← Back to Skills Marketplace
115
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install video-generation-online
Description
Turn a short text description of a product demo scene into 1080p ready-to-share videos just by typing what you need. Whether it's generating videos from text...
Usage Guidance
This skill will upload your prompts and any files you provide to an external service (mega-api-prod.nemovideo.ai) and will request or mint short-lived tokens to operate. That behavior is consistent with a cloud video-generation tool, but you should: (1) avoid sending sensitive content (private data, secrets, PII) to the service; (2) prefer using an anonymous token or a dedicated limited-scope token rather than a long-lived production token; (3) ask the publisher for the official homepage, privacy policy, and who runs the mega-api-prod.nemovideo.ai domain before installing; (4) ask the author to clarify the config path behavior (frontmatter lists ~/.config/nemovideo/ but registry metadata did not) and to enumerate the exact headers and data the skill will send. Because this is instruction-only with no packaged code, there's nothing else to audit beyond SKILL.md — treat network/transmit behavior and metadata inconsistencies as the main risk factors.
Capability Analysis
Type: OpenClaw Skill
Name: video-generation-online
Version: 1.0.0
The skill is a functional integration for an AI video generation service hosted at nemovideo.ai. It provides detailed instructions for the agent to manage sessions, upload media, and poll for rendered video files via a cloud API. The logic includes standard authentication flows (including an anonymous token fallback), error handling, and platform attribution. No malicious indicators such as exfiltration of sensitive local credentials, unauthorized command execution, or harmful prompt injection were identified; the instructions specifically advise the agent not to expose tokens or raw API output to the user.
Capability Assessment
Purpose & Capability
Name/description (text→video) match the runtime instructions (upload, SSE, render, export). Requiring NEMO_TOKEN is expected. However the skill frontmatter lists a config path (~/.config/nemovideo/) while the registry metadata reported none — this mismatch is inconsistent. The skill also provides an anonymous-token fallback if NEMO_TOKEN is absent, which is plausible but makes the declared 'required env var' semantics a bit ambiguous.
Instruction Scope
SKILL.md explicitly instructs the agent to: check environment for NEMO_TOKEN, optionally POST to an external auth endpoint to obtain an anonymous token, create sessions, upload files (multipart or URL), and stream SSE responses. All of this is coherent with video generation. The important runtime behavior is that user prompts/files are sent to https://mega-api-prod.nemovideo.ai — this is expected but has privacy implications. The instructions are somewhat vague about the exact attribution headers (mentions 'three attribution headers above') and about how long tokens/sessions are persisted.
Install Mechanism
Instruction-only skill with no install spec or code files — lowest install risk. Nothing written to disk by an install step in the package itself.
Credentials
Only one declared env var (NEMO_TOKEN) — appropriate for a cloud API client. However the SKILL.md will obtain an anonymous token by calling the service if NEMO_TOKEN is missing, so the practical need for providing your own token is optional. The frontmatter's mention of a config path (~/.config/nemovideo/) (missing from registry metadata) suggests the skill may try to read user config for attribution — this should be clarified before trusting it with sensitive config files.
Persistence & Privilege
No 'always: true'. The skill instructs keeping session_id in memory for operations but does not request system-wide persistent privileges. Autonomous invocation is allowed by default but not combined here with elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-generation-online - After installation, invoke the skill by name or use
/video-generation-online - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of Video Generation Online: create and download 1080p videos from text prompts or images in 1–2 minutes.
- Automatic cloud backend setup with secure, token-based authentication (100 free credits for new users).
- Supports text-to-video, quick edits, and batch/bulk video processing workflows without complex timelines or export steps.
- File uploads, session state, exports, and credits management streamlined via one unified interface.
- Includes clear error handling, supported formats (mp4, mov, jpg, etc.), and detailed prompt/action routing.
Metadata
Frequently Asked Questions
What is Video Generation Online?
Turn a short text description of a product demo scene into 1080p ready-to-share videos just by typing what you need. Whether it's generating videos from text... It is an AI Agent Skill for Claude Code / OpenClaw, with 115 downloads so far.
How do I install Video Generation Online?
Run "/install video-generation-online" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Generation Online free?
Yes, Video Generation Online is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Generation Online support?
Video Generation Online is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Generation Online?
It is built and maintained by mory128 (@mory128); the current version is v1.0.0.
More Skills