← 返回 Skills 市场
286
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install vidu-video-publisher
功能描述
Automatically publish videos to Xiaohongshu, Douyin, WeChat Channels, and Kuaishou with platform-tailored titles and tags via browser automation.
安全使用建议
Key points before installing:
- The skill advertises 'Vidu API' and automated AI video generation but the code only automates a browser to upload existing local videos; if you expected an API-based or auto-generation pipeline, this skill does not provide it. Ask the author for clarification or an updated README.
- The package uses Playwright but provides no install instructions or dependency declarations; you will need to install python-playwright and browser binaries yourself. Prefer running this in an isolated environment or VM to limit risk.
- The scripts will access local video files you provide and reuse browser_state.json (cookies/auth). Do not point it at videos or browser state from accounts with sensitive access. Inspect browser_state.json contents before reuse and avoid sharing it.
- The tool requires you to be logged into target platforms (it may prompt for manual login). Be aware of platform terms of service and content-moderation risk when publishing sensitive material (e.g., political/military news).
- If you want to proceed, request from the publisher: (1) a clear install spec (requirements.txt or install script), (2) confirmation whether any external Vidu API exists and its endpoint/auth, and (3) assurance about how browser_state.json is used/saved. If those are not provided, treat the package as untrusted and run only in an isolated test environment.
功能分析
Type: OpenClaw Skill
Name: vidu-video-publisher
Version: 1.0.1
The bundle provides a video publishing tool that utilizes Playwright for browser automation on platforms like Xiaohongshu, Douyin, and Kuaishou. It is classified as suspicious due to high-risk capabilities that are plausibly needed for its stated purpose but lack robust security controls, specifically the automated control of browser sessions and the storage of sensitive authentication states in a local file ('browser_state.json' in scripts/browser_publisher.py). Additionally, the tool uses subprocess execution to coordinate between scripts (scripts/interactive_publish.py), which, while implemented using argument lists, remains a sensitive capability in an agent-led environment.
能力评估
Purpose & Capability
The skill name/description advertise a Vidu API and automated 24-hour AI video generation and one‑click publishing. The code, SKILL.md, and README do not call any 'Vidu' API, do not generate videos, and only implement browser automation to upload existing local video files. This mismatch (advertised API/auto-generation vs actual local-file publishing via Playwright) is an incoherence a user should note.
Instruction Scope
SKILL.md instructs the agent to open a browser, reuse or create login state, upload user-supplied video files, and fill titles/tags; that matches the code. It requires access to local video paths and to browser_state.json (Playwright storage state). The instructions do not ask the agent to read unrelated system secrets, but they do rely on reusing browser login state which may expose account cookies if mishandled.
Install Mechanism
There is no install spec despite the code importing and using Playwright (playwright.async_api) and expecting a browser runtime. Required dependencies (python-playwright, and browser binaries) are not declared. That omission is disproportionate: users will need to install Playwright and browsers manually; an install step should be provided and audited.
Credentials
The skill declares no environment variables or credentials (which is consistent with browser-based automation). However, it will access local files (the user-supplied video path) and a storage_state file (browser_state.json) containing browser authentication state — access to those should be considered sensitive. No unrelated credentials are requested.
Persistence & Privilege
always:false and model invocation are default. The skill does not request permanent platform-wide privileges. It does read/use (and may write, depending on Playwright behavior) browser_state.json to persist login sessions; that is normal for browser automation but worth noting.
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 vidu-video-publisher - 安装完成后,直接呼叫该 Skill 的名称或使用
/vidu-video-publisher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
v1.0.1
Initial release of video-publisher.
- 一站式视频发布工具,支持小红书、抖音、视频号、快手等主流平台
- 自动根据平台调性生成吸引人的标题和标签
- 支持多平台、批量视频发布流程
- 展示并允许修改标题与标签后再自动发布
- 明确平台视频参数要求、账号登录与内容审核须知
- 完善的错误处理和平台限制说明
元数据
常见问题
24-hour news is automatically generated into AI videos and can be published with one click, provided by the Vidu API. 是什么?
Automatically publish videos to Xiaohongshu, Douyin, WeChat Channels, and Kuaishou with platform-tailored titles and tags via browser automation. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 286 次。
如何安装 24-hour news is automatically generated into AI videos and can be published with one click, provided by the Vidu API.?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vidu-video-publisher」即可一键安装,无需额外配置。
24-hour news is automatically generated into AI videos and can be published with one click, provided by the Vidu API. 是免费的吗?
是的,24-hour news is automatically generated into AI videos and can be published with one click, provided by the Vidu API. 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
24-hour news is automatically generated into AI videos and can be published with one click, provided by the Vidu API. 支持哪些平台?
24-hour news is automatically generated into AI videos and can be published with one click, provided by the Vidu API. 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 24-hour news is automatically generated into AI videos and can be published with one click, provided by the Vidu API.?
由 Vidu AI(@x-jihua)开发并维护,当前版本 v1.0.1。
推荐 Skills