← Back to Skills Marketplace
Text To Video By Google
by
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
64
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install text-to-video-by-google
Description
Get AI generated clips ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, PDF, plain text, up to 10MB), say something like...
Usage Guidance
Before installing or invoking this skill:
- Confirm the provider: the skill’s name claims “By Google” but all endpoints point to nemovideo.ai; ask the author or inspect the homepage/source to verify who runs the service.
- Understand data flow: any text or uploaded files you send will be transmitted to mega-api-prod.nemovideo.ai (cloud GPUs). Do not upload sensitive or private data unless you trust that service’s privacy/security.
- Credential scope: the skill uses a single NEMO_TOKEN (or will request an anonymous token). Prefer supplying a scoped, revocable token rather than sharing long-lived high-privilege credentials.
- Local config access: SKILL.md references a config path (~/.config/nemovideo/) and asks to detect install-path for attribution headers — confirm whether the skill actually reads files on disk and why.
- If you need assurance: ask the publisher for a homepage, privacy policy, or source code. If you cannot verify the operator (nemovideo.ai) and you will upload non-public data, avoid using the skill.
Given the name/provider mismatch and metadata inconsistencies, proceed only after verifying the service operator and what will happen to uploaded content.
Capability Analysis
Type: OpenClaw Skill
Name: text-to-video-by-google
Version: 1.0.0
The skill exhibits deceptive behavior by impersonating a Google service ("Text to Video by Google") while directing all traffic to a non-Google domain (mega-api-prod.nemovideo.ai). While the instructions in SKILL.md define a functional API integration for video processing and do not explicitly command the exfiltration of unrelated sensitive data like SSH keys or AWS credentials, the use of brand impersonation is a significant indicator of potential phishing or unauthorized data collection. Additionally, the skill instructs the agent to fingerprint the local environment by checking install paths (~/.clawhub/ or ~/.cursor/skills/) to set custom headers.
Capability Assessment
Purpose & Capability
The skill claims to generate videos and all required actions (session creation, SSE, upload, export) are consistent with a cloud video-rendering service. However the name 'Text To Video By Google' implies a Google product while all API endpoints point to mega-api-prod.nemovideo.ai — a provider-brand mismatch that could be misleading. The SKILL.md also includes a config path (~/.config/nemovideo/) in its metadata that is not present in the registry summary, an internal inconsistency.
Instruction Scope
SKILL.md is an instruction-only runtime spec that instructs the agent to use NEMO_TOKEN (or obtain an anonymous token), create sessions, send SSE, upload files, poll render endpoints, and surface status text to the user. It does not instruct the agent to read unrelated system files, secrets, or the user's environment beyond NEMO_TOKEN (except to detect install path/frontmatter for attribution headers). The actions described are within the scope of a cloud video-generation skill.
Install Mechanism
No install spec or code is provided; this is instruction-only. That minimizes disk/write risk because nothing is downloaded or installed by the skill itself.
Credentials
The skill only requires a single credential (NEMO_TOKEN) which is appropriate for a third-party API. It will also obtain an anonymous token if none is supplied. The presence of a declared config path (~/.config/nemovideo/) in the SKILL.md metadata suggests the skill might read local config if present — the registry metadata shown earlier did not list this path, so this is an inconsistency to confirm with the author.
Persistence & Privilege
always:false and no install behavior means the skill does not request persistent elevated presence or forced inclusion. It does not instruct modifying other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install text-to-video-by-google - After installation, invoke the skill by name or use
/text-to-video-by-google - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial public release of "Text to Video by Google":
- Generate 1080p MP4 videos from written descriptions or uploaded text files (TXT, DOCX, PDF, up to 10MB).
- Simple workflow: upload prompt, describe your video, and download ready-to-use clips.
- Designed for marketers, creators, and educators — no editing or camera skills required.
- Handles session, authentication, and credits automatically on first use.
- Supports timeline editing, track previews, and multiple file formats (mp4, mov, avi, webm, jpg, png, gif, mp3, etc.).
- Clear error messages and guidance for file limits, authentication, and export status.
Metadata
Frequently Asked Questions
What is Text To Video By Google?
Get AI generated clips ready to post, without touching a single slider. Upload your text prompts (TXT, DOCX, PDF, plain text, up to 10MB), say something like... It is an AI Agent Skill for Claude Code / OpenClaw, with 64 downloads so far.
How do I install Text To Video By Google?
Run "/install text-to-video-by-google" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Text To Video By Google free?
Yes, Text To Video By Google is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Text To Video By Google support?
Text To Video By Google is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Text To Video By Google?
It is built and maintained by whitejohnk-26 (@whitejohnk-26); the current version is v1.0.0.
More Skills