pic-genAI 图片生成与提示词优化工具。支持通义万相、Banana (Flux)、DALL-E 等多模型。用于:根据用户简单描述生成高质量图片提示词、优化已有提示词、直接调用配置好的模型出图。触发场景:「生成图片」「画一个 XXX」「优化这个提示词」「设置 API key」「切换模型」。用户可直接发送密钥给 bot,自动...
Install via ClawdBot CLI:
clawdbot install aoturlab/pic-genGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
$OPENAISends data to undocumented external endpoint (potential exfiltration)
POST → https://api.banana.dev/start/fetch/v4/{your-model-key}Calls external URL not in known-safe list
https://api.banana.dev/start/fetch/v4/{your-model-key}Uses known external API (expected, informational)
api.openai.comGenerated May 20, 2026
A marketing team needs high-quality images for social media posts and ad campaigns. They can describe their needs in plain language, and pic-gen selects the best model and generates professional prompts to produce stunning visuals.
Digital artists and content creators can use pic-gen to optimize their prompts for various platforms like Midjourney, Stable Diffusion, and DALL-E. The tool rewrites simple descriptions into detailed, platform-specific prompts to achieve desired artistic styles.
E-commerce businesses can generate product images and lifestyle shots by describing the product and setting. Pic-gen optimizes prompts for realistic or stylized outputs, reducing the need for expensive photoshoots.
Educators and instructional designers can create custom illustrations and diagrams for teaching materials. By describing the concept, pic-gen generates appropriate visuals that enhance learning.
Offer pic-gen as a subscription service where users pay monthly or yearly for access to prompt optimization and image generation across multiple models. Tiered pricing based on usage limits.
License the prompt optimization and generation API to third-party platforms, such as design tools or content management systems, for integration into their workflows.
Provide a free tier with basic prompt optimization and limited generation capabilities. Premium unlocks multiple models, higher resolution, and priority support.
💬 Integration Tip
Integrate via API for seamless addition to existing workflows; the dialogue-based interaction reduces learning curve for non-technical users.
Scored Jun 29, 2026
AI Analysis
The skill interacts with legitimate, documented AI image generation APIs (DashScope/Qwen, Banana/Flux, OpenAI/DALL-E) consistent with its stated purpose. While it handles user API keys, the configuration process is described and appears user-initiated. The external endpoint 'api.banana.dev' is a known service for running AI models, not an unauthorized or hidden data sink.
Audited Apr 16, 2026 · audit v1.0
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。