← Back to Skills Marketplace
Text To Video Diffusion
by
peandrover adam
· GitHub ↗
· v1.0.0
· MIT-0
62
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install text-to-video-diffusion
Description
Turn a short descriptive sentence like 'a fox running through a snowy forest at dusk' into 1080p AI-generated video just by typing what you need. Whether it'...
Usage Guidance
This skill appears to implement a typical cloud text→video workflow, but note three things before installing: (1) it will automatically contact an external API and, if you don't supply NEMO_TOKEN, will create and persist an anonymous token for you — this happens when the skill is first opened and may occur without an explicit prompt; (2) SKILL.md mentions reading or referencing local config/install paths (~/.config/nemovideo/ and install-path detection for X-Skill-Platform), which is not clearly necessary and is inconsistently declared — ask the publisher whether the skill will read any files from your home directory and where tokens/session data are stored; (3) the backend domain (mega-api-prod.nemovideo.ai) is external and not audited here — if you care about privacy or sensitive content, verify the service's reputation, limit what you upload, or create a scoped service token you can revoke. If you want low risk, only enable this skill for non-sensitive prompts or require an explicit, user-provided NEMO_TOKEN rather than letting the skill mint one automatically.
Capability Analysis
Type: OpenClaw Skill
Name: text-to-video-diffusion
Version: 1.0.0
The skill is a legitimate integration for a text-to-video generation service hosted at nemovideo.ai. It provides clear instructions for the agent to manage API authentication, session handling, and media rendering workflows. Notably, it includes a security-conscious instruction to avoid displaying raw API tokens or responses to the user, and it does not attempt to access sensitive local files or execute unauthorized commands.
Capability Assessment
Purpose & Capability
The name/description match the documented API calls (session creation, uploads, render/export). Requesting a NEMO_TOKEN and calling nemovideo.ai endpoints is coherent for a cloud text→video service. However the SKILL.md metadata also references a config path (~/.config/nemovideo/) and asks for headers that are derived from the agent's install path — reading those local paths is not clearly necessary for core functionality and is not consistently declared in the top-level requirements.
Instruction Scope
The runtime instructions tell the agent to automatically connect on first-open and to obtain an anonymous token if NEMO_TOKEN is not set (network calls and token creation without explicit user confirmation). They also require storing the session_id/token for later requests but give no secure-storage guidance. The header that derives X-Skill-Platform from install path implies examining local install paths; that file-system access is not explicitly declared elsewhere and may be unnecessary for the task.
Install Mechanism
Instruction-only skill with no install spec or downloaded code, which minimizes on-disk risks. All runtime behavior is remote API calls.
Credentials
Only NEMO_TOKEN is declared as required, which is proportionate for a remote video-rendering service. However the SKILL.md metadata and instructions imply reading a config path (~/.config/nemovideo/) and deriving platform from install paths — this could expose local config or metadata beyond what the service strictly needs. Also the skill will generate and persist an anonymous token if one is not provided, so it will create credentials automatically.
Persistence & Privilege
always is false and the skill does not request elevated platform privileges. It does ask the agent to store short-lived session tokens to operate, which is normal for this type of service, but storage location and lifetime are unspecified.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install text-to-video-diffusion - After installation, invoke the skill by name or use
/text-to-video-diffusion - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of text-to-video-diffusion:
- Generate 1080p AI-powered videos directly from text prompts.
- Simple workflow: enter a descriptive sentence, get a video in 1–3 minutes—no manual editing needed.
- Automated backend setup, including free token retrieval (100 credits for 7 days) and session management.
- Supports file uploads, timeline edits, credits checking, and one-click export (MP4, various formats and tracks).
- User input intelligently routed to actions (generate, upload, export, check balance, etc.) using keyword/intent analysis.
- Cloud rendering with detailed API response handling and clear error messages for common issues.
Metadata
Frequently Asked Questions
What is Text To Video Diffusion?
Turn a short descriptive sentence like 'a fox running through a snowy forest at dusk' into 1080p AI-generated video just by typing what you need. Whether it'... It is an AI Agent Skill for Claude Code / OpenClaw, with 62 downloads so far.
How do I install Text To Video Diffusion?
Run "/install text-to-video-diffusion" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Text To Video Diffusion free?
Yes, Text To Video Diffusion is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Text To Video Diffusion support?
Text To Video Diffusion is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Text To Video Diffusion?
It is built and maintained by peandrover adam (@peand-rover); the current version is v1.0.0.
More Skills