morfeo-nano-banana-proGenerate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
Install via ClawdBot CLI:
clawdbot install PauldeLavallaz/morfeo-nano-banana-proGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image-previCalls external URL not in known-safe list
https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image-previUses known external API (expected, informational)
googleapis.comAI Analysis
The skill's external API calls are to Google's official generativelanguage.googleapis.com domain, which is consistent with its stated purpose of using Google's Gemini 3 Pro Image API. There is no evidence of credential harvesting, hidden instructions, or obfuscation. The 'unknown data sink' signal is a false positive for this legitimate, documented service.
Generated Mar 22, 2026
Online retailers can use this skill to generate high-quality product images from basic descriptions or edit existing photos to improve lighting, background, and consistency across listings. It supports reference images to maintain product packaging and style, enabling bulk creation of professional shots without expensive photoshoots.
Marketing teams can quickly produce custom images for social media, ads, and promotional materials by inputting campaign themes and reference styles. The skill's text rendering and resolution options allow for branded visuals with accurate logos and high-resolution outputs suitable for print and digital media.
Game developers and animators can generate consistent character visuals across multiple scenes using reference images to maintain facial features and traits. The skill supports high-resolution outputs for detailed artwork, streamlining concept art creation and in-game asset production.
Architects and designers can create realistic renders of spaces from textual descriptions or modify existing floor plans with new furnishings and lighting. The skill's aspect ratio and style controls help produce professional visualizations for client presentations and project proposals.
Educators and content creators can generate illustrative images for textbooks, online courses, and presentations based on educational topics. The skill allows for easy editing of diagrams and infographics, enhancing visual learning materials without graphic design expertise.
Offer tiered subscription plans for businesses to access the image generation and editing API, with limits based on resolution and usage volume. Revenue comes from monthly fees, targeting small to medium enterprises needing regular visual content.
Charge users per image generated or edited, with pricing varying by resolution (e.g., higher fees for 4K outputs). This model suits freelance designers or occasional users who prefer flexibility over subscriptions, driving revenue through transaction fees.
License the skill as a white-label service for large corporations to integrate into their internal tools, such as marketing platforms or product design software. Revenue is generated through annual licensing contracts and custom integration support.
💬 Integration Tip
Ensure API keys are securely managed via environment variables, and always run scripts from the user's current directory to save outputs in their workspace, avoiding skill directory conflicts.
Scored Apr 19, 2026
Audited Apr 17, 2026 · audit v1.0
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Capture frames or clips from RTSP/ONVIF cameras.
Create, inspect, process, and optimize image files and visual assets with reliable format choice, resizing, compression, color-profile, metadata, and platfor...
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
Extract text from images using Tesseract OCR