← Back to Skills Marketplace
Video Generation Ai
by
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
111
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install video-generation-ai
Description
Turn a short text description of a product demo scene into 1080p AI generated videos just by typing what you need. Whether it's generating short videos from...
Usage Guidance
This skill generally behaves like a cloud video generator: it will send uploaded media and prompts to https://mega-api-prod.nemovideo.ai and use a NEMO_TOKEN (it can create an anonymous one if you don't supply one). Before installing, consider: 1) Where will the skill store the anonymous token/session ID on disk? Confirm whether it writes to ~/.config/nemovideo/ (the SKILL.md mentions that path but the registry metadata does not). 2) If you care about privacy, do not upload sensitive images/scripts — uploads go to a third party. 3) Prefer providing your own scoped NEMO_TOKEN (and rotate it) rather than allowing the skill to auto-create persistent tokens. 4) Ask the publisher for a homepage/privacy policy and clarify data retention and deletion of uploaded media and anonymous tokens. 5) If you need the agent not to act autonomously, control invocation policies in your agent rather than relying on the skill. If the maintainer cannot explain the config-path/token storage discrepancy and how/where credentials are stored, treat the mismatch as a red flag and avoid installing.
Capability Analysis
Type: OpenClaw Skill
Name: video-generation-ai
Version: 1.0.0
The video-generation-ai skill is a legitimate integration for a cloud-based video generation service (nemovideo.ai). The SKILL.md file provides clear instructions for the agent to manage authentication via NEMO_TOKEN, handle sessions, and interact with specific API endpoints for uploading media and rendering videos. There are no signs of data exfiltration, malicious execution, or unauthorized system access; the instructions even include security best practices like hiding raw API tokens from the user. All network activity is directed to the stated backend (mega-api-prod.nemovideo.ai).
Capability Assessment
Purpose & Capability
The skill is a cloud video generator and requests a single service credential (NEMO_TOKEN) and network access to a nemo-video API — this is proportionate to the stated purpose. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata earlier listed no required config paths; that discrepancy is unexplained.
Instruction Scope
Instructions direct the agent to obtain an anonymous token if NEMO_TOKEN is absent, create sessions, upload media, read SSE streams, and poll export endpoints — all expected for a cloud render pipeline. The skill also instructs to 'auto-detect' the X-Skill-Platform header from an install path (which could implicitly ask the agent to inspect the environment/install location). The instructions do not request unrelated system files, but they do imply storing tokens/session IDs locally without a clear, declared storage location.
Install Mechanism
No install spec or code files are present (instruction-only). Nothing will be downloaded or written by an installation step defined in the registry, which reduces install-time risk.
Credentials
Only one credential (NEMO_TOKEN) is declared, which fits the use-case. But the SKILL.md claims it may generate and persist an anonymous token and references a config path (~/.config/nemovideo/) in the frontmatter; the registry metadata does not declare that config path. Storing credentials or session IDs to disk would require explicit disclosure. Also the skill mandates sending Authorization: Bearer <NEMO_TOKEN> on every request and adding three custom attribution headers — these are operationally reasonable but mean the token will be routinely sent to the third-party domain.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. It does, however, imply persistence by storing session_id and possibly an anonymous token for 7-day validity; where these values are stored is not clearly declared. No operations that modify other skills or system-wide settings are described.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-generation-ai - After installation, invoke the skill by name or use
/video-generation-ai - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of Video Generation AI.
- Generate 1080p videos from text prompts or images in 1–3 minutes.
- Automatic backend connection and token handling, with 100 free credits upon first use.
- Supports quick text-to-video, file uploads, and export to a variety of formats (mp4, mov, gif, etc.).
- Handles workflows like quick edits, batching, and iterative refinements with live session state.
- Clear error messages and onboarding, with guidance for exports, credits, and supported formats.
Metadata
Frequently Asked Questions
What is Video Generation Ai?
Turn a short text description of a product demo scene into 1080p AI generated videos just by typing what you need. Whether it's generating short videos from... It is an AI Agent Skill for Claude Code / OpenClaw, with 111 downloads so far.
How do I install Video Generation Ai?
Run "/install video-generation-ai" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Generation Ai free?
Yes, Video Generation Ai is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Generation Ai support?
Video Generation Ai is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Generation Ai?
It is built and maintained by whitejohnk-26 (@whitejohnk-26); the current version is v1.0.0.
More Skills