← Back to Skills Marketplace
Shinewilzhang Video Generate
by
shinewilzhang
· GitHub ↗
· v1.0.0
· MIT-0
125
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install shinewilzhang-video-generate
Description
使用 video_generate.py 脚本生成视频,需要提供文件名和 prompt,可选提供首帧图片(URL或本地路径)。
Usage Guidance
This skill likely does what it says (calls an Ark content-generation API and downloads a video), but there are several practical and privacy issues to consider before installing or running it:
- Credentials: The manifest omitted required env vars. You must set MODEL_VIDEO_API_KEY or ARK_API_KEY for the script to work. Do not provide sensitive production credentials if you are unsure where requests are sent.
- Dependency: The script imports volcenginesdkarkruntime but gives no install steps. Ensure you install the correct SDK (preferably from a trusted source) in an isolated environment before running.
- Local files may be uploaded: If you pass a local image path as the first_frame argument, the script base64-encodes the file and sends it to the Ark API. Do not use private images or sensitive files unless you understand the provider's data handling and privacy policy.
- Documentation mismatch: SKILL.md claims a VOLCENGINE_* fallback to obtain an Ark API key, but the code does not implement that. Ask the author to clarify or update the docs.
Recommendations: run this in a sandbox/VM, review and pin the Ark SDK package before installing, set a throwaway API key or account for testing, avoid passing local files containing sensitive data, and request that the skill manifest be updated to declare required env vars and dependency installation steps. If you require stronger assurance, ask the publisher to explain the VOLCENGINE fallback and to provide a reproducible install/run guide.
Capability Assessment
Purpose & Capability
The skill's name/description match the code (a script that calls the Ark content-generation API and downloads the result). However the registry metadata declared no required environment variables or credentials while both SKILL.md and the script expect an Ark-style API key (MODEL_VIDEO_API_KEY or ARK_API_KEY). The omission in the manifest is inconsistent.
Instruction Scope
SKILL.md claims the skill will fall back to VOLCENGINE_ACCESS_KEY/VOLCENGINE_SECRET_KEY to obtain an Ark API key, but the script does not implement that fallback (it only checks MODEL_VIDEO_API_KEY or ARK_API_KEY). The script will read local image files (if provided) and convert them to base64, then include that data in the request to the external Ark API — i.e., local file contents may be transmitted to a third party. SKILL.md documents the first-frame behavior, but the false claim about VOLCENGINE keys and the unadvertised transmission of local files are scope mismatches that matter for privacy.
Install Mechanism
There is no install spec. The script imports volcenginesdkarkruntime.Ark, but the skill provides no instructions or dependencies list (e.g., pip install) to ensure that SDK is present. That omission is a usability/security gap (missing explicit dependency installation), but there is no external download or installer in the manifest.
Credentials
The registry metadata lists no required env vars, but both SKILL.md and the code require an API key via MODEL_VIDEO_API_KEY or ARK_API_KEY. SKILL.md further claims a VOLCENGINE_* fallback which the code does not perform. The skill therefore asks for credentials in practice (API key used to contact Ark) without declaring them up front. Also, providing a local image causes the script to read and send file contents to the external API — this is expected for image-driven generation but should be highlighted as sensitive data exposure.
Persistence & Privilege
The skill does not request permanent/always-on inclusion, does not modify other skills or system configs, and does not persist credentials itself. Normal autonomous invocation is allowed but not combined with other elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install shinewilzhang-video-generate - After installation, invoke the skill by name or use
/shinewilzhang-video-generate - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
shinewilzhang-video-generate 1.0.0
- Initial release.
- Generate videos from prompt text using the video_generate.py script.
- Optionally set the first video frame via image URL or local image file.
- API credentials are read from environment variables or generated as needed.
- Console outputs video download link; file saved to specified location.
- Includes clear usage instructions and examples.
Metadata
Frequently Asked Questions
What is Shinewilzhang Video Generate?
使用 video_generate.py 脚本生成视频,需要提供文件名和 prompt,可选提供首帧图片(URL或本地路径)。 It is an AI Agent Skill for Claude Code / OpenClaw, with 125 downloads so far.
How do I install Shinewilzhang Video Generate?
Run "/install shinewilzhang-video-generate" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Shinewilzhang Video Generate free?
Yes, Shinewilzhang Video Generate is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Shinewilzhang Video Generate support?
Shinewilzhang Video Generate is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Shinewilzhang Video Generate?
It is built and maintained by shinewilzhang (@shinewilzhang); the current version is v1.0.0.
More Skills