← Back to Skills Marketplace
Text To Video Invideo
by
dsewell-583h0
· GitHub ↗
· v1.0.0
· MIT-0
67
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install text-to-video-invideo
Description
Get AI-generated videos ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, PDF, copied text, up to 500MB), say something l...
Usage Guidance
This skill appears to do what it says (call a remote video-render API and upload user-provided files) but exercise caution before installing: 1) The source/homepage is missing — verify the service (nemovideo / mega-api-prod.nemovideo.ai) independently before providing tokens or files. 2) The SKILL.md YAML mentions a config path (~/.config/nemovideo/) that is not declared elsewhere — confirm whether the skill will read or write files there. 3) Only set NEMO_TOKEN if you trust the service; prefer ephemeral anonymous tokens and avoid storing long-lived secrets in global env vars. 4) Only upload content you own or that doesn't contain secrets (do not let the agent pick arbitrary local file paths). 5) If you need higher assurance, ask the publisher for a homepage/terms/privacy and a code/artifact link (or request a signed maintainer identity) — that information would move this assessment toward 'benign.'
Capability Analysis
Type: OpenClaw Skill
Name: text-to-video-invideo
Version: 1.0.0
The skill bundle provides a functional interface for a text-to-video service using the nemovideo.ai API. It includes detailed instructions for the agent to handle authentication, session management, and video rendering workflows. While it automates token acquisition and environment detection (e.g., identifying if it's running in Cursor or Clawhub), these actions are transparently documented in SKILL.md and directly support the stated purpose of the tool without evidence of malicious intent or data exfiltration.
Capability Assessment
Purpose & Capability
Name/description match the instructions: the skill drives a remote AI video API and requires an API token (NEMO_TOKEN). That credential is proportional to the stated purpose. However the package has no homepage/source and the YAML frontmatter in SKILL.md references a config path (~/.config/nemovideo/) while the registry metadata lists no required config paths — an internal inconsistency.
Instruction Scope
Instructions explicitly perform network calls to https://mega-api-prod.nemovideo.ai, create or reuse NEMO_TOKEN, open sessions, stream SSE, and upload user files (multipart or URL). Those actions are expected for a cloud render service. The only scope concern is the skill's attempt to derive install platform from local install paths and its implicit expectation to read user-supplied file paths for upload — benign for intended uploads, but worth noting because it could be used to exfiltrate arbitrary local files if misused.
Install Mechanism
Instruction-only skill with no install spec or code files — lowest install risk. Nothing is downloaded or written to disk by an installer.
Credentials
Only one env var is required (NEMO_TOKEN), which matches the API usage. But SKILL.md suggests auto-generating and storing a token and references a config directory in YAML, creating a mismatch with registry metadata. The skill will also read local file paths when uploading user files — expected, but sensitive if the agent is allowed to choose arbitrary paths.
Persistence & Privilege
always:false and no install behavior means no forced persistent presence. The skill does instruct saving a session_id for the service, but it does not request platform-wide privileges or modification of other skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install text-to-video-invideo - After installation, invoke the skill by name or use
/text-to-video-invideo - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Text to Video InVideo skill — initial release.
- Instantly converts text prompts or uploads into shareable AI-generated videos with voiceover and visuals.
- Supports TXT, DOCX, PDF, and raw text inputs up to 500MB.
- 1080p MP4 export, no manual video editing required.
- Automatic setup: free token and session are established on first use.
- Clear handling of common actions: upload, export, check credits, view project state.
- Built for fast, marketer-focused video creation workflows.
Metadata
Frequently Asked Questions
What is Text To Video Invideo?
Get AI-generated videos ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, PDF, copied text, up to 500MB), say something l... It is an AI Agent Skill for Claude Code / OpenClaw, with 67 downloads so far.
How do I install Text To Video Invideo?
Run "/install text-to-video-invideo" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Text To Video Invideo free?
Yes, Text To Video Invideo is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Text To Video Invideo support?
Text To Video Invideo is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Text To Video Invideo?
It is built and maintained by dsewell-583h0 (@dsewell-583h0); the current version is v1.0.0.
More Skills