| name | pdf-doc-processing |
| description | Use when reading, extracting, summarizing, or converting PDFs related to landscape project documentation, client briefs, reference packs, estimates, contracts, or scanned drawings. |
PDF Doc Processing
Goal
Extract project-useful information from PDFs without losing page references or bloating context.
Process
- Identify PDF type: text PDF, scan, drawing, presentation, estimate, contract.
- If a text layer is available, extract relevant text using available means.
- If there is no text layer, use OCR/VLM-style processing or work page by page with screenshots/exports.
- Save the result in the relevant project folder or
91_references if it is a shared sample.
- For large PDFs, create a short index: pages, topics, important excerpts, what applies to the project.
- Do not convert the whole PDF into Markdown unless necessary.
Extract
- Documentation scope.
- Client requirements.
- Dimensions, areas, quantities.
- Prices and price dates.
- Legal or technical constraints.
- Pages with layout examples.
Output
- Short summary.
- Table: page -> meaning -> action.
- Requirements to move into brief, documentation, or estimate.