Xpersona
O

OCR - Local (No API Key)

CLAWHUB · Unverified

Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English. Skill: OCR - Local (No API Key) Owner: shaw555 Summary: Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-03-14T23:38:29.815Z | user Local OCR skill using Tesseract.js, no API key required Archive index: Archive v1.0.0: 7 files, 5938 bytes Files: package.json (615b), PUBLISH.md (20

62
Rank
84
Safety
21k
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 20.6K downloads reported by the source. Last updated 11/16/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: medium.

clawhub skill install s17b01bv27h3qeag7mh9c1j9jn83fqbx:ocr-local
  1. Setup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-shaw555-ocr-local-cr-local-2/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

8,186 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: ocr-local
description: Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English.
homepage: https://github.com/naptha/tesseract.js
metadata: {"openclaw":{"emoji":"📝","requires":{"bins":["node"]},"install":[{"id":"npm","kind":"npm","packages":["tesseract.js"],"label":"Install tesseract.js"}]}}
---

# OCR - Image Text Recognition (Local)

Extract text from images using Tesseract.js. **100% local run, no API key required.** Supports Chinese and English.

## Quick start

```bash
node {baseDir}/scripts/ocr.js /path/to/image.jpg
node {baseDir}/scripts/ocr.js /path/to/image.png --lang chi_sim
node {baseDir}/scripts/ocr.js /path/to/image.jpg --lang chi_tra+eng
```

## Options

- `--lang <langs>`: Language codes (default: chi_sim+eng)
  - `chi_sim` - Simplified Chinese
  - `chi_tra` - Traditional Chinese  
  - `eng` - English
  - Combine with `+`: `chi_sim+eng`

- `--json`: Output as JSON instead of plain text

## Examples

```bash
# Recognize Chinese screenshot
node {baseDir}/scripts/ocr.js screenshot.png

# Recognize English document
node {baseDir}/scripts/ocr.js document.jpg --lang eng

# Mixed Chinese + English
node {baseDir}/scripts/ocr.js mixed.png --lang chi_sim+eng
```

## Notes

- First run downloads language data (~20MB per language)
- Subsequent runs are cached locally
- Works best with clear, high-contrast images
- For handwritten text, accuracy may vary

README.md

# OCR Skill for OpenClaw

📝 Extract text from images using Tesseract.js OCR.

## Features

- **Multi-language support**: Simplified Chinese, Traditional Chinese, English
- **Easy to use**: Single command to recognize any image
- **Flexible output**: Plain text or JSON format
- **No API key required**: Runs locally with Tesseract.js

## Installation

```bash
# Via ClawHub (recommended)
# Coming soon to ClawHub

# Manual installation
git clone https://github.com/openclaw/skill-ocr.git ~/.openclaw/workspace/skills/ocr
cd ~/.openclaw/workspace/skills/ocr
npm install
```

## Usage

```bash
# Basic usage (Chinese + English)
node {baseDir}/scripts/ocr.js /path/to/image.jpg

# Specify language
node {baseDir}/scripts/ocr.js image.png --lang chi_sim
node {baseDir}/scripts/ocr.js image.png --lang chi_tra+eng
node {baseDir}/scripts/ocr.js image.png --lang eng

# JSON output
node {baseDir}/scripts/ocr.js image.jpg --json
```

## Language Codes

- `chi_sim` - Simplified Chinese
- `chi_tra` - Traditional Chinese
- `eng` - English
- Combine with `+`: `chi_sim+eng`, `chi_tra+eng`

## Examples

### Recognize a screenshot
```bash
node ~/.openclaw/workspace/skills/ocr/scripts/ocr.js ~/Downloads/screenshot.png
```

### Extract text from a photo of document
```bash
node ~/.openclaw/workspace/skills/ocr/scripts/ocr.js document.jpg --lang chi_sim+eng
```

### Get structured output with confidence scores
```bash
node ~/.openclaw/workspace/skills/ocr/scripts/ocr.js image.jpg --json
```

## Notes

- First run downloads Tesseract.js language data (~20MB per language)
- Subsequent runs use cached data
- Works best with clear, high-contrast images
- Handwritten text recognition accuracy may vary
- For best results, ensure images are well-lit and text is clearly visible

