← Back to Skills Marketplace
71
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install text-to-video-image
Description
Turn a written description of a sunset over a mountain lake into 1080p AI-generated video just by typing what you need. Whether it's generating short video c...
Usage Guidance
This skill appears to be a straightforward cloud text→video client, but exercise caution: it uploads files and uses a bearer token (NEMO_TOKEN) to a third-party domain (mega-api-prod.nemovideo.ai). The SKILL.md will generate an anonymous token if you don't provide one, and it may check local install/config paths to build attribution headers. Before installing, consider: (1) there is no homepage or known source — that reduces traceability and accountability; (2) do not upload sensitive or private media until you’ve verified the service's privacy policy; (3) prefer providing a dedicated, limited-scope token (or none) and rotate it if compromised; (4) test the skill with non-sensitive content first; (5) if you need to be extra cautious, request the skill author/source or prefer a vetted provider.
Capability Analysis
Type: OpenClaw Skill
Name: text-to-video-image
Version: 1.0.0
The skill is a standard integration for the NemoVideo AI service, providing instructions for an agent to manage authentication and video generation tasks via the mega-api-prod.nemovideo.ai API. It includes legitimate session management, credit checking, and error handling logic consistent with its stated purpose. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
Name/description (text→video) align with the declared NEMO_TOKEN and the API endpoints in SKILL.md. However metadata also lists a config path (~/.config/nemovideo/) and the runtime asks to detect install paths to set X-Skill-Platform; detecting local install paths for attribution is not required for core video generation and is an extra capability that should be justified.
Instruction Scope
The instructions will: check an env var (NEMO_TOKEN), if missing call an anonymous-token API to obtain a token, create sessions, upload user files (multipart) to the remote service, stream SSE responses, and poll render endpoints. These actions are expected for a cloud render skill. Concerns: (1) the skill may read/inspect local install paths to set X-Skill-Platform, which requires filesystem checks outside the stated core task; (2) user files are uploaded to a third-party backend — this is expected but carries privacy/exfiltration risk; (3) the SKILL.md tells the agent not to expose tokens, but there is no technical enforcement — the agent could still leak tokens or API responses if misused.
Install Mechanism
Instruction-only skill with no install spec and no bundled code — lowest install risk. All network activity comes from runtime API calls described in SKILL.md.
Credentials
Only one required env var (NEMO_TOKEN) is declared, which is appropriate. The skill also declares a config path (~/.config/nemovideo/) in metadata and expects to detect install paths — those imply the skill may read local filesystem state beyond a single token env var. The fallback behavior (automatically requesting an anonymous token from nemovideo.ai when NEMO_TOKEN is absent) is reasonable but means the agent will make outbound network calls autonomously.
Persistence & Privilege
always is false and there are no install scripts or instructions to modify other skills or global agent settings. The skill can invoke autonomously (default), which increases blast radius but is normal for skills; combined with network/file access noted above this raises operational privacy considerations but not an outright privilege escalation.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install text-to-video-image - After installation, invoke the skill by name or use
/text-to-video-image - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Text to Video Image 1.0.0 — initial release!
- Generate 1080p AI video clips from written text prompts in 30–90 seconds.
- No manual editing needed: just type your idea to get a rendered video.
- Automatic first-time cloud backend setup with token generation.
- Supports export to multiple formats (mp4, mov, avi, webm, gif, etc.).
- Rapid workflows: upload, generate, preview, and export, all in the same session.
Metadata
Frequently Asked Questions
What is Text To Video Image?
Turn a written description of a sunset over a mountain lake into 1080p AI-generated video just by typing what you need. Whether it's generating short video c... It is an AI Agent Skill for Claude Code / OpenClaw, with 71 downloads so far.
How do I install Text To Video Image?
Run "/install text-to-video-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Text To Video Image free?
Yes, Text To Video Image is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Text To Video Image support?
Text To Video Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Text To Video Image?
It is built and maintained by tk8544-b (@tk8544-b); the current version is v1.0.0.
More Skills