O

Umi OCR

VERIFIED

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

Downloads 0
Stars 44.9K
Version 1.0.0
Quality 100/100 · Excellent

Install with one command

$ npx skills add hiroi-sora/Umi-OCR

Decision summary

Production-ready for Document processing

Use this as a leading candidate, then validate the README and install path in your own agent stack.

100
Readiness

Best for

  • Document processing workflows
  • Claude Code teams
  • teams that value GitHub adoption signals

Not ideal for

  • teams that need a vendor-supported SLA
  • high-compliance environments without internal security review

Risk notes

  • No major risk signals from current metadata

Quality profile

Excellent candidate for agent workflows

High-confidence pick with strong adoption and healthy maintenance signals.

100
GitHub stars
45K
Freshness
7mo ago
Install ready
Yes
License
MIT

Workflow fit

Use this skill in these scenarios

Parse messy files

Document processing

I need my agent to read PDFs, extract tables, and turn documents into structured data.

Search private knowledge

RAG and knowledge

I need my agent to build a RAG workflow over documents and retrieve reliable context.

Build and ship code

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Stack fit

Add it to a complete workflow

Ingest, retrieve, and cite

RAG knowledge base

A stack for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.

Inspect, patch, and verify code

Coding review agent

A stack for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.

Turn skills into distribution

Content growth agent

A stack for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.

Overview

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

Imported by the skill-only GitHub discovery pipeline because it matches agent skill, automation, RAG, or developer-tool signals. Protocol-server projects are excluded from automated imports.

Platform Compatibility

pythonFULL
ocrFULL

Technical Details

Version
1.0.0
License
MIT
Last Updated
6/6/2026
Published
6/5/2026

Frameworks & Tools

PythonOCR

Install

Free and open source

Compare AlternativesView on GitHubDocumentation

Claim this skill

Project owners can request ownership review. Approved claims unlock a stronger trust signal.

Author

H

hiroi-sora✓

@hiroi-sora

Tags

ocrdocumentsextractionocr-pythonpaddleocrqmlqtscreenshotumi-ocrpython

Platform Fit

Claude Code

Health Signals

GitHub stars
44.9K
Quality score
65/100
Last GitHub push
Nov 20, 2025
Framework hints
2
OpenAgentSkill views
2
Install copies
0
Outbound clicks
0

Community Signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & Safety

  • —Open source (public GitHub repo)
  • —AI static analysis passed
  • —License: MIT
  • —Manually verified by team

Related Skills

Stirling PDF

#1 PDF Application on GitHub that lets you edit PDFs on any device anywhere

80.3K stars · 0 installs

Tesseract

Tesseract Open Source OCR Engine (main repository)

74.6K stars · 0 installs

MinerU

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

66.8K stars · 0 installs

Docling

Get your documents ready for gen AI

61.1K stars · 0 installs