當用戶需要從圖片、照片、掃描檔、螢幕截圖或掃描式 PDF 中提取文字時，使用此技能。它會傳回可讀取的字串，包含逐行文字與可選的邊界框 (bbox) 座標，對中日韓 (CJK) 字元、小字體及手寫文字具有高準確度。
此技能以 PaddleOCR 為基礎，為 AI 智能體提供光學字元辨識 (OCR) 功能。它能從圖片、照片、文件掃描、螢幕截圖及掃描式 PDF 中精確提取文字，並支援逐行結果與可選的邊界框 (bbox) 座標，方便進行版面分析。特別擅長處理中日韓 (CJK) 字元、小字體及手寫文字，適合用於在地化文件數位化、螢幕截圖文字提取及表單辨識等場景。作為一個 CLI 技能，它接收圖片或 PDF 路徑作為輸入，透過 PaddleOCR 的深度學習模型進行處理，並在終端機輸出結構化的 JSON 結果。此技能已在 Claude Code 及類似的 CLI 智能體環境中驗證，可流暢整合至開發者流程。
npx skills add https://github.com/aidenwu0209/paddleocr-skills/tree/main/skills/paddleocr-text-recognitionInstalled? Explore more 影像 skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →
當用戶需要從圖片、照片、掃描檔、螢幕截圖或掃描式 PDF 中提取文字時，使用此技能。它會傳回精確的機器可讀字串，包含逐行文字與可選的邊界框 (bbox) 座標。對中日韓 (CJK) 字元、小字體及手寫文字具有高準確度。觸發詞彙：OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字, plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan, recognize text。
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Add documentation for a new AI provider — usage docs, env vars, Docker config, image resources.
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.