## License

MIT License

## Credits

Powered by [Tesseract.js](https://github.com/naptha/tesseract.js)

_meta.json

{
  "ownerId": "kn76tv0e2bf2bjea89hadd010n82xz04",
  "slug": "ocr-local",
  "version": "1.0.0",
  "publishedAt": 1773531509815
}

PUBLISH.md

# OCR Skill 发布清单

## 文件结构

```
ocr/
├── SKILL.md           # OpenClaw 技能定义(必需)
├── package.json       # NPM 配置和依赖
├── README.md          # 使用说明
├── .gitignore         # Git 忽略文件
├── scripts/
│   └── ocr.js         # OCR 主脚本
└── PUBLISH.md         # 本文件
```

## 发布步骤

### 1. 确认文件完整
- [x] SKILL.md - 技能定义
- [x] package.json - NPM 配置
- [x] README.md - 使用文档
- [x] scripts/ocr.js - 主脚本
- [x] .gitignore - Git 配置

### 2. 清理不必要文件
已删除:
- ❌ node_modules/ - 用户安装时会自动下载
- ❌ *.traineddata - Tesseract 语言数据(运行时自动下载)
- ❌ package-lock.json - 让用户使用最新版本

### 3. 发布到 ClawHub

**方式 A:使用 CLI**
```bash
cd ~/.openclaw/workspace/skills/ocr
clawhub publish . --changelog "Initial release - OCR skill with Tesseract.js support for Chinese and English text recognition"
```

**方式 B:通过网站**
1. 访问 https://clawhub.com
2. 登录账号
3. 点击 "Publish Skill"
4. 上传整个 `ocr` 文件夹

### 4. 发布后验证

```bash
# 搜索技能
clawhub search ocr

# 安装测试
clawhub install ocr

# 测试使用
node ~/.openclaw/workspace/skills/ocr/scripts/ocr.js test-image.jpg
```

## 技能信息

- **名称**: OCR - Image Text Recognition
- **版本**: 1.0.0
- **作者**: OpenClaw Community
- **许可**: MIT
- **分类**: Productivity
- **标签**: ocr, image, text-recognition, tesseract, chinese, image-to-text

## 功能特性

✅ 支持简体中文识别
✅ 支持繁体中文识别
✅ 支持英文识别
✅ 多语言混合识别
✅ 纯本地运行(无需 API Key)
✅ 支持 JSON 格式输出

## 依赖

- Node.js >= 18.0.0
- tesseract.js ^7.0.0

## 首次运行说明

用户首次使用时会下载 Tesseract 语言数据(约 20MB/语言),后续运行使用缓存。

---

**准备就绪,可以发布!** 🚀

skill-card.md

## Description:

Extract text from images using Tesseract.js OCR (100% local, no API key required). Supports Chinese (simplified/traditional) and English.

This skill is ready for commercial/non-commercial use.

## Publisher:

[shaw555](https://clawhub.ai/user/shaw555)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and end users use this skill to extract text from local images, screenshots, and documents in Simplified Chinese, Traditional Chinese, and English without using an OCR API key.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Installation and first use can download npm packages and Tesseract language data from third-party sources.

Mitigation: Use environments that permit those downloads, or pin tesseract.js to a reviewed exact version, add a lockfile, and prefetch or vendor required language data for offline or restricted deployments.

Risk: OCR output may be inaccurate for handwritten, low-contrast, poorly lit, or unclear images.

Mitigation: Review extracted text before using it in downstream decisions, and prefer clear, high-contrast source images.

## Reference(s):

- [Tesseract.js Project](https://github.com/naptha/tesseract.js)
- [ClawHub Skill Page](https://clawhub.ai/shaw555/skills/ocr-local)

## Skill Output:

**Output Type(s):** [text, JSON]

**Output Format:** [Plain text, or JSON containing recognized text, confidence scores, words, and bounding boxes]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Language selection supports chi_sim, chi_tra, eng, and combined language codes; OCR quality depends on source image clarity.]

## Skill Version(s):

1.0.0 (source: server release evidence and package.json)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Sponsored

Ads related to OCR - Local (No API Key) and adjacent AI workflows.