Run3 Extract PDF Form Field Names

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/court-form-filling/run3_Extract-PDF-Form-Field-Names

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Install

npx -y skills add cxcscmu/SkillLearnBench --skill run3_Extract-PDF-Form-Field-Names

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Use this skill first to discover the actual field names in a PDF form. Extracts and prints all form field names from a PDF file to ensure accurate field mapping before filling the form.

SKILL.md

2.0 KB, as published. Nobody here has run it

Extract PDF Form Field Names

Purpose

Discover the exact field names in a PDF form before attempting to fill it. This prevents mapping errors and field-not-found issues.

Implementation

import pdfrw

def extract_pdf_field_names(pdf_path):
    """
    Extract all form field names from a PDF.
    
    Args:
        pdf_path: Path to the PDF file
    
    Returns:
        List of field names
    """
    template = pdfrw.PdfReader(pdf_path)
    field_names = []
    
    if template.Root.AcroForm is None:
        print("No form fields found in PDF")
        return field_names
    
    for page in template.pages:
        annotations = page.get("/Annots")
        if annotations:
            for annotation in annotations:
                if annotation["/Subtype"] == "/Widget":
                    field_name = annotation["/T"]
                    if field_name:
                        # Remove parentheses that pdfrw adds
                        clean_name = field_name[1:-1] if field_name.startswith('(') else field_name
                        field_names.append(clean_name)
                        print(f"Field found: {clean_name}")
    
    return field_names

# Run extraction
pdf_path = "/root/sc100-blank.pdf"
fields = extract_pdf_field_names(pdf_path)
print(f"\nTotal fields found: {len(fields)}")

Steps

Load the PDF using pdfrw
Check if form exists in Root.AcroForm
Iterate through all pages and annotations
Extract field names from Widget annotations
Clean field names (remove parentheses added by pdfrw)
Print each field name for verification
Use the printed names for accurate field mapping

Notes

Run this skill BEFORE attempting to fill the form
Document all field names printed to ensure mapping accuracy
Field names are case-sensitive