agentsclimarketplace

Self media wechat publisher

Skill yanhua1010/self-media-content-workflow/skills/self-media-wechat-publisher

把已确认的公众号终稿 Markdown 排版并写入微信公众号草稿箱。用于用户说"发布到公众号、写入草稿箱、公众号排版、换个排版主题、发小绿书图片消息"等场景。自动上传封面与文内图片,支持多主题与自定义 CSS、多账号和 server 模式。只创建草稿不群发,凭据只通过环境变量提供,未安装适配工具时交付手动发布包。From its SKILL.md

Install
npx -y skills add yanhua1010/self-media-content-workflow --skill self-media-wechat-publisher

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.6 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

公众号发布

目标

把确认过的公众号终稿 Markdown 排版成平台原生富文本,连同封面和文内图片写入公众号草稿箱。只创建草稿,从不群发。

适配层说明

本模块是公众号渠道的发布适配层,基于开源工具 wenyan CLI(Apache-2.0)。wenyan 不可用时不阻塞创作流程,按 self-media-content-delivery 交付手动发布包。

前置检测

  1. wenyan --version 确认安装。未安装时提示 npm install -g @wenyan-md/cli,用户不想安装则直接交付手动发布包。
  2. 确认 WECHAT_APP_IDWECHAT_APP_SECRET 环境变量存在。只判断存在性,不读取、不回显、不写入任何文件。
  3. 首次发布前确认运行机器 IP 已加入公众号后台白名单。IP 频繁变动或团队协作场景使用 server 模式,见 wenyan-setup.md

输入契约

文章顶部必须有 frontmatter:title 必填;cover 为本地或网络路径,缺省时自动取正文第一张图;authorsource_url 可选。文内图片支持本地绝对路径、相对路径和网络地址,发布时自动上传公众号素材库。模板见 wechat-article-template.md

小绿书图片消息:frontmatter 设 type: image 自动提取正文全部图片,或手动列出 image_list。最多 20 张,首图即封面。

主题选择

  1. 优先读取账号风格档案中的默认排版主题。
  2. 没有默认主题或用户要求换风格时,用当前文章渲染候选主题生成本地预览(wenyan render -f 文章.md -t 主题),让用户对比选择。
  3. 用户选定后写入账号风格档案,后续沿用,不重复询问。
  4. 需要品牌化排版时用 -c 加载自定义 CSS 主题。

发布流程

两层授权缺一不可:终稿确认,加上草稿箱写入授权。

  1. 核对 frontmatter 完整、封面可用、文内图片路径全部有效。
  2. wenyan render 本地渲染,确认无乱码、代码块和表格可读。
  3. wenyan publish -f 文章.md -t 主题 -h 高亮主题 写入草稿箱。
  4. 提醒用户在公众号后台打开草稿,核对标题、封面、前两段、图片数量和外链。
  5. 把草稿创建时间、使用主题和核对结果写回任务卡。

发布失败时按 wenyan-setup.md 排查。同一错误不盲目重试超过一次,凭据类问题交给用户处理。

多账号

发布到多个公众号时,改用 wenyan 的凭据配置管理多账号,publish 时加 --app-id 指定。每个账号都需要独立配置 IP 白名单。

安全边界

  • 只写草稿箱,不调用群发接口。
  • 凭据只通过环境变量或 wenyan 凭据配置提供,不写入任务卡、文章、日志或仓库。
  • 命令输出中出现 token 或密钥片段时不记录、不转述。
  • 发布接口报错、白名单拦截或凭据失效时立即停止并交给用户。

输出

返回:草稿标题、使用主题、封面来源、图片数量、草稿创建时间和需要人工核对的清单。

What ships with it: 3 files

3.4 KB alongside SKILL.md

agents/

references/

Gives 0 of the 12 instructions most media documents skills give in ~1.1k tokens

Counted across 99 of the 124 authors here whose files we hold, read 2026-09-06

  • Define three to five content pillarsin 7 of 99, across 5 files
  • Tag every finding as verified, medium, or assumedin 5 of 99, across 3 files
  • Respond to comments within one hourin 5 of 99
  • Adapt content format to each platformin 5 of 99
  • Choose platforms where the audience already spends timein 4 of 99, across 2 files
  • Cap promotional content at ten percentin 4 of 99, across 2 files
  • Answer product questions within two hoursin 4 of 99, across 2 files
  • Acknowledge complaints publicly, resolve them privatelyin 4 of 99, across 2 files
  • Batch-create posts to keep cadence consistentin 4 of 99, across 2 files
  • Fan out across free media sources in one queryin 3 of 99, across 1 file
  • Use Pexels or Pixabay for modern short clipsin 3 of 99, across 1 file
  • Extract historical shots from archival filmsin 3 of 99, across 1 file

Said here and by no other author read

  • Run `wenyan --version` to confirm installation
  • Confirm WECHAT_APP_ID and WECHAT_APP_SECRET environment variables exist
  • Confirm machine IP is whitelisted before first publish
  • Verify frontmatter, cover, and image paths before publishing
  • Render locally and check for garbled output
  • Publish to draft box with `wenyan publish`

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.