← 返回 Skills 市场
xiaohongshu-full-auto
作者
guanlansss
· GitHub ↗
· v1.0.0
· MIT-0
89
总下载
2
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install xiaohongshu-full-auto
功能描述
🚀 小红书全链路自动化自媒体工作流，从热点抓取 → 选题分析 → 文案生成 → 封面图生成 → 自动发布，一条龙全自动搞定小红书内容创作。适合自媒体博主、副业玩家、内容工作室批量生产小红书内容。触发关键词："全自动小红书", "小红书创作", "小红书自动发布", "小红书热榜", "批量做小红书", "xia...
安全使用建议
This package is inconsistent and needs closer review before use. Specific things to check: 1) The bundle is missing key modules (generate_content.py, generate_cover.py, publish.py) referenced by full_auto.py — obtain or inspect those files before running. 2) SKILL.md and config-example require sensitive credentials (XIAOHONGSHU_COOKIE, XIAOHONGSHU_BUSINESS_ID, optional OPENAI_API_KEY, Feishu tokens) but the registry metadata lists none — do not supply real cookies/keys to this code until you verify the publish implementation. 3) get_hot_topics calls a third‑party endpoint (api.fakey.top) rather than an official API; confirm what data is sent and whether that endpoint is trustworthy. 4) Because the package may attempt network calls and publishing, test in an isolated/sandbox environment and run in semi-auto/assist-only mode first. 5) Ask the publisher for the missing files or a provenance explanation (why credentials aren't declared, where publish.py comes from) and review publish.py to confirm it posts only to legitimate Xiaohongshu endpoints. If you cannot obtain or verify the missing modules and code provenance, avoid using with real account credentials.
功能分析
Type: OpenClaw Skill
Name: xiaohongshu-full-auto
Version: 1.0.0
The skill bundle provides a legitimate automation workflow for Xiaohongshu content creation, including trend scraping, AI content generation, and automated publishing. The code is well-structured, uses safe practices like `yaml.safe_load`, and contains no evidence of malicious intent, data exfiltration, or unauthorized execution. While it requires sensitive credentials (XIAOHONGSHU_COOKIE) and utilizes a third-party API (api.fakey.top) for scraping, these are standard requirements for the stated functionality and are handled within the user's local environment. No prompt injection or obfuscation was found in the documentation or scripts (full_auto.py, get_hot_topics.py).
能力评估
Purpose & Capability
The skill's name/description promise full-chain posting to Xiaohongshu, which would legitimately require Xiaohongshu credentials and a publishing implementation — the SKILL.md and config-example list XIAOHONGSHU_COOKIE and BUSINESS_ID and mention Feishu tokens, but the registry metadata declares no required env/primary credential. More critically, the main script (full_auto.py) imports generate_content.py, generate_cover.py and publish.py which are NOT present in the bundle. That makes the package incoherent: it claims to perform publishing but does not include the publishing/generation modules or declare where they come from.
Instruction Scope
SKILL.md instructs the agent to fetch hot topics, generate content and covers, and call Xiaohongshu/Feishu APIs to publish and record results. Those instructions include reading a config file, writing local logs, and performing network calls. That scope is expected for a publisher skill, but the instructions require secrets (cookies/business_id, optional OpenAI key) that are not declared in the registry metadata. The instructions also reference files/scripts (generate_content.py, publish.py, generate_cover.py) missing from the package, creating a gap between what the agent is told to do and what it actually can do.
Install Mechanism
No install spec (instruction-only style) — lower risk from installations. SKILL.md requests pip install requests, beautifulsoup4, markdownify which are reasonable for scraping/text processing. However the get_hot_topics implementation calls an external third‑party endpoint (https://api.fakey.top/xiaohongshu/hot) instead of an official Xiaohongshu API which is unexpected and introduces a network dependency to an untrusted domain.
Credentials
The package metadata lists no required env vars, but SKILL.md and config-example explicitly require XIAOHONGSHU_COOKIE and XIAOHONGSHU_BUSINESS_ID and optionally OPENAI_API_KEY and Feishu tokens. This mismatch is a red flag: the runtime needs sensitive credentials to publish on behalf of a user, yet those were not declared. The skill would therefore request secrets at runtime without the package metadata signalling that.
Persistence & Privilege
The skill is not marked always:true and uses normal user-invocable/autonomous defaults. It writes a local published.jsonl log but does not request persistent system-wide privileges or attempt to modify other skills' configs. No other elevated persistence or privileged behaviour is present in the bundle.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install xiaohongshu-full-auto - 安装完成后，直接呼叫该 Skill 的名称或使用
/xiaohongshu-full-auto触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
xiaohongshu-full-auto v1.0.0
- 初始版本发布，提供小红书全链路内容创作自动化，从选题到发布全流程一站式完成
- 支持自动抓取小红书热榜、智能匹配垂类选题、生成小红书风格文案及 AI 封面图
- 集成原生API自动发布功能，发布结果自动记录日志
- 提供全自动、半自动、仅辅助三种内容创作模式
- 详细支持环境配置、依赖安装及分步/全流程使用
- 内置小红书写作规范与企业级可靠性设计
元数据
常见问题
xiaohongshu-full-auto 是什么？
🚀 小红书全链路自动化自媒体工作流，从热点抓取 → 选题分析 → 文案生成 → 封面图生成 → 自动发布，一条龙全自动搞定小红书内容创作。适合自媒体博主、副业玩家、内容工作室批量生产小红书内容。触发关键词："全自动小红书", "小红书创作", "小红书自动发布", "小红书热榜", "批量做小红书", "xia... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 89 次。
如何安装 xiaohongshu-full-auto？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install xiaohongshu-full-auto」即可一键安装，无需额外配置。
xiaohongshu-full-auto 是免费的吗？
是的，xiaohongshu-full-auto 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
xiaohongshu-full-auto 支持哪些平台？
xiaohongshu-full-auto 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 xiaohongshu-full-auto？
由 guanlansss（@guanlansss）开发并维护，当前版本 v1.0.0。
推荐 Skills