用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/Lap-Platform/claude-marketplace --skill ocrapi命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | ocrapi |
| description | ocrapi API skill. Use when working with ocrapi for ocr. Covers 20 endpoints. |
| version | 1.0.0 |
| generator | lapsh |
API version: v1
ApiKey Apikey in header
20 endpoints across 1 groups. See references/api-spec.lap for full details.
| Method | Path | Description |
|---|---|---|
| POST | /ocr/image/toText | Convert a scanned image into text |
| POST | /ocr/image/to/words-with-location | Convert a scanned image into words with location |
| POST | /ocr/image/to/lines-with-location | Convert a scanned image into words with location |
| POST | /ocr/photo/toText | Convert a photo of a document into text |
| POST | /ocr/photo/to/words-with-location | Convert a photo of a document or receipt into words with location |
| POST | /ocr/photo/recognize/receipt | Recognize a photo of a receipt, extract key business information |
| POST | /ocr/photo/recognize/business-card | Recognize a photo of a business card, extract key business information |
| POST | /ocr/photo/recognize/form | Recognize a photo of a form, extract key fields and business information |
| POST | /ocr/photo/recognize/form/advanced | Recognize a photo of a form, extract key fields using stored templates |
| POST | /ocr/pdf/toText | Converts an uploaded PDF file into text via Optical Character Recognition. |
| GET | /ocr/pdf/get-job-status | Returns the result of the Async Job - possible states can be STARTED or COMPLETED |
| POST | /ocr/pdf/to/words-with-location | Convert a PDF into words with location |
| POST | /ocr/pdf/to/lines-with-location | Convert a PDF into text lines with location |
| POST | /ocr/preprocessing/image/binarize | Convert an image of text into a binarized (light and dark) view |
| POST | /ocr/preprocessing/image/binarize/advanced | Convert an image of text into a binary (light and dark) view with ML |
| POST | /ocr/preprocessing/image/get-page-angle | Get the angle of the page / document / receipt |
| POST | /ocr/preprocessing/image/unrotate | Detect and unrotate a document image |
| POST | /ocr/preprocessing/image/unrotate/advanced | Detect and unrotate a document image (advanced) |
| POST | /ocr/preprocessing/image/unskew | Detect and unskew a photo of a document |
| POST | /ocr/receipts/photo/to/csv | Convert a photo of a receipt into a CSV file containing structured information from the receipt |
Match user requests to endpoints in references/api-spec.lap. Key patterns:
Generated from the official API spec by LAP