What does visual-proxy do?
Claude Code skill — A vision proxy for text-only LLMs (DeepSeek/o1/o3) that adds image understanding capabilities. Supports OpenAI/Anthropic/DashScope/Qwen3-VL.
Vision proxy for text-only LLMs (DeepSeek/o1/o3), supports OpenAI/Anthropic/DashScope/Qwen3-VL.
A Claude Code skill that adds vision capabilities to text-only LLMs like DeepSeek, o1, and o3 by proxying image inputs through vision-capable models. It acts as a middleware that forwards image requests to models supporting vision (OpenAI, Anthropic, DashScope, Qwen3-VL) and returns the visual understanding results to the text-only LLM. This allows developers and users to give image understanding abilities to otherwise blind models, expanding their use cases in multimodal scenarios. It supports multiple backend providers and can be configured via environment variables.
npx skills add daiuuuuuuuuuuuuu/visual-proxyClaude Code skill — A vision proxy for text-only LLMs (DeepSeek/o1/o3) that adds image understanding capabilities. Supports OpenAI/Anthropic/DashScope/Qwen3-VL.
ElevenLabs text-to-speech with mac-style say UX.
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
Capture and automate macOS UI with the Peekaboo CLI.
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".