nano-banana-skillsGenerate images using Google Gemini models (Nano Banana 2 / gemini-3-pro-image-preview). Use when the user asks to create, generate, or make an image, pictur...
Install via ClawdBot CLI:
clawdbot install 0n1onr1ng/nano-banana-skillsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://api.wisgate.ai/v1beta/models/{model}:generateContentAudited Apr 17, 2026 · audit v1.0
Generated May 9, 2026
Generate high-quality images for social media posts, blog headers, and advertisements from text prompts. Marketers can quickly create custom visuals for campaigns without needing design skills or stock photo subscriptions.
Modify existing product images by applying style transfers, changing backgrounds, or generating lifestyle scenes around products. Online retailers can improve product listings with minimal effort and cost.
Create detailed educational visuals such as infographics, diagrams, and illustrations from descriptive text. Teachers and content creators can produce engaging learning materials tailored to specific topics.
Quickly iterate on design concepts by generating and refining images based on client feedback. Designers can explore multiple visual directions and styles in a single session using multi-turn refinement.
Generate unique, custom images for social media posts and stories that reflect personal branding. Influencers can maintain a consistent visual identity without relying on generic stock photos.
Offer a limited number of free image generations per month (e.g., 10 images) with watermark, then charge per image or subscription for higher resolution, multiple inputs, and priority models.
License the image generation API to businesses (e.g., marketing agencies, e-commerce platforms) who integrate it into their own tools. Pricing based on volume of API calls and model tier.
Integrate the skill into a consumer app (e.g., photo editor) and sell image generation credits. Users buy credits to generate or refine images, with different credit costs for higher quality or resolution.
💬 Integration Tip
Set up the environment variable WISGATE_KEY for authentication and use the provided scripts (generate_image.py, refine_image.py) with minimal coding; the smart model selection handles optimal cost-quality trade-offs automatically.
Scored May 9, 2026
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据
Generate or edit images with Gemini using the Google GenAI SDK. Use when the user asks to create, transform, render, or save one or more images in an OpenCla...
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。