# PDF Extract

> Extracts text and tables from PDFs, fills forms, and merges documents. Use when the user mentions PDFs, form filling, or document extraction. Do not use for scanned image-only PDFs without OCR.

- Skill: `gesh75/pdf-extract` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add gesh75/pdf-extract`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gesh75/pdf-extract/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- License: MIT
- Author: gesh75 (https://skillmd.com/u/gesh75)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/gesh75/pdf-extract

---


# PDF extract

1. Confirm the file path and the desired output (text, tables, filled form, merge).
2. Prefer `scripts/extract.py` over ad-hoc one-liners.
3. For form field maps see [FORMS.md](references/FORMS.md).
4. Return the artifact path and a one-line summary of pages processed.

Do not load every page into context. Stream through the script and keep only the rows you need.

```python
python scripts/extract.py input.pdf --tables
```

## Safety

Never upload the PDF to a third-party API. Confirm page count before writing.