← 返回 Skills 市场
Ai Video Gen
作者
rhanbourinajd
· GitHub ↗
· v1.0.0
7931
总下载
7
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ai-video-gen
功能描述
End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg editing.
安全使用建议
Install only if you are comfortable sending prompts and narration to cloud AI providers and using paid API keys. Use a virtual environment, keep .env out of version control, avoid sensitive prompts/media, run scripts in a private working directory, and verify provider support before relying on Runway, ElevenLabs, or the missing helper scripts.
功能分析
Type: OpenClaw Skill
Name: ai-video-gen
Version: 1.0.0
The OpenClaw AgentSkills skill bundle for AI video generation appears benign. All Python scripts utilize `subprocess.run` with a list of arguments for executing FFmpeg, which is a secure method that mitigates shell injection risks. API keys are loaded from environment variables, and network requests are directed to legitimate AI service providers (OpenAI, Replicate, LumaAI). File system operations are limited to creating output directories and saving generated media, aligning with the skill's stated purpose. No evidence of data exfiltration, persistence mechanisms, obfuscation, or prompt injection attempts in the markdown files was found. The use of `ffmpeg -safe 0` in `images_to_video.py` is noted, but its context within the script (programmatic construction of a file list with absolute paths) does not indicate malicious intent.
能力评估
Credentials
Network access, API keys, FFmpeg execution, and media file writes fit the purpose, but downloads from provider-returned URLs have no host, scheme, type, timeout, or size checks, and images_to_video.py uses a predictable filelist.txt in the working directory.
Install Mechanism
Installation uses ordinary pip dependencies, but versions are only minimum-pinned and docs reference missing setup assets such as .env.example and setup.bat.
Instruction Scope
The scripts are user-invoked and I found no prompt hijacking, memory poisoning, persistence instructions, or hidden role changes; however, third-party prompt/media processing is not clearly disclosed as a privacy boundary.
Persistence & Privilege
No services, startup hooks, scheduled tasks, tool replacement, or cross-session persistence were found; credential use is limited to environment variables or .env loading for the named providers.
Purpose & Capability
The core purpose is coherent, but the artifacts advertise Runway, ElevenLabs, multi_scene.py, edit_video.py, local/free options, and richer editing capabilities that are not shipped or implemented; selecting Runway falls back to Luma.
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 ai-video-gen - 安装完成后，直接呼叫该 Skill 的名称或使用
/ai-video-gen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
- Initial release of ai-video-gen skill: end-to-end AI video generation from text prompts.
- Supports multiple image and video generation models (OpenAI DALL-E, Replicate, LumaAI, Runway).
- Includes voice-over (OpenAI TTS, ElevenLabs) and advanced FFmpeg video editing.
- Provides quick start guides, usage examples, and workflow customization (free/budget and paid/quality modes).
- Comprehensive setup instructions for API keys and dependencies.
元数据
常见问题
Ai Video Gen 是什么？
End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg editing. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 7931 次。
如何安装 Ai Video Gen？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-video-gen」即可一键安装，无需额外配置。
Ai Video Gen 是免费的吗？
是的，Ai Video Gen 完全免费（开源免费），可自由下载、安装和使用。
Ai Video Gen 支持哪些平台？
Ai Video Gen 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 Ai Video Gen？
由 rhanbourinajd（@rhanbourinajd）开发并维护，当前版本 v1.0.0。
推荐 Skills