corespeed-nanobananaGenerate and edit images using Google Gemini models via Corespeed AI Gateway. Supports text-to-image generation, image editing, multi-image input, and text r...
Install via ClawdBot CLI:
clawdbot install zypher-agent/corespeed-nanobananaGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/astral-sh/uvAudited Apr 16, 2026 · audit v1.0
Generated May 9, 2026
Marketing teams can generate custom images and text for social media posts using natural language prompts. This streamlines content production for platforms like Instagram, Twitter, and LinkedIn, reducing reliance on graphic designers.
E-commerce businesses can edit product photos programmatically—removing backgrounds, adding scenes, or blending multiple images. This enables consistent and appealing product imagery at scale without manual Photoshop work.
Manufacturing or logistics companies can use the gemini-2.5-flash model to analyze images and detect defects, compare before/after states, or extract text from labels. This automates visual inspection tasks.
Designers and product teams can generate multiple visual concepts (e.g., UI mockups, architectural sketches) quickly by describing ideas in text. This accelerates the ideation phase and facilitates client feedback.
Offer AI-powered image generation and editing as a feature within existing software (e.g., CMS, design tools) charged per API call or monthly subscription tier.
Operate as a service where clients pay per project or retainer for automated content creation (social media visuals, product images, etc.) leveraging the skill.
Provide a free tier with limited credits to attract developers, then charge for higher usage and premium features (e.g., faster models, higher resolution).
💬 Integration Tip
To integrate, set the two environment variables (CS_AI_GATEWAY_BASE_URL and CS_AI_GATEWAY_API_TOKEN), then call the script via uv run with appropriate arguments. Use --json flag for structured output to easily parse results in your application.
Scored Jun 27, 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...
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, docu...
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
AI avatar creation and digital persona design powered by CellCog. Character.ai for agents — create characters, clone voices, generate images, build personalities. Persistent avatars reusable across all chats. Brand mascots, digital twins, creative characters, AI spokespersons, podcast hosts. Describe your character in plain language and CellCog builds it.