← Back to Skills Marketplace
kukuoai

Deepsop Xiaohongshu 助手

by kukuoAI · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
34
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install deepsop-xiaohongshu-ai
Description
小红书视频/图文自动上传 skill。当用户需要登录小红书、校验账号或上传内容时使用。基于 social-auto-upload 项目,OPclaw 自动准备运行环境,无需用户手动安装。
README (SKILL.md)

\r \r

小红书上传 Skill\r

\r 本 skill 通过 social-auto-upload 项目(以下简称 SAU)完成小红书操作。OPclaw 自带 uv 工具,会在首次使用时自动 clone SAU 并准备依赖,不要让用户手动 pip install。\r \r

功能概览\r

\r | 功能 | 子命令 | 说明 |\r | --- | --- | --- |\r | 登录 | login --account \x3Cname> | 用户在本机真实终端里执行,扫码完成 |\r | 校验 | check --account \x3Cname> | 检查指定账号 cookie 当前是否有效 |\r | 视频上传 | upload-video ... | 上传一条小红书视频 |\r | 图文上传 | upload-note ... | 上传一条小红书图文 |\r \r 元数据约定:\r \r

  • 视频使用 title + desc + tags\r
  • 图文使用 title + note + tags\r \r

默认工作流\r

\r

  1. 先确认环境就绪 —— 见 references/runtime-requirements.md\r
  2. 再确认命令格式 —— 见 references/cli-contract.md\r
  3. 执行匹配的 python sau_cli.py xiaohongshu ... 命令\r
  4. 失败时查 references/troubleshooting.md\r \r

命令选择建议\r

\r

  • 用户需要新的 cookie 或现有 cookie 失效 → 用 login\r
  • 用户只想确认 cookie 状态 → 用 check\r
  • 用户要发视频 → 用 upload-video\r
  • 用户要发图文 → 用 upload-note\r \r

执行前必做检查(agent 行为约定)\r

\r 执行任何 python sau_cli.py xiaohongshu ... 之前,必须references/runtime-requirements.md 的"自动准备流程"完成环境校验:\r \r

  1. 检查 ~/.openclaw/social-auto-upload 是否存在\r
  2. 不存在则自动 clone + uv sync --python 3.12\r
  3. 准备好后,所有调用都用 uv run --project ~/.openclaw/social-auto-upload python sau_cli.py xiaohongshu ...\r
  4. 不要直接 sau xiaohongshu ...(这条命令不存在)\r
  5. 网络失败时git clone 直连超时/失败,agent 必须自动gh-proxy.org / gh-proxy.com / hub.gitmirror.com 三个镜像依次重试,严禁第一次失败就告诉用户'无法访问 GitHub'。详见 references/runtime-requirements.md Step 2\r
  6. 当用户明确指定无头或有头模式时,显式传 --headless--headed\r
  7. 只有用户明确要求定时发布时,才使用 --schedule\r \r

登录注意事项\r

\r

  • login 命令应由用户自己在本机终端执行,agent 在非交互环境下不要硬跑\r
  • 如果终端二维码显示不完整,提醒用户打开 SAU 仓库目录下的 qrcode.png 扫码\r
  • 一个 --account \x3Cname> 对应一个本地账号文件,可用于多账号隔离\r
  • 如果登录流程生成了本地二维码图片,不要只把图片路径告诉用户,优先直接把本地图片展示/发送给用户\r \r

模板文件\r

\r

  • scripts/examples/xiaohongshu_commands.ps1\r
  • scripts/examples/xiaohongshu_commands.sh\r
  • scripts/examples/xiaohongshu_cli_template.py\r \r

参考文档\r

\r

  • 运行前提:references/runtime-requirements.md\r
  • CLI 契约:references/cli-contract.md\r
  • 故障排查:references/troubleshooting.md\r
Usage Guidance
Review this skill before installing. Use it only if you trust the social-auto-upload project and the listed mirror hosts, preferably after pinning the upstream code yourself. Use a dedicated Xiaohongshu account or isolated profile, treat generated cookie files as credentials, and require a manual preview/confirmation before any upload command publishes content.
Capability Assessment
Purpose & Capability
The stated purpose is coherent: login, cookie checks, and video/image-note uploads to Xiaohongshu through social-auto-upload. The concern is that these are high-impact account actions, including public posting and session use, with no built-in preview or confirmation gate before upload commands.
Instruction Scope
The runtime instructions tell the agent to prepare the environment automatically, retry clones through multiple mirrors without asking, and run upload commands through the external CLI. Login is correctly directed to the user's local terminal, but upload/check operations remain broadly agent-executable.
Install Mechanism
First use clones an unpinned external repository into ~/.openclaw/social-auto-upload, copies config, runs uv sync, and installs a Chromium browser binary. Fallback clone hosts include Gitee and public proxy/mirror domains without integrity verification.
Credentials
Browser automation, dependency downloads, user media upload, and Xiaohongshu session handling are related to the skill's purpose, but the README frames the skill as low risk and automatic while underplaying supply-chain, storage, and account-security implications.
Persistence & Privilege
The skill creates persistent local state under the user's home directory, including the cloned tool, dependencies, configuration, browser components, and account cookie files generated by the external CLI. No cleanup path or clear credential-handling guardrails are provided.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install deepsop-xiaohongshu-ai
  3. After installation, invoke the skill by name or use /deepsop-xiaohongshu-ai
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
deepsop-xiaohongshu-ai v1.0.0 – Initial Release - Enables automatic upload of videos and photo notes to Xiaohongshu via the social-auto-upload project. - Handles login, cookie verification, and content upload processes, with clear subcommands for each function. - Automatically prepares and manages environment dependencies; no manual installation required by the user. - Includes robust checks and network fallback for project cloning using GitHub mirrors. - Provides guidance on correct command usage, file templates, and troubleshooting steps.
Metadata
Slug deepsop-xiaohongshu-ai
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Deepsop Xiaohongshu 助手?

小红书视频/图文自动上传 skill。当用户需要登录小红书、校验账号或上传内容时使用。基于 social-auto-upload 项目,OPclaw 自动准备运行环境,无需用户手动安装。 It is an AI Agent Skill for Claude Code / OpenClaw, with 34 downloads so far.

How do I install Deepsop Xiaohongshu 助手?

Run "/install deepsop-xiaohongshu-ai" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Deepsop Xiaohongshu 助手 free?

Yes, Deepsop Xiaohongshu 助手 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Deepsop Xiaohongshu 助手 support?

Deepsop Xiaohongshu 助手 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Deepsop Xiaohongshu 助手?

It is built and maintained by kukuoAI (@kukuoai); the current version is v1.0.0.

💬 Comments