经周报、深度分析、新闻资讯类文章。内置多种模板,并提供本地渲染、校验、图片规划和发布流水线脚本。

    207 GitHub stars~1.4k tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check passed
  • Qiaomu Wx Video

    joeseesun/qiaomu-wx-video

    Qiaomu skill and workflow for downloading a WeChat Channels / 视频号 video or generated live replay when the user provides a weixin.qq.com/sph share link.

    135 GitHub stars~751 tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed

More from aAAaqwq/AGI-Super-Team

All 167 skills in this repo
  • Content Creator

    aAAaqwq/AGI-Super-Team

    Create SEO-optimized marketing content with consistent brand voice.

    105 GitHub starsUsed in 3 repos~1.9k tokens
    Auto-check passed
  • Financial Calculator

    aAAaqwq/AGI-Super-Team

    Advanced financial calculator with future value tables, present value, discount calculations, markup pricing, and compound interest.

    105 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • Bankr Signals

    aAAaqwq/AGI-Super-Team

    Transaction-verified trading signals on Base blockchain. An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub starsUsed in 2 repos~3.3k tokens
    Auto-check passed
  • Erc 8004

    aAAaqwq/AGI-Super-Team

    Register AI agents on Ethereum mainnet using ERC-8004 (Trustless Agents).

    105 GitHub starsUsed in 2 repos~1.2k tokens
    Auto-check passed
  • Frontend Design Ultimate

    aAAaqwq/AGI-Super-Team

    Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed.

    105 GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed
  • Zsxq Smart Publish

    aAAaqwq/AGI-Super-Team

    Publish and manage content on 知识星球 (zsxq.com). An agent skill from aAAaqwq/AGI-Super-Team.

    105 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed

Works with

Questions about Weixin Channels Publish

What does Weixin Channels Publish do?

微信视频号助手网页版视频发布全流程。通过浏览器自动化操控 channels.weixin.qq.com 完成登录检测、扫码登录、上传视频、填写描述和短标题、截图确认后发布或保存草稿。触发场景:用户需要发布视频到视频号、视频号发布、视频号上传视频、发视频号。. Weixin Channels Publish is an agent skill from aAAaqwq/AGI-Super-Team.

When should I use Weixin Channels Publish?

Weixin Channels Publish fits situations like: productivity & Automation work in your project.

How do I install Weixin Channels Publish in Claude Code?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill weixin-channels-publish -a claude-code`. Or copy the skill folder (skills/weixin-channels-publish in aAAaqwq/AGI-Super-Team) into .claude/skills/weixin-channels-publish in your project. Claude Code loads it when a task matches its description.

How do I install Weixin Channels Publish in Codex?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill weixin-channels-publish -a codex`. Or copy the skill folder (skills/weixin-channels-publish in aAAaqwq/AGI-Super-Team) into .agents/skills/weixin-channels-publish in your project. Codex loads it when a task matches its description.

Can I use Weixin Channels Publish in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aAAaqwq/AGI-Super-Team --skill weixin-channels-publish -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/weixin-channels-publish, .gemini/skills/weixin-channels-publish, .github/skills/weixin-channels-publish and .opencode/skills/weixin-channels-publish in your project.

What does Weixin Channels Publish need to run?

SKILL.md names no scripts, command-line tools or credentials: Weixin Channels Publish is instructions for the agent only.

Does Weixin Channels Publish access the network?

SKILL.md names 1 domain. In commands or code: channels.weixin.qq.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Weixin Channels Publish safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Weixin Channels Publish use?

Weixin Channels Publish is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Weixin Channels Publish use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Weixin Channels Publish?

Skills that share tags, products or a category with Weixin Channels Publish: She Love Me (863401402/she-love-me, 931 stars), Wechat Article Extractor (freestylefly/wechat-article-extractor-skill, 136 stars), Wechat Miniprogram Builder (chenjin-cmd/wechat-miniprogram-builder, 356 stars) and Skill Wechat Publisher (ZJU-REAL/Easel, 3.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Weixin Channels Publish?

aAAaqwq (a GitHub user) maintains it in aAAaqwq/AGI-Super-Team, which has 105 GitHub stars. The repository holds 167 skills in this directory. The repository was last updated on October 8, 2026.

Source: aAAaqwq/AGI-Super-Team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.