← Back to Skills Marketplace
video
by
TobeyRebecca
· GitHub ↗
· v1.0.0
· MIT-0
96
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install toby-video
Description
Generate video using SkillBoss API Hub (video generation, auto-routed via /v1/pilot).
Usage Guidance
This skill appears to do what it claims (call SkillBoss API Hub and download an MP4), but the package metadata is inconsistent: the script requires SKILLBOSS_API_KEY and Python + requests, yet the registry entry does not list the API key or Python dependency. Before installing/using: 1) Verify the publisher and that you trust api.skillbossai.com. 2) Ensure you set SKILLBOSS_API_KEY in a safe scope (this key can be abused to consume the account's quota). 3) Confirm your environment has the 'uv' runner, Python >=3.10, and the 'requests' package. 4) Be aware the script will upload prompt text and any reference images you provide to SkillBoss and will print a MEDIA: local path (which chat providers may expose). If you cannot verify the publisher or do not want to share prompts/images with SkillBoss, do not install it. To improve safety, ask the publisher to correct registry metadata to declare SKILLBOSS_API_KEY as the primary credential and to list Python/requests as runtime requirements.
Capability Analysis
Type: OpenClaw Skill
Name: toby-video
Version: 1.0.0
The skill bundle provides a straightforward utility for generating videos using the SkillBoss API Hub. The script `scripts/generate_video.py` functions as described, taking a text prompt and optional local images (encoded as base64) to request a video from `https://api.skillbossai.com/v1/pilot`. It then downloads the resulting file to a user-specified path. No evidence of data exfiltration, malicious code execution, or harmful prompt injection was found.
Capability Tags
Capability Assessment
Purpose & Capability
The skill's name, description, SKILL.md, and script all align: it calls SkillBoss API Hub (/v1/pilot) to generate video and downloads the result. However, the registry metadata omitted the required SKILLBOSS_API_KEY (the script reads os.environ['SKILLBOSS_API_KEY']), and the script requires Python >=3.10 and the requests package which are not declared in the registry's required binaries/env/dependencies. This metadata mismatch is unexpected.
Instruction Scope
SKILL.md instructs running the included script via the uv binary and documents the SKILLBOSS_API_KEY. The runtime actions are scoped to: POST to /v1/pilot, download the returned video URL, read optional local image files (up to 3), base64-encode them, and write an MP4 file. It does not read unrelated system files, other env vars, or other skill configs. It prints a MEDIA: line to allow automatic attachment; be aware that that will expose the local path to chat providers.
Install Mechanism
This is instruction-only (no install spec). That's lower risk, but the script declares runtime Python and a requests dependency in comments; the SKILL.md only requires the 'uv' binary. The skill will fail or behave unexpectedly if Python/requests are not present — the absence of an install step or explicit dependency declaration is a packaging concern.
Credentials
The script requires a single API credential (SKILLBOSS_API_KEY) which is proportionate to the stated purpose. However, the registry metadata lists no required env vars while SKILL.md explicitly documents SKILLBOSS_API_KEY and the script reads it directly. The skill's primary credential field is blank in the registry; that mismatch is a security/packaging inconsistency that should be corrected before use.
Persistence & Privilege
The skill does not request persistent/always-on presence (always: false) and does not modify other skills or global agent settings. Autonomous invocation is allowed by default but is not combined here with broad privileged access.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install toby-video - After installation, invoke the skill by name or use
/toby-video - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of veo: generate video clips using the SkillBoss API Hub, auto-routed to the best available model.
- Supports specifying video duration, aspect ratio, and optional model hints.
- Provides image-to-video capability with input image option.
- Requires SKILLBOSS_API_KEY environment variable.
- Output videos are in MP4 format; script prints MEDIA: line for easy attachment.
Metadata
Frequently Asked Questions
What is video?
Generate video using SkillBoss API Hub (video generation, auto-routed via /v1/pilot). It is an AI Agent Skill for Claude Code / OpenClaw, with 96 downloads so far.
How do I install video?
Run "/install toby-video" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is video free?
Yes, video is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does video support?
video is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created video?
It is built and maintained by TobeyRebecca (@tobeyrebecca); the current version is v1.0.0.
More Skills