← Back to Skills Marketplace
YouTube Thumbnail Generator with Nano Banana
by
Magiclight
· GitHub ↗
· v0.1.1
285
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install youtube-cover-nano-banana
Description
Create high-converting YouTube thumbnail concepts, overlay text, image prompts, and optional AI-generated cover images from raw titles, hooks, scripts, or ma...
Usage Guidance
This package is internally consistent with its stated purpose, but review before running: (1) The scripts will send whatever you pass as copy to Google's generativelanguage API using your GEMINI_API_KEY/GOOGLE_API_KEY — avoid sending private or sensitive data. (2) Ensure the API key you provide has appropriate billing/usage controls and is stored securely. (3) The scripts write files to an outputs/ directory; run them in a workspace you control (or a sandbox) if you are cautious. (4) Run the included selftest (scripts/selftest.py) and inspect the scripts if you want to confirm behavior; the code is small and uses only standard library network calls to the official generativelanguage endpoint. (5) If you need tighter assurance, restrict the key scope, rotate keys after testing, or run the code in an isolated environment.
Capability Analysis
Type: OpenClaw Skill
Name: youtube-cover-nano-banana
Version: 0.1.1
The skill bundle provides a legitimate workflow for generating YouTube thumbnail concepts and images using Gemini APIs. The Python scripts (create_thumbnail.py and generate_image.py) use the standard library (urllib) to communicate with official Google endpoints (generativelanguage.googleapis.com) and do not exhibit signs of data exfiltration, obfuscation, or unauthorized execution. The instructions in SKILL.md and the reference documents are strictly aligned with the stated purpose of thumbnail generation and do not contain malicious prompt injection attempts.
Capability Assessment
Purpose & Capability
Name/description match the implementation: scripts build a thumbnail plan with a Gemini text model and optionally call Gemini's image endpoint. Requested binaries (python3) and environment variables (GEMINI_API_KEY / GOOGLE_API_KEY) are appropriate and expected for this functionality.
Instruction Scope
SKILL.md instructs the agent to analyze input copy, build prompts, and optionally call local scripts that POST to Google's generativelanguage endpoint. The instructions reference only the provided scripts, output paths under outputs/, and the declared API keys — they do not instruct reading unrelated system files or other credentials.
Install Mechanism
There is no external install spec (instruction-only / local scripts), so nothing is downloaded from remote URLs. The included Python scripts are self-contained and use only the standard library for network calls; no third-party package installs or external archives are pulled.
Credentials
Only GEMINI_API_KEY (primary) or GOOGLE_API_KEY are required and are used to authenticate with Google's generativelanguage API. No unrelated secrets or many credentials are requested. The credential usage is proportional to the described purpose.
Persistence & Privilege
The skill is not forced always-on (always: false) and does not modify other skills or global agent settings. It writes outputs to local files under outputs/, which is expected behavior for a generator script.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install youtube-cover-nano-banana - After installation, invoke the skill by name or use
/youtube-cover-nano-banana - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.1
Improve marketplace discoverability, convert all examples and descriptive content to English, and refresh listing-oriented metadata.
v0.1.0
Initial release.
- Converts user-provided copy, titles, or messaging into a strong YouTube thumbnail concept and a ready-to-use Nano Banana image prompt.
- Analyzes input text to select the optimal thumbnail angle, compresses it into click-driven overlay text, and crafts a detailed, high-contrast 16:9 image prompt.
- Guides selection of visual style, focal point, and on-image text according to best YouTube practices.
- Provides a workflow for automated script execution and manual prompt usage, with clear output format and constraints for legibility and clickability.
- Includes self-critique step to minimize common thumbnail design failures before final output.
Metadata
Frequently Asked Questions
What is YouTube Thumbnail Generator with Nano Banana?
Create high-converting YouTube thumbnail concepts, overlay text, image prompts, and optional AI-generated cover images from raw titles, hooks, scripts, or ma... It is an AI Agent Skill for Claude Code / OpenClaw, with 285 downloads so far.
How do I install YouTube Thumbnail Generator with Nano Banana?
Run "/install youtube-cover-nano-banana" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is YouTube Thumbnail Generator with Nano Banana free?
Yes, YouTube Thumbnail Generator with Nano Banana is completely free (open-source). You can download, install and use it at no cost.
Which platforms does YouTube Thumbnail Generator with Nano Banana support?
YouTube Thumbnail Generator with Nano Banana is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created YouTube Thumbnail Generator with Nano Banana?
It is built and maintained by Magiclight (@luo-2q); the current version is v0.1.1.
More Skills