Ocr Service

Simple OCR extraction wrapped in a Python client. You pass it a base64 encoded image and it returns the text, supporting multiple formats and languages according to the docs. The API is straightforward: health check, image conversion helper, and the main OCR call. With 276 installs and passing most security audits (Snyk shows a warning worth checking), it's seeing real use. The documentation is minimal and partly in Chinese, which might signal where the primary development focus is. If you need basic text extraction from images without dealing with complex ML setup, this does the job.

skills.sh installs: 302
GitHub stars: 7
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add lin-a1/skills-agent --skill ocr-service --agent claude-code

Installs into .claude/skills of the current project.

Files

功能

从图像中提取文字内容，支持多种图像格式和语言。

调用方式

from services.ocr_service.client import OCRServiceClient

client = OCRServiceClient()

# 健康检查
status = client.health_check()

# OCR识别
image_base64 = client.image_to_base64("/path/to/image.jpg")
result = client.ocr(image_base64)

# 获取识别结果
texts = result["rec_texts"]    # ["识别的文字1", "识别的文字2", ...]
scores = result["rec_scores"]  # [0.98, 0.95, ...]

返回格式

{
  "doc_preprocessor_res": {"angle": 0},
  "dt_polys": [[x1,y1], [x2,y2], ...],
  "rec_texts": ["识别的文字1", "识别的文字2"],
  "rec_scores": [0.98, 0.95]
}

字段说明

rec_texts: 识别出的文字列表
rec_scores: 每个文字块的置信度
dt_polys: 检测到的文本区域坐标

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Details

Repository: github.com/lin-a1/skills-agent
Categories: AI & Agent Building, Office & Documents
First seen: Jun 3, 2026