微信公众号贴图发布器

该 Skill 以 Python 脚本调用微信公众平台官方接口，先上传永久图片素材，再创建 newspic 图片消息草稿，最多支持 20 张绝对路径图片，第一张作为封面；每次运行在 outputs/ 写入 JSON 记录以便调试核对。最终发布仍需在微信后台手动完成，凭证由环境变量或本地配置文件提供。

hzlawliet

热度 46.44

最近更新 2026-05-11 17:44:36

分类：营销依赖：代码执行 / 读写文件 / 第三方 API应用场景：社交媒体 / API 集成 / 自动化脚本

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add wechat-sticker-publisher

Metadata

name: wechat-sticker-publisher
description: Publish WeChat Official Account image-first sticker posts (图片消息 / 发贴图) into the draft box via the official API. Use when the user wants to create公众号“发贴图”草稿、图片消息草稿、image-first posts, poster-style posts, or a visual post that is primarily images with short supporting text instead of a long article. This skill uploads permanent image materials and creates `newspic` drafts only; final publication remains manual in the WeChat backend.
metadata: {"openclaw":{"emoji":"🖼️","category":"publishing"},"clawdbot":{"emoji":"🖼️","requires":{"bins":[],"env.optional":["WECHAT_APP_ID","WECHAT_APP_SECRET"]}}}

WeChat Sticker Publisher

Create draft-only WeChat Official Account sticker/image-message posts using the official API.

Workflow

Use scripts/publish_sticker.py.
Provide one or more absolute image paths.
Provide a title and short text.
The script uploads permanent image materials.
The script creates a newspic draft in the WeChat draft box.
Do not auto-publish; final publish is manual in the WeChat backend.

Rules

Keep this skill limited to draft creation.
Do not modify the existing daily article publishing workflow unless explicitly requested.
Require absolute local image paths.
Support up to 20 images; the first image becomes the cover image.
Send JSON request bodies explicitly as UTF-8 (application/json; charset=utf-8).
- This is important: using a different request-body path can lead to garbled Chinese text.

Credentials

The script reads credentials from environment variables:

WECHAT_APP_ID
WECHAT_APP_SECRET

It can also load a local wechat.env file placed in the skill root. Use wechat.env.example as the starting template.

If packaging/publishing this skill publicly, do not include any real secrets or local credential files.

Primary command

python3 scripts/publish_sticker.py \
  --image /abs/path/to/image.jpg \
  --title "标题 / Title" \
  --text "配文 / Caption"

Multi-image example

python3 scripts/publish_sticker.py \
  --image /abs/1.jpg \
  --image /abs/2.jpg \
  --title "多图贴图测试" \
  --text "这是一个多图图片消息草稿。"

Outputs

Each run writes a JSON record to outputs/ containing:

uploaded image material responses
draft request body
draft creation response

Use those files for debugging and verification.

Files

scripts/publish_sticker.py — main deterministic implementation
references/api-notes.md — concise implementation notes and known behavior
README.md — bilingual human-facing overview for repository/ClawHub readers
LICENSE — MIT license

When to read references

Read references/api-notes.md if you need:

the exact API mapping (add_material + draft/add)
encoding gotchas
the distinction between news and newspic