← Back to Skills Marketplace
Text To Video Json Prompt
by
francemichaell-15
· GitHub ↗
· v1.0.0
· MIT-0
91
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install text-to-video-json-prompt
Description
Skip the learning curve of professional editing software. Describe what you want — generate a 15-second video from this JSON prompt describing a sunset beach...
Usage Guidance
This skill appears to do what it says: it talks to a third-party rendering API and uploads files for server-side video creation. Before installing/using it, consider: (1) the NEMO_TOKEN is a bearer secret — do not supply a token you use elsewhere; prefer the anonymous-token flow if you don't trust the service, (2) anything you upload (videos, images, JSON) will go to mega-api-prod.nemovideo.ai — check the service's privacy/retention policy or avoid uploading sensitive content, (3) the skill may probe a couple of standard install paths to set an attribution header — if you are uncomfortable with filesystem probing, decline or ask for a version that doesn't do that, and (4) because the skill's source and homepage are unknown, you may want to test with throwaway data/tokens first. If you can obtain documentation or a known, trusted homepage for the nemovideo service, that would raise confidence; conversely, if the API domain or anonymous-token endpoint is untrusted or the skill asked for unrelated credentials, reassess and treat as suspicious.
Capability Analysis
Type: OpenClaw Skill
Name: text-to-video-json-prompt
Version: 1.0.0
The skill is a functional integration for the NemoVideo AI service, enabling an agent to generate videos from text or structured data (JSON, CSV, etc.). It provides detailed instructions for the agent to manage authentication via the `NEMO_TOKEN` environment variable or an anonymous token, handle session states, and interact with the `mega-api-prod.nemovideo.ai` API. The logic is consistent with the stated purpose of video generation and does not exhibit signs of data exfiltration, unauthorized execution, or malicious prompt injection.
Capability Assessment
Purpose & Capability
The name/description (generate videos from text/JSON) aligns with the requested credential (NEMO_TOKEN) and the SKILL.md describes API endpoints for creating sessions, uploading files, and rendering. The declared config path (~/.config/nemovideo/) is plausible for storing session/state and matches the skill's purpose. No unrelated environment variables or unrelated binaries are requested.
Instruction Scope
SKILL.md gives explicit runtime steps (acquire anonymous token if needed, create session, send SSE, upload multipart files up to 500MB, poll render endpoint). These are within the skill's scope. One minor scope note: it instructs deriving an X-Skill-Platform header by detecting install paths (e.g., checking ~/.clawhub/ or ~/.cursor/skills/), which implies the agent may probe the user's home directory for those paths; this is limited but is extra filesystem access beyond purely network calls. The instructions also require sending user files to the external API — expected but privacy-relevant.
Install Mechanism
There is no install specification and no code files; this is instruction-only. That minimizes on-disk changes and execution of third-party code from arbitrary URLs, which is the lower-risk option for skills.
Credentials
Only one required environment variable (NEMO_TOKEN) is declared and used as the bearer token for the service. The SKILL.md even documents an anonymous-token flow to obtain a short-lived token, which explains why a token is needed. No unrelated secrets or multiple credentials are requested.
Persistence & Privilege
The skill is not force-enabled (always:false) and does not request elevated platform privileges. It instructs saving a session_id from the API but does not mandate writing persistent system-wide configuration or modifying other skills. Autonomous invocation is allowed by platform default but not a standalone concern here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install text-to-video-json-prompt - After installation, invoke the skill by name or use
/text-to-video-json-prompt - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of text-to-video-json-prompt skill.
- Generate 15-second AI videos from natural language or structured (JSON, TXT, CSV, YAML) prompts; ideal for developers and content creators.
- Automatic setup with free token support for up to 100 credits, no installation required.
- Supports input upload up to 500MB and video export in multiple formats (mp4, mov, avi, webm, etc.).
- Integrated cloud GPU rendering pipeline with workflows for editing, batch processing, and iterative refinement.
- Clear guidance for command routing and error handling included.
Metadata
Frequently Asked Questions
What is Text To Video Json Prompt?
Skip the learning curve of professional editing software. Describe what you want — generate a 15-second video from this JSON prompt describing a sunset beach... It is an AI Agent Skill for Claude Code / OpenClaw, with 91 downloads so far.
How do I install Text To Video Json Prompt?
Run "/install text-to-video-json-prompt" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Text To Video Json Prompt free?
Yes, Text To Video Json Prompt is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Text To Video Json Prompt support?
Text To Video Json Prompt is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Text To Video Json Prompt?
It is built and maintained by francemichaell-15 (@francemichaell-15); the current version is v1.0.0.
More Skills