小红书自动发布

自动读取指定文件夹当日视频和标题，连接Chrome通过脚本将内容发布到小红书账号。

This skill automates posting by controlling your Chrome browser via the remote debugging port — that means it will act as whatever Chrome profile is exposed (including using your logged-in accounts and cookies). Before installing: - Inspect and/or modify the code: change the hardcoded path /Users/today to a proper configurable path (e.g., process.env.HOME) or confirm it matches your environment. - Do not run this against your main Chrome profile. Start Chrome with a dedicated user-data-dir and only enable --remote-debugging-port for that profile, or run it in a throwaway profile. - Ensure Puppeteer and Node dependencies come from a trusted source; the package has no install spec for npm modules. - Be aware the script uses macOS-specific commands (open) and curl; it appears Mac-only. - Review the unexplained skill.json note about YouTube cookies — the runtime does not download videos, so confirm your workflow and privacy implications. - If you proceed, run in a controlled environment first, and avoid leaving the remote debugging port open after use.

Type: OpenClaw Skill Name: xiaohongshu-publish-auto Version: 1.2.0 The skill is a browser automation tool designed to upload videos and titles to the Xiaohongshu (Red) creator platform. It uses Puppeteer to connect to a local Chrome instance via the remote debugging port (9222) and automates the file upload and form-filling process using local files from a specific directory. While it interacts with the user's active browser session and local filesystem, its behavior is entirely consistent with its stated purpose in SKILL.md and skill.json, with no evidence of data exfiltration, malicious execution, or prompt injection.