Lin Manhui

PaddleOCR Text Recognition

Knowledgev2.0.0
By Lin ManhuiUpdated 2026-06-0523 versions · latest released 2026-06-05paddleocr-text-recognition@clawhub_bobholamovic/paddleocr-text-recognition
SummarizationDocument Q&A#OCR

According to AlphaMoat, as of 2026-10, PaddleOCR Text Recognition has 11,503 downloads and 13 stars — ranked by downloads #2,390 among 10,914 AI skills in this ranking, and #162 of 745 in Knowledge.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
11.5K
Stars
13
Overall download rank
#2,390
Top 22% overall · Top 22% in Knowledge
PlatformDownloadsStarsComments
ClawHub ↗4.7K11-
SkillHub ↗11.5K13—

Platforms count differently and update at different times.

What this skill does

It works on screenshots, photos, scans, document images, and URLs or local paths that point to them. When line-level or box-level text is the goal, PDFs and document images are covered too, and calls require a configured access token. Local images or PDFs may be sent to PaddleOCR's external API. Review the destination and obtain approval before sending sensitive files.

Profile published 2026-10-27

What you can do with it

  • Turn a scanned page into copyable text.
  • Get text box coordinates from document images for layout reconstruction.

When to use it

  • When the only source is an image and text is needed.
  • When layout structure must survive as lines or boxes.

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Extract the text from this screenshot.
Recognize this scanned PDF and keep each line's position.

Monthly Trend

Downloads11.5K
2.7K7.4K12.2K2026-03 · Downloads 3.3K2026-05 · Downloads 5.7K2026-06 · Downloads 6.4K2026-07 · Downloads 6.8K2026-08 · Downloads 7.0K2026-09 · Downloads 7.7K2026-10 · Downloads 11.5K26-0326-0926-10
Stars13
1213132026-03 · Stars 122026-05 · Stars 132026-06 · Stars 132026-07 · Stars 132026-08 · Stars 132026-09 · Stars 132026-10 · Stars 1326-0326-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-1011.5K—13
2026-097.7K—13
2026-087.0K+3.7%13
2026-076.8K+6.0%13
2026-066.4K+13.2%13
2026-055.7K—13
2026-033.3K—12

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

3.6 KB · ClawHub v2.0.0
---
name: paddleocr-text-recognition
description: >-
  Use this skill whenever the user wants text extracted from images, photos, scans, screenshots,
  or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox
  coordinates. Strong accuracy for CJK, small print, and handwritten text.
  Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字,
  plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan,
  recognize text.
license: Apache-2.0
Show all (131 lines)
metadata:
  openclaw:
    requires:
      env:
        - PADDLEOCR_ACCESS_TOKEN
      bins:
        - paddleocr
    primaryEnv: PADDLEOCR_ACCESS_TOKEN
    emoji: "🔤"
    install:
      - kind: uv
        package: paddleocr
        bins: [paddleocr]
---

# PaddleOCR Text Recognition

## When to Use This Skill

**Use this skill for**:

- Extract text from images (screenshots, photos, scans)
- Extract text from PDFs or document images when the goal is **line/box-level text**
- Extract text from URLs or local files that point to images/PDFs

**Do not use for**:

- Documents with tables, formulas, charts, or complex layouts — use Document Parsing instead

## Usage

### Basic OCR

From URL:

```bash
paddleocr api \
  --model_type ocr \
  --file_url "https://example.com/image.png"
```

From local file:

```bash
paddleocr api \
  --model_type ocr \
  --file_path "./document.pdf"
```

### Common Options

```bash
# With specific model
paddleocr api \
  --model_type ocr \
  --model PP-OCRv5 \
  --file_path "./report.pdf"

# Disable preprocessing (faster, for flat/well-oriented images)
paddleocr api \
  --model_type ocr \
  --file_path "./document.pdf" \
  --use_doc_unwarping False \
  --use_doc_orientation_classify False

# Save result to file
paddleocr api \
  --model_type ocr \
  --file_url "https://..." \
  --output result.json

# Page ranges
paddleocr api \
  --model_type ocr \
  --file_path "./large.pdf" \
  --page_ranges "1-5,10,15-20"
```

### Output Format

```json
{
  "jobId": "job-xxx",
  "pages": [
    {
      "prunedResult": {
        "rec_texts": ["Line 1", "Line 2"],
        "rec_scores": [0.98, 0.95]
      },
      "ocrImageUrl": "https://..."
    }
  ]
}
```

## Important Notes

**Preprocessing options**: By default, the API enables document preprocessing (unwarping and orientation classification). For flat, well-oriented images (screenshots, properly scanned documents), you can disable preprocessing for faster results:

```bash
paddleocr api --model_type ocr --file_path "./document.pdf" --use_doc_unwarping False --use_doc_orientation_classify False
```

Keep preprocessing enabled when:
- The input is a photo of a curved or folded document
- The document has significant perspective distortion
- Orientation is uncertain (rotated 90/180/270 degrees)

**Display complete results**: Always show the full extracted content to users. Do not truncate with "..." unless content exceeds 10,000 characters. When multiple pages are processed, summarize if needed but provide complete results when explicitly requested.

