Extract Chinese and English text from images and scanned PDFs, including documents like invoices and contracts, using PaddleOCR in Python.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install ocr-python或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install ocr-python⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/ocr-python/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: ocr description: Optical Character Recognition (OCR) tool, supports Chinese and English text extraction from PDFs and images. Use cases: (1) extract text from scanned PDFs, (2) recognize text from images, (3) extract text content from invoices, contracts, and other documents ---
This skill uses PaddleOCR for text recognition, supporting both Chinese and English.
Perform OCR recognition directly on image or PDF files:
from paddleocr import PaddleOCR
ocr = PaddleOCR(lang='ch')
result = ocr.predict("file_path.jpg")Install dependencies before first use:
pip3 install paddlepaddle paddleocrRecognition results return JSON containing:
rec_texts: List of recognized textrec_scores: Confidence score for each textCommon scripts are located in the scripts/ directory.
安装 OCR with python 后，可以对 AI 说这些话来触发它
Help me get started with OCR with python
Explains what OCR with python does, walks through the setup, and runs a quick demo based on your current project
Use OCR with python to extract Chinese and English text from images and scanned PDFs, incl...
Invokes OCR with python with the right parameters and returns the result directly in the conversation
What can I do with OCR with python in my documents & notes workflow?
Lists the top use cases for OCR with python, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/ocr-python/ 目录（个人级，所有项目可用），或 .claude/skills/ocr-python/（项目级）。重启 AI 客户端后，用 /ocr-python 主动调用，或让 AI 根据上下文自动发现并使用。
OCR with python 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
OCR with python 可免费安装使用。请查阅仓库了解许可证信息。
Extract Chinese and English text from images and scanned PDFs, including documents like invoices and contracts, using PaddleOCR in Python.
OCR with python 属于「Documents & Notes」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my documents & notes tasks using OCR with python
Identifies repetitive steps in your workflow and sets up OCR with python to handle them automatically