Wechat Mp Writer

What it does

When your agent uses it

• Tasks that involve Messaging and chat bots

Example prompts

• “/wechat-mp-writer”

Requirements

• Python 3
• Compatibility (from SKILL.md): {"platforms":["openclaw"]}

Workflow steps

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

1. 1信息搜集：scripts/collect_sources.py 归并本地文件、URL、原始文本
2. 2AI配图规划：scripts/plan_images.py 自动补封面图和正文图 prompt、caption、文件路径
3. 3世界级排版：scripts/render_article.py 渲染报刊级 HTML 模板
4. 4硬约束校验：scripts/validate_article.py 校验标题、摘要、图片 URL、正文大小
5. 5自动发布：scripts/run_pipeline.py 串联渲染、校验、上传封面、上传正文图、建草稿、发布

What it can do on your machine

Read from SKILL.md and the folder at commit 566d36c. 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 1 file in scripts/, 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:

  • cnbc.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.

• Compatibility

  {"platforms":["openclaw"]}

  From compatibility in the SKILL.md frontmatter.

Context cost

Wechat Mp Writer loads about 1.4k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 233 words of instructions outside code blocks.

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

~33

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

~1.4k

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

~3.3k

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

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 th3ee9ine/wechat-claw-skill at commit 566d36c, republished under its MIT licence (© th3ee9ine). 233 words, ~1,399 tokens.

name

wechat-mp-writer

description

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。

compatibility

{"platforms":["openclaw"]}

version

1.1.0

author

39Claw

license

MIT

# 渲染 HTML
python3 scripts/render_article.py article.json -o build/article.html --check

# 单独校验
python3 scripts/validate_article.py article.json --html build/article.html

# 规划封面图和正文配图
python3 scripts/plan_images.py article.json --write-article build/article.with-images.json

# 跑完整本地流水线
python3 scripts/run_pipeline.py article.json --output-dir build --dry-run

python3 scripts/run_pipeline.py article.json \
  --output-dir build \
  --nanobanana-script /abs/path/to/generate_image.py \
  --wechat-script /abs/path/to/wechat_mp.py \
  --create-draft \
  --publish

{
  "template": "daily-intelligence",
  "meta": {
    "title": "AI日报3.15｜亮点1·亮点2·亮点3",
    "digest": "摘要，128字以内",
    "author": "39Claw",
    "date": "2026-03-15"
  },
  "headline": {
    "title": "头条标题",
    "body": ["第一段", "第二段"],
    "source": "CNBC"
  },
  "sections": [
    {
      "en": "BRIEFING",
      "cn": "要闻",
      "blocks": [
        {
          "type": "card",
          "style": "highlight",
          "number": 1,
          "title": "卡片标题",
          "body": ["正文段落"],
          "source": "财联社"
        }
      ]
    }
  ],
  "conclusion": "适用于 deep-analysis 的结论段",
  "cta": "你最关注哪一点？欢迎留言。"
}

python3 scripts/collect_sources.py source-spec.json -o build/sources.json

python3 scripts/collect_sources.py \
  --source-file "飞书导出::/path/to/daily.md" \
  --source-url "CNBC::https://www.cnbc.com/world/" \
  --source-text "补充备注::今天重点看模型价格战和 Agent 落地" \
  -o build/sources.json

python3 scripts/plan_images.py article.json \
  --write-article build/article.with-images.json \
  --output-dir build/images

python3 scripts/render_article.py build/article.with-images.json \
  -o build/article.html \
  --check

python3 scripts/validate_article.py build/article.with-images.json --html build/article.html

python3 scripts/run_pipeline.py article.json \
  --output-dir build \
  --nanobanana-script /abs/path/to/generate_image.py \
  --wechat-script /abs/path/to/wechat_mp.py \
  --create-draft \
  --publish

© th3ee9ine, 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 32 other files (scripts, references) in the repository root of th3ee9ine/wechat-claw-skill.

• SKILL.md
• .gitignore
• LICENSE
• README.md
• docs/README.en.md
• docs/README.zh.md
• docs/img/介绍1.jpeg
• docs/img/介绍2.jpeg
• docs/img/介绍3.jpeg
• docs/img/样例1.jpeg
• docs/img/样例2.jpeg
• docs/img/赞赏码.png
• docs/openclaw.en.md
• docs/openclaw.zh.md
• references/image-prompts.md
• references/title-formulas.md
• references/writing-guide.md
• scripts
• … and 15 more

Open the folder on GitHubat commit 566d36c