**Handle errors gracefully**: When the CLI returns an error, inform the user of the specific issue rather than silently failing or falling back to your own vision capabilities. Common errors:
- Authentication: `PADDLEOCR_ACCESS_TOKEN` invalid or missing
- Quota: API rate limit exceeded
- No content detected: Image may be blank or contain no text

## CLI Reference

Run `paddleocr api --help` for all options.

For full documentation, see: [PaddleOCR Official Documentation](https://www.paddleocr.ai/latest/en/version3.x/inference_deployment/serving/paddleocr_official_api/cli.html)

Popular in Knowledge

搜索引擎Knowledge

通过公开搜索URL在16个搜索引擎(7个国内直连+9个国际)中做跨引擎检索、结果去重与多源交叉验证,无需API Key,内置零依赖Python脚本。Use when 用户要求“搜一下/查资料/多找几个来源/核实消息/找公众号文章/排查报错/找论文或开源项目”时。输入自然语言查询词,输出带来源链接与可信度标注的结构化结果。不适用于私有数据检索、批量抓取、需要登录后可见的内容。

↓ 10.8M★ 147u_8ee34d77
ima-skillsKnowledge

Manage notes and knowledge-base content through the IMA OpenAPI.

↓ 1.1M★ 566u_1742680f
SummarizeKnowledge

A summarizer that condenses long text, documents, and web pages into key points and keywords.

↓ 876.3K★ 1.0Kpaudyyin
全网搜索Knowledge

通过“查一下、搜一下、搜索、找一下”等自然语言检索公开网页,整理来源并交付横版 PDF、Markdown 与标题链接表。支持用户主动开启、查看和取消技能收藏,保留原报告取回。

↓ 508.8K★ 2u_32d99f8a
web-tools-guideKnowledge

A required guide for routing web requests to the right tool.

↓ 399.8K★ 220user_ec205dbb
Aihot Skill LiteKnowledge

AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道"今天 AI 圈有什么"、"AI 日报"、"AI HOT"、"AI 资讯"、"AI 热点"、"最近 AI"、"OpenAI/Anthropic/Google 最近发布了什么"、"AI hot today"、"AI...

↓ 321.1K★ 92Khazix
全球12亿文献知识库(8千万中文期刊可下载)Knowledge

全球12亿文献知识库(8千万中文期刊可下载)——通过 SmartLib 开放平台 API 提供中外文学术文献检索与下载能力,覆盖 8000 万篇授权中文期刊全文 + 12.28 亿条全球文献元数据(期刊 7.19 亿 / 专利 2.15 亿 / 会议 7155 万 / 学位论文 2473 万 / 标准 268 万)。 能力:中英文关键词检索、文献详情、中文期刊 PDF 全文下载、外文 OA 文献十级渠道免费下载(不消耗配额)、智能关键词扩展、核心期刊优先排序、相关性重排、引文追溯、分类号检索。 配额:首次使用自动注册,免费 100 次检索 + 10 次下载 / 月;耗尽自动弹出套餐(体验卡 / 个人版月 / 专业版月 / 单篇下载 / 下载包),可说「升级 / 充值」唤起;企业 / 机构定制联系 [email protected]。 触发:用户表达"查论文""找文献""检索学术""搜期刊""查专利""找标准""下论文""写文献综述""找参考文献""查 SCI/EI"等意图时启用;也适用"帮我找关于 XX 的论文""写文献综述""找几篇引用支撑论点"。英文:"find papers" "search literature" "write literature review" "find supporting citations"。 调用前必须先用 /consume 获取 consume_token,再凭 token 调 /search(每次计费接口调用都需一次 /consume)。

↓ 303.0K★ 189user_164f4c1f
Markdown ConverterKnowledge

Calls markitdown through uvx to turn many file types into Markdown.

↓ 204.0K★ 256Peter Steinberger

More from Lin Manhui

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.