Wechat Auto Publishing Complete

Community

16Miku

wechat-auto-publishing-complete

Use this skill for a reproducible WeChat Official Account workflow with dual channels (API draft and/or Chrome browser publish) and production default draft_notify_feishu: API draft/add then Feishu notify for human formal publish in mp admin (avoids freepublish visibility bugs on Linux/OpenClaw). Also covers browser publish, Feishu QR verify push, multi-account checks, image/gallery strategy, and archival. Keep secrets outside the package.

Overview

Publisher	16Miku
Repository	`wechat-auto-publishing`
Skill name	`wechat-auto-publishing-complete`
Stars	54
Forks	14
Bundled files	32
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
32 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by 16Miku on GitHub. Read the source before you install it.

Installation

Install the Wechat Auto Publishing Complete AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/16Miku/wechat-auto-publishing/tree/main
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/16Miku/wechat-auto-publishing.git \
  .claude/skills/wechat-auto-publishing-complete

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wechat Auto Publishing Complete in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wechat Auto Publishing Complete on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wechat Auto Publishing Complete is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

WeChat Auto Publishing Complete

本 Skill 用于复现、文档化和运营一套本地/服务器可交接的微信公众号发文工作流。

发布通道与生产默认

通道	名称	适用场景
A	微信开放平台 API	草稿入库、定时、Linux/OpenClaw
B	Chrome 操控本地浏览器	Windows 本机、要与后台「发表」一致的自动化点击

模式	含义	推荐场景
`draft_notify_feishu`	API 仅草稿 → 飞书待办 → 人手后台发表	Linux/OpenClaw 默认生产
`draft_only`	仅草稿，不通知	调试
`browser_full`	本机浏览器发表 + 可选飞书推验证码	有桌面、要少点几次
`api_freepublish`	draft + freepublish	实验；接受可见性异常

生产默认（服务器）：publish_channel=api + publish_mode=draft_notify_feishu。
不要在 OpenClaw 日更任务里默认 freepublish 当「粉丝可见正发」。

安全铁律：Skill 包内永不写入真实 AppID/Secret、Cookie、token、飞书密钥。

Core outcome

环境与密钥外置
资讯采集与事实核对
文风写稿
配图（图库 / AI / 提示词直出）
当日包 output/YYYY-MM-DD/
API 草稿（media_id）和/或 Browser 草稿（appmsgid）
draft_notify_feishu：飞书摘要 + mp 后台入口
人工后台发表（或本机 Browser 发表 + 扫码）
归档与可选调度

Skill structure

文件	用途
`references/draft-notify-feishu.md`	服务器默认：草稿+飞书+人手发表
`references/publishing.md`	双通道与各 publish_mode 总览
`references/browser-chrome-publish.md`	通道 B 逐步手册
`references/feishu-qr-notify.md`	浏览器发表时的验证码推送（非草稿待办）
`references/multi-account.md`	多账号自检
`references/session-practices.md`	实战一页纸
`references/environment-and-config.md`	环境、代理、部署形态（含为何不做 Linux 无头登录）
`references/source-gathering.md` / `writing-style.md` / `image-strategy.md`	内容与图
`references/scheduling-and-alerting.md`	定时与告警
`references/security-boundary.md`	安全边界
`templates/feishu-draft-ready.example.*`	草稿就绪飞书通知脚本
`templates/feishu-qr-notify.example.*`	验证码飞书推送脚本
`templates/publish.mjs`	API 备用（注意默认只应用到草稿）
`templates/browser-checklist.example.md`	Browser 清单
`templates/env.example.txt`	环境变量占位
`runbook.md`	操作员清单

Standard execution flow

Step 0：选择通道与模式

text
publish_channel = api | browser | hybrid
publish_mode    = draft_notify_feishu | draft_only | browser_full | api_freepublish

场景	建议
Linux + OpenClaw 日更	`api` + `draft_notify_feishu`
本机 Chrome 要自动点到扫码	`browser` + `browser_full`
仅调试草稿	`api` + `draft_only`
实验 freepublish	`api_freepublish` + 书面接受风险

