Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Extracts structured data from construction PDFs, including specifications, bills of materials, schedules, and reports. Supports both native PDFs via pdfplumber and scanned documents via OCR. Outputs to Excel, CSV, or JSON.
Handles both native and scanned PDFs in one workflow, eliminating the need to switch between tools depending on document type.
When to use it
- Extracting a bill of materials table from a construction spec PDF
- Converting scanned project schedules into Excel for analysis
- Batch processing a folder of PDF reports into a single spreadsheet
- Pulling section numbers and titles from a technical specification document
- Exporting parsed PDF tables to JSON for downstream API integration
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: extract all tables from material_specification.pdf and save to Excel
- 1Open PDF with pdfplumber
- 2Iterate over each page and call extract_tables()
- 3Convert each table to a DataFrame with page and table metadata
- 4Concatenate all DataFrames
- 5Export combined DataFrame to materials.xlsx
materials.xlsx containing all extracted tables with _page and _table columns
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.