一键生成PPT截图和缩略图工具发布到微信去的工具，MAC版本

自动将指定Mac路径下的PPT按页生成截图和缩略图，并发布到微信公众号，支持自定义配置和参数调整。

This skill appears internally consistent and implements the stated workflow. Before installing/using it: (1) Verify you have LibreOffice (soffice) and Ghostscript installed and configured paths in config.json. (2) Replace the placeholder wechat_appid and wechat_appsecret in config.json with your real credentials and keep that file private (do not commit it to git). (3) Understand the script will upload images to your WeChat account using those credentials—only run it with credentials you control. (4) The script compresses images in-place and writes output under the PPT-named work directory; verify disk/write permissions and available space. (5) If you need higher assurance, review or run the script in an isolated environment (local VM) and monitor outgoing network calls; the only external endpoints used are api.weixin.qq.com (official WeChat API).

Type: OpenClaw Skill Name: ppt2wechat Version: 1.0.0 The skill automates the conversion of PPT files to images and their subsequent upload to WeChat Official Accounts using `ppt2wechat.py`. It requires the user to provide sensitive API credentials (`wechat_appid`, `wechat_appsecret`) and utilizes `subprocess.run` to execute external system binaries (LibreOffice and Ghostscript) for file processing. While the code logic appears to follow the stated purpose and communicates only with official WeChat endpoints (api.weixin.qq.com), the handling of sensitive credentials and the execution of external system commands are classified as high-risk behaviors under the provided criteria.