Step 1–5：环境 / 素材 / 写稿 / 配图 / 打包

同既有约定；见各 references。多账号先做自检（multi-account.md）。

Step 6：发布到草稿

API：draft 成功 → 必须有 media_id；draft_notify_feishu / draft_only 下禁止 freepublish
Browser：保存草稿 → appmsgid /「已保存」

Step 7A：draft_notify_feishu（服务器主路径）

清代理
飞书发送「待发布·草稿已进箱」（账号、标题、摘要、media_id、操作三步、https://mp.weixin.qq.com/）
可选附封面图（相对路径）
归档 status=draft_ready_notified
本 run 成功 = 草稿 + 通知；正发由管理员完成

详见 references/draft-notify-feishu.md。
脚本：templates/feishu-draft-ready.example.sh / .ps1。

Step 7B：人工 / Browser 正式发表（可选）

管理员按飞书指引后台发表；或
Windows 上走 browser-chrome-publish.md，验证码走 feishu-qr-notify.md

Step 8：归档

见 templates/publish-result.example.json。
区分 draft_ready_notified 与 published。

Step 9：调度

定时任务默认：生成 + API 草稿 + 飞书草稿通知。
默认不要无人值守 freepublish / 服务器无头登录微信。

两类飞书消息（勿混淆）

类型	模式/时机	内容
草稿就绪	`draft_notify_feishu`，API 出 media_id 后	摘要 + 后台链接 + 操作步骤
验证码	Browser 点到「微信验证」后	二维码图片

通道选择（第一性）

需求	选择
服务器稳定日更、避开 freepublish 坑	draft_notify_feishu
与后台发表按钮完全一致且本机有 Chrome	Browser full
只要进草稿	API draft_only / notify
实验 API 正发	api_freepublish（非默认）

关键坑（必须遵守）

freepublish 可见性 ≠ 后台手动发表；OpenClaw 默认不要正发 API。
Linux 不推荐 Xvfb/无头登录 mp 做正发；用飞书喊人手点。
双 ProseMirror、封面从正文选、代理三分、飞书相对路径——见 session-practices.md。
换号自检作者与 token——见 multi-account.md。
飞书链接优先 https://mp.weixin.qq.com/，慎用带 token 深链。

Reproduction checklist

draft_notify_feishu 文档与模板齐全
API 能拿到 media_id
飞书草稿通知可发送
管理员清单可执行
freepublish 非默认且有风险说明
Browser / 推码路径仍可选
无真实密钥进包

Final rule

流程写全，秘密不进包。
服务器生产 = 草稿自动化 + 飞书触达 + 人正发。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wechat Auto Publishing Complete AI skill do?

Why use Wechat Auto Publishing Complete on TypingMind?

Because you install it once and use it with any model. Wechat Auto Publishing Complete is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wechat Auto Publishing Complete in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/16Miku/wechat-auto-publishing/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wechat Auto Publishing Complete?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wechat Auto Publishing Complete?

As many as you like. As long as a model supports skills, you can use Wechat Auto Publishing Complete with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wechat Auto Publishing Complete AI skill free?

It is published on GitHub by 16Miku. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Executing Plans

obra

CommunityPopular

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Using Superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Context And Decisions

affaan-m

CommunityPopular

Govern stable domain context with a narrowly scoped CONTEXT.md when needed, and route hard-to-reverse decisions to ECC's existing architecture-decision-records skill. Use when domain terms require…

Docs Governance

Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

WeChat Auto Publishing Complete

发布通道与生产默认

Core outcome

Skill structure

Standard execution flow

Step 0：选择通道与模式

Step 1–5：环境 / 素材 / 写稿 / 配图 / 打包

Step 6：发布到草稿

Step 7A：draft_notify_feishu（服务器主路径）

Step 7B：人工 / Browser 正式发表（可选）

Step 8：归档

Step 9：调度

两类飞书消息（勿混淆）

通道选择（第一性）

关键坑（必须遵守）

Reproduction checklist

Final rule

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now