Run1 pdf form filling
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill run1_pdf-form-fillingAssembled 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 to identify, extract, and populate specific fields within a PDF form using the pdftk or pikepdf toolsets.
SKILL.md
0.9 KB, as published. Nobody here has run it
To fill a PDF form programmatically:
- Identify Field Names: Use
pdftk /root/sc100-blank.pdf dump_data_fieldsto list all available form fields and their current values. - Prepare Data: Create a data mapping of the field names found in the previous step to the values provided in the case description (e.g., Plaintiff Name, Defendant Address