Extract text, tables, and images from PDFs or images using Mistral OCR API and output in Markdown, JSON, or HTML formats.
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 mistral-ocr或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install mistral-ocr⚠️ 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/mistral-ocr/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: mistral-ocr description: "Convert PDF/images to Markdown/JSON/HTML using Mistral OCR API. Supports image extraction, table recognition, header/footer handling, and multi-column layouts. Usage: Upload a file and say Use Mistral OCR to process this." registry: homepage: https://github.com/YZDame/Mistral-OCR-SKILL author: YZDame credentials: required: true env_vars: - MISTRAL_API_KEY ---
IMPORTANT - READ BEFORE INSTALLING:
This skill uploads your files to Mistral's cloud servers for OCR processing.
Do NOT use with sensitive or confidential documents unless:
For sensitive documents, use offline/local OCR tools instead.
---
A powerful OCR tool that converts PDF files and images into Markdown, JSON, or HTML formats using Mistral's state-of-the-art OCR API.
# Clone or download this repository
git clone https://github.com/YZDame/Mistral-OCR-SKILL.git
cd Mistral-OCR-SKILL
# Install dependencies
pip install -r requirements.txt
Get your API key: 👉 https://console.mistral.ai/home
Set the environment variable:
export MISTRAL_API_KEY=your_api_key
cd scripts
# Process PDF to Markdown
python3 mistral_ocr.py -i input.pdf
# Process PDF to JSON
python3 mistral_ocr.py -i input.pdf -f json
# Specify output directory
python3 mistral_ocr.py -i input.pdf -o ~/my_ocr_results
| Flag | Description | |------|-------------| | -i, --input | Input file path (required) | | -f, --format | Output format: markdown/json/html (default: markdown) | | -o, --output | Output directory |
What happens to your files:
For more details, see: https://mistral.ai/privacy-policy
MIT
安装 Mistral OCR 后,可以对 AI 说这些话来触发它
Help me get started with Mistral OCR
Explains what Mistral OCR does, walks through the setup, and runs a quick demo based on your current project
Use Mistral OCR to extract text, tables, and images from PDFs or images using Mistral ...
Invokes Mistral OCR with the right parameters and returns the result directly in the conversation
What can I do with Mistral OCR in my documents & notes workflow?
Lists the top use cases for Mistral OCR, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/mistral-ocr/ 目录(个人级,所有项目可用),或 .claude/skills/mistral-ocr/(项目级)。重启 AI 客户端后,用 /mistral-ocr 主动调用,或让 AI 根据上下文自动发现并使用。
Mistral OCR 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Mistral OCR 可免费安装使用。请查阅仓库了解许可证信息。
Extract text, tables, and images from PDFs or images using Mistral OCR API and output in Markdown, JSON, or HTML formats.
Mistral OCR 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 Mistral OCR
Identifies repetitive steps in your workflow and sets up Mistral OCR to handle them automatically