dsh-vision-toolkit 是做什麼的？
讓純文字模型更好地處理視覺任務的 DeepSeek Harness 插件：含意圖的圖片問答、長截圖 OCR、UI 還原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
讓純文字模型更好地處理視覺任務的 DeepSeek Harness 插件：含意圖的圖片問答、長截圖 OCR、UI 還原等。
這是一個為 DeepSeek Harness 深度整合的視覺工具套件（agent-vision-toolkit）。它能讓純文字模型也能執行多種視覺相關任務，例如：帶有語意的智慧圖片問答、長截圖的 OCR（光學字元辨識）、UI 設計還原、元素定位、像素差異比對、產出 Artifacts，以及提供 Web UI 操作介面。其主要價值在於補足純文字模型缺乏視覺感知的短板，讓開發者可以在本機或虛擬機中，透過文字指令來完成複雜的圖像分析與自動化任務。此工具高度整合於 DeepSeek Harness 生態系，也支援如 Claude Code、Cursor 等代理平台，適合需要視覺理解與驗證的開發場景。
npx skills add Anionex/dsh-vision-toolkit讓純文字模型更好地處理視覺任務的 DeepSeek Harness 插件：含意圖的圖片問答、長截圖 OCR、UI 還原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
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".