← 返回 Skills 市场
VidAU Video Generator
作者
bigjoehuang
· GitHub ↗
· v1.0.8
· MIT-0
297
总下载
0
收藏
0
当前安装
9
版本数
在 OpenClaw 中安装
/install vidau-video-generator
功能描述
Use Vidau Open API to generate short videos with Veo3, Sora2, and other models, or query account credits. Register at superaiglobal.com and configure API Key.
安全使用建议
This skill appears to do what it says: call Vidau/SuperAI APIs to generate videos and check credits. Before installing, consider: 1) you must provide VIDAU_API_KEY (or store it in your OpenClaw config) for the skill to work; 2) the skill will create log and cache files in your home directory (~/.vidau_api.log, ~/.vidau_models_cache.json, ~/.vidau_asset_cache.json) and will read ~/.openclaw/openclaw.json as a fallback to find an API key — if you are uncomfortable with those files, set the optional env vars (VIDAU_API_LOG, VIDAU_MODELS_CACHE, VIDAU_ASSET_CACHE) to control paths or avoid using the skill; 3) the skill communicates only with api.superaiglobal.com (per the code) — if you require stricter network controls, review network destinations before enabling. Overall the package is internally consistent with its stated purpose.
功能分析
Type: OpenClaw Skill
Name: vidau-video-generator
Version: 1.0.8
The Vidau Video Generator skill bundle is a legitimate integration for the Vidau Open API. It provides scripts for video generation, credit querying, and asset management, using standard Python libraries without external dependencies. Security review shows safe handling of API keys (retrieved from environment variables or standard OpenClaw config), transparent logging to a local file (~/vidau_api.log) that excludes sensitive headers, and functional local caching for assets and model metadata. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
Name/description match the implemented behavior: scripts call https://api.superaiglobal.com endpoints to query models, create tasks, upload assets, and check credits. The single required credential (VIDAU_API_KEY) is appropriate for the stated functionality.
Instruction Scope
Runtime instructions and the scripts stay within the stated purpose (creating/querying video tasks). The code will attempt to read the OpenClaw config (~/.openclaw/openclaw.json) as a fallback for the API key if VIDAU_API_KEY isn't set; it also creates cache and log files in the user's home. These file accesses are reasonable for convenience but are not listed in the skill's declared config paths.
Install Mechanism
No install spec is provided (instruction-only with shipped scripts). Nothing is downloaded from external or untrusted URLs at install time. The scripts use only the Python standard library and expect Python 3 on PATH — consistent with the SKILL.md environment checks.
Credentials
The skill declares one required env var (VIDAU_API_KEY), which is appropriate. The code also recognizes optional environment variables (VIDAU_API_LOG to override log path, VIDAU_MODELS_CACHE and VIDAU_ASSET_CACHE to override cache paths) but these are not listed in requires.env; the agent will create files (~/.vidau_api.log, ~/.vidau_models_cache.json, ~/.vidau_asset_cache.json) in the user's home by default.
Persistence & Privilege
The skill is not always-enabled and uses normal, on-demand invocation. It does not request system-wide privileges, does not alter other skills' configs, and only writes its own caches/logs in the user's home directory.
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 vidau-video-generator - 安装完成后，直接呼叫该 Skill 的名称或使用
/vidau-video-generator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
v1.0.8
- Bumped version to 1.0.8.
- No functional changes; documentation update only (SKILL.md updated).
v1.0.7
Version 1.0.7 — Documentation update only
- Updated version number in SKILL.md from 1.0.6 to 1.0.7.
- No functional or behavioral changes; documentation content remains the same otherwise.
v1.0.6
**Changelog for vidau-video-generator 1.0.6**
- Added explicit output formatting instructions: always display video and thumbnail URLs in a code block, verbatim.
- Updated model list querying: recommend using --no-cache to refresh model capabilities after new releases.
- Changed task polling guidance: use `wait_task.py` by default; only use `query_task.py` for scheduled polling platforms.
- Documentation and homepage links updated to point to English versions where possible.
- Clarified and reorganized workflow and best-practices for error reporting and result display.
v1.0.5
- Version bump to 1.0.5.
- Documentation updates in SKILL.md.
- No behavioral changes to code or scripts.
v1.0.4
**Skill 1.0.4—adds model capability validation and a new model query script**
- Added new script: scripts/query_models.py to query available video models and their capabilities.
- New workflow step: Validate user’s requested parameters (resolution, ratio, duration, generate_audio) against the selected model’s allowed values before creating a video task.
- If a user’s parameters do not match the model’s supported capabilities, the skill informs the user and does not submit the task.
- Model/capability info is cached for 10 minutes, reducing redundant API calls.
- Documentation updated to describe the new script and the stricter validation process.
v1.0.3
- Version updated to 1.0.3.
- Documentation refreshed to reflect new version number.
- No workflow, parameter, or usage instructions were changed.
v1.0.2
- Added support for uploading local images/videos to Vidau via the new `scripts/upload_asset.py` script.
- Now supports local file uploads when the user only has local assets (no URL); asset URLs are automatically cached to avoid duplicate uploads.
- Documentation updated to include the new upload workflow and script usage.
- No breaking changes to generation or credit query workflows.
v1.0.1
- Updated skill name in SKILL.md from "vidau" to "vidau video generator".
- No changes to functionality or APIs; documentation edit only.
- All workflow, script, and usage details remain unchanged.
v1.0.0
Initial release of Vidau Video Generator skill.
- Generate short videos using Vidau Open API with models like Veo3, Sora2, etc., or query account credits.
- Requires configuration of VIDAU_API_KEY; user must register at superaiglobal.com to obtain one.
- Includes scripts to create video tasks, poll task status/results, and check credit balance.
- Responds to user queries in their preferred language (matches input language).
- Provides clear error handling and prerequisites, including Python 3 environment checks.
- Includes a detailed workflow, parameters, and supported models for video generation.
元数据
常见问题
VidAU Video Generator 是什么？
Use Vidau Open API to generate short videos with Veo3, Sora2, and other models, or query account credits. Register at superaiglobal.com and configure API Key. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 297 次。
如何安装 VidAU Video Generator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vidau-video-generator」即可一键安装，无需额外配置。
VidAU Video Generator 是免费的吗？
是的，VidAU Video Generator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
VidAU Video Generator 支持哪些平台？
VidAU Video Generator 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 VidAU Video Generator？
由 bigjoehuang（@bigjoehuang）开发并维护，当前版本 v1.0.8。
推荐 Skills