Wechat Publisher

What it does

When your agent uses it

• Tasks that involve Messaging and chat bots
• Tasks that involve Linting and formatting

Example prompts

• “发到公众号草稿箱”
• “推送到公众号”
• “做张公众号封面”
• “/wechat-publisher”

Requirements

• Python 3
• Node.js
• A credential in WECHAT_APP_SECRET
• A credential in DASHSCOPE_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1核心意象:文章前 200 字提取 2-4 个具象名词(不要"效率""创新"这种抽象概念)
2. 2情绪基调:从 7 选 1——温暖治愈 / 专业冷静 / 紧张焦虑 / 轻松愉悦 / 怀旧沉思 / 励志昂扬 / 神秘高级
3. 3画面风格:按文章主题查 references/image-prompts.md 的 9 种风格映射表
4. 4构图与镜头(固定文本):2.35:1 横向构图,主体居中偏左,右上角嵌入小字「意疏的AI口袋」,中部区域小字「<标题关键词 3-5 字>」(避开底部 15% 遮挡区)
5. 5负面提示(固定文本):画面主体不要出现任何文字、字母、汉字,水印、logo、签名

What it can do on your machine

Read from SKILL.md and the folder at commit 38bd735. 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

  Ships 7 files in scripts/ (Python and JavaScript), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  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:

  • mp.weixin.qq.com

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • WECHAT_APP_SECRET
  • DASHSCOPE_API_KEY
  • DOUBAO_API_KEY

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

Context cost

Wechat Publisher loads about 951 tokens when it runs, and up to ~5.2k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 223 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~84

When it runs · the whole SKILL.md, loaded when a task matches

~951

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.2k

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

• NoteMentions a .env fileSKILL.md:18

  source <(grep -E '^WECHAT_' .env | sed 's/^/export /')

• NoteMentions a .env fileSKILL.md:95

  凭证只写进 `.env`(已 gitignore)。

• NoteMentions a .env fileSKILL.md:105

  ### 脚本对 `.env` 的支持

• NoteMentions a .env fileSKILL.md:107

  | 脚本 | 支持 `.env` | 不支持 → CLI 必传 |

• NoteMentions a .env fileSKILL.md:116

  t.py` 前,**先 `source <(grep -E '^WECHAT_' .env | sed 's/^/export /')`** 把凭证拼成环境变量,不要让用户重复输。

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); the scripts in this folder are not scanned.

SKILL.md

The full file from YiShu5/claude-skills at commit 38bd735, republished under its MIT licence (© YiShu5). 223 words, ~951 tokens.

name

wechat-publisher

description

微信公众号文章的发布管道——封面生成、本地图片上传素材库、创建草稿、发布草稿、以及从 mp.weixin URL 提取原文。**触发场景**:用户说 "发到公众号草稿箱" / "推送到公众号" / "做张公众号封面" / "上传图片到微信" / "把这篇文章提取成 markdown" / "改写这篇 mp.weixin 链接(的提取部分)" / 任何提到「发布 / 草稿 / 封面 / 推送 / 提取微信文章」的请求。本 skill **不写文章**(交给 wechat-writer),**不做 markdown → html 排版**(交给 wechat-formatter)——它只处理图片生成、文件上传、微信 API 调用。

# 0. 加载凭证
source <(grep -E '^WECHAT_' .env | sed 's/^/export /')

# 1. 生成封面图(五要素 prompt 见 references/image-prompts.md)
python3 scripts/generate_cover.py \
  --prompt "<五要素 prompt>" \
  --output cover.jpg

# 2. 上传封面到微信永久素材
python3 scripts/upload_material.py \
  --app_id "$WECHAT_APP_ID" --app_secret "$WECHAT_APP_SECRET" \
  --image_path cover.jpg
# 输出: thumb_media_id=THUMB_XXX

# 3. 创建草稿
python3 scripts/create_draft.py \
  --title "文章标题" \
  --content "$(cat drafts/article.html)" \
  --thumb_media_id "THUMB_XXX" \
  --author "意疏"

# 4. (可选)直接发布
python3 scripts/publish_draft.py \
  --app_id "$WECHAT_APP_ID" --app_secret "$WECHAT_APP_SECRET" \
  --media_id "MEDIA_XXX"

python3 scripts/extract_to_markdown.py \
  "https://mp.weixin.qq.com/s/xxx" \
  -o drafts/extracted.md

python3 scripts/publish_article.py \
  --input article.md \
  --title "文章标题" \
  --author "意疏"

© YiShu5, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (scripts, references) in skills/wechat-publisher of YiShu5/claude-skills.

• SKILL.md
• reader/extract_and_convert.js
• reader/package-lock.json
• reader/package.json
• references/examples.md
• references/image-prompts.md
• references/wechat-api.md
• scripts/config.py
• scripts/create_draft.py
• scripts/extract_to_markdown.py
• scripts/generate_cover.py
• scripts/publish_article.py
• scripts/publish_draft.py
• scripts/upload_material.py

Open the folder on GitHubat commit 38bd735