liteparse vs PDF
Сравнение двух Agent Skills бок о бок. Выбери подходящий для Claude Code или Claude Desktop.
Local document and PDF parsing with spatial text and bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; OCR on scans; layout-pre
Сравнение
| Параметр | liteparse | |
|---|---|---|
| Скрипты | есть | есть |
| Разрешённые инструменты | 1 | 3 |
| Тип установки | personal | personal |
| Категория | documents | documents |
| Проверен | — | |
| Лицензия | Apache-2.0 | MIT |
| Автор | K-Dense AI | Anthropic |
| Repo | K-Dense-AI/scientific-agent-skills | anthropics/skills |
Когда брать liteparse
Local document and PDF parsing with spatial text and bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; OCR on scans; layout-preserved JSON for RAG; batch-ingesting paper folders; or page screenshots for multimodal agents — even when the user does not name liteparse. Prefer over MarkItDown when you need bboxes, fast local parsing, or PNG page renders; prefer over the pdf skill for merge/split/forms.
Когда брать PDF
A skill for working with PDF files: extract text and tables, fill in form fields, split and merge documents, and convert pages to images — all from within Claude.
Ищешь другое? Все скиллы.