← Back to Skills Marketplace
小红书全能运营助手,AI生图 + 草稿发布
by
shichao666
· GitHub ↗
· v1.0.0
· MIT-0
110
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install xhs-content-studio
Description
小红书博主运营助手,集成AI生图智能路由、爆款文案创作及草稿自动发布功能,支持未登录二维码扫码登录。
Usage Guidance
This skill appears to do what it claims: generate images (via MiniMax API or by automating a web service) and automate draft uploads to Xiaohongshu by controlling a locally running OpenClaw/Playwright browser over CDP (default port 18800). Before installing/using: 1) Review scripts (upload_auto.js, generate_image_smart.js) yourself — they control your local browser and can interact with any open page and its logged-in sessions. 2) Run in a dedicated/browser profile or isolated environment so the automation cannot access other browser accounts or sensitive tabs. 3) Check or create scripts/config.json yourself — the MiniMax API key is stored there; do not put other secrets in that file. 4) If you are uncomfortable with automated browser control, do not run the scripts or only run them after auditing the code. 5) When in doubt, run the commands manually step‑by‑step (inspect screenshots in the temp folder) rather than allowing unattended/autonomous runs. I have medium confidence because parts of the scripts were truncated in the provided listing — full review of all code paths (especially the truncated sections that download/extract URLs) would raise confidence to high.
Capability Analysis
Type: OpenClaw Skill
Name: xhs-content-studio
Version: 1.0.0
The xhs-content-studio skill bundle is a legitimate automation tool designed for Xiaohongshu content creators. It provides a workflow for AI image generation and automated draft uploading using Playwright to interact with the Xiaohongshu creator platform and the Doubao AI web interface. The scripts (generate_image_smart.js and upload_auto.js) perform browser automation, such as navigating to URLs, handling rich-text via the clipboard, and triggering login QR codes, all of which are aligned with the stated functionality. There is no evidence of data exfiltration, credential theft, or malicious instructions intended to subvert the agent or the user's security.
Capability Assessment
Purpose & Capability
Name/description (Xiaohongshu content assistant: AI image + draft publish) match the included scripts: image-generation (MiniMax + web automation) and upload_auto.js for draft publishing. Requested files and behaviors (finding playwright-core in OpenClaw locations, using local browser CDP, config.json for MiniMax key) are consistent with this purpose.
Instruction Scope
SKILL.md and scripts instruct the agent to connect to a locally running OpenClaw/Playwright browser (CDP on 127.0.0.1:18800), open creator.xiaohongshu.com and doubao.com, click UI elements, screenshot QR codes, paste content and upload files. These actions are expected for automation but do grant the skill broad access to anything open in that browser context (pages, cookies, local storage). The code does not appear to read unrelated system files beyond config.json, generated_images, and temp upload dirs.
Install Mechanism
No external installer is executed by the platform; this is instruction + script bundle (no remote archive fetch). Scripts expect Playwright to be provided by OpenClaw or global npm. There are no downloads from unknown hosts in the included files.
Credentials
The skill requests no environment variables or secret tokens from the OpenClaw platform. MiniMax API key is stored in a local config.json (not an env var). No unrelated credentials are requested.
Persistence & Privilege
always:false and user-invocable: true. The skill does connect to a local browser for automation, but it does not request permanent platform-wide privileges or modify other skills. Autonomous invocation is allowed by default (not flagged here) — combine that with browser access if you plan to allow autonomous runs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install xhs-content-studio - After installation, invoke the skill by name or use
/xhs-content-studio - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
🎨 AI生图MiniMax API 优先,豆包自动降级
📤 草稿发布自动上传图片+标题+正文
📱 二维码登录未登录时自动弹出扫码
🔄 浏览器复用disconnect 不杀浏览器
慎用!有封号风险,建议图片自己替换两张
Metadata
Frequently Asked Questions
What is 小红书全能运营助手,AI生图 + 草稿发布?
小红书博主运营助手,集成AI生图智能路由、爆款文案创作及草稿自动发布功能,支持未登录二维码扫码登录。 It is an AI Agent Skill for Claude Code / OpenClaw, with 110 downloads so far.
How do I install 小红书全能运营助手,AI生图 + 草稿发布?
Run "/install xhs-content-studio" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 小红书全能运营助手,AI生图 + 草稿发布 free?
Yes, 小红书全能运营助手,AI生图 + 草稿发布 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 小红书全能运营助手,AI生图 + 草稿发布 support?
小红书全能运营助手,AI生图 + 草稿发布 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 小红书全能运营助手,AI生图 + 草稿发布?
It is built and maintained by shichao666 (@shichao666); the current version is v1.0.0.
More Skills