← Back to Skills Marketplace
253
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install tl-video
Description
Generate videos using TensorsLab's AI video generation models. Supports text-to-video and image-to-video generation with automatic prompt enhancement, progre...
Usage Guidance
This bundle appears to be a legitimate client for TensorsLab's video API, but do the following before installing or using it: 1) Note the registry metadata omits the required TENSORSLAB_API_KEY — the script will fail without that key; verify the developer/source and correct metadata before trusting the skill. 2) Understand that any local image files you pass will be uploaded to api.tensorslab.com; do not upload sensitive or private images. 3) The script disables proxies for its requests session (it sets session.proxies to empty strings), which can bypass local proxy monitoring — verify you are comfortable with that network behavior or inspect/modify the code to remove that line. 4) Keep your TENSORSLAB_API_KEY secret and monitor billing/quotas on your TensorsLab account (the API may charge or consume credits). 5) Check the API host strings in the included docs (there are minor domain inconsistencies/typos such as tensorai.tensorslab.com vs tensorslab.tensorslab.com) and confirm the correct official endpoints before sending production data. If you need higher assurance, ask the publisher for a canonical source/homepage and a clear declaration of required env vars and network endpoints.
Capability Analysis
Type: OpenClaw Skill
Name: tl-video
Version: 0.1.0
The skill bundle is a legitimate tool for generating AI videos using the TensorsLab API. The Python script (scripts/tensorslab_video.py) implements standard API client logic, including multipart form-data uploads for images, task status polling, and secure file downloading to a dedicated local directory (./tensorslab_output/). The instructions in SKILL.md are well-structured, include safety checks for environment variables, and lack any malicious prompt-injection attempts or unauthorized commands.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, API reference, and bundled Python client all align: this is a client for TensorsLab video-generation and reasonably needs a TENSORSLAB_API_KEY and network access to api.tensorslab.com. However, the registry metadata lists no required environment variables while both SKILL.md and the script explicitly require TENSORSLAB_API_KEY — this metadata mismatch is inconsistent and should be corrected/clarified.
Instruction Scope
The runtime instructions and bundled script stick to the stated task: they call the TensorsLab API, upload optional local source images (if provided), poll status, and download resulting videos to ./tensorslab_output. This behavior is expected for image-to-video/text-to-video. Important privacy-related behavior: any local images you pass will be uploaded to the remote service, and the script disables session proxies (see code) which may bypass local proxy/network inspection — users should be aware of these facts.
Install Mechanism
There is no install spec that downloads remote code; the package is instruction + included Python script. The only dependency is the common 'requests' library which the SKILL.md instructs to pip install. No unusual external download URLs or archive extracts are present in the bundled files.
Credentials
The script and SKILL.md require a TENSORSLAB_API_KEY environment variable (used as a bearer token). That is proportionate to the declared purpose, but the registry metadata incorrectly states 'Required env vars: none' and 'Primary credential: none' — this is a material inconsistency. Also the script sets requests.Session().proxies to empty strings (disables proxies for the session), which is an unusual network-related choice that could affect routing/monitoring.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system settings, and is user-invocable. It runs as an on-demand client; no elevated/persistent privileges are requested by the bundle.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tl-video - After installation, invoke the skill by name or use
/tl-video - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial release of TensorsLab video generation skill.
- Supports text-to-video and image-to-video generation using TensorsLab's API.
- Automatic prompt enhancement for cinematic and realistic results.
- Progress tracking with regular status updates during multi-minute generation.
- Output management: downloads results to configurable local directory.
- Supports multiple models, aspect ratios, durations, and resolutions.
- User-friendly messages for authentication setup and common errors.
Metadata
Frequently Asked Questions
What is Tensorslab Video?
Generate videos using TensorsLab's AI video generation models. Supports text-to-video and image-to-video generation with automatic prompt enhancement, progre... It is an AI Agent Skill for Claude Code / OpenClaw, with 253 downloads so far.
How do I install Tensorslab Video?
Run "/install tl-video" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Tensorslab Video free?
Yes, Tensorslab Video is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Tensorslab Video support?
Tensorslab Video is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Tensorslab Video?
It is built and maintained by bob (@bob5-tensorslab); the current version is v0.1.0.
More Skills