phy-ai-imageFull AI image creation workflow — intent classification, prompt enhancement, multi-direction generation via fal.ai, and error recovery. Triggers on "generate...
Install via ClawdBot CLI:
clawdbot install PHY041/phy-ai-imageGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://example.com/original.jpgAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
Users need quick, visually appealing images for posts, ads, or stories across platforms like Instagram or Facebook. The skill classifies intent, enhances prompts for engagement, and generates images tailored to specific styles (e.g., realistic product shots or anime illustrations).
Designers or small businesses create product visuals, logos, or packaging mockups. The skill handles brief ideas by enhancing prompts with technical details, uses models like fal-ai/image-apps-v2 for product photography, and supports batch requests for multiple design variations.
Writers, game developers, or educators generate concept art, character designs, or scene illustrations. It classifies intents like exploring ideas or detailed prompts, applies style templates (e.g., anime or illustration), and ensures cohesive narrative outputs via the blueprint method.
Photographers or agencies need photorealistic portraits, architectural visuals, or image edits. The skill uses models like fal-ai/nano-banana-pro for high-quality portraits and edit-capable models for modifications, with error recovery for reliable results.
Companies create consistent visual assets for branding, such as logos, marketing materials, or social media graphics. The skill plans multi-step workflows, handles batch requests for variants, and integrates with brand-specific skills if available for tailored outputs.
Offer basic image generation for free with limited features, then charge for advanced models, higher resolutions, or batch processing via a subscription or pay-per-use API. Integrates with fal.ai pricing tiers for scalable revenue.
License the skill as a customizable platform for businesses in marketing, e-commerce, or design agencies. Include features like intent classification, prompt enhancement, and model selection, with tiered pricing based on usage and support.
Provide tailored solutions for enterprises needing specific workflows, such as product mockups or brand asset creation. Offer setup, training, and ongoing support, leveraging the skill's error recovery and multi-direction generation capabilities.
💬 Integration Tip
Set up environment variables for fal.ai API keys and reference external files like prompt-templates.md for seamless style application.
Scored Apr 19, 2026
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`。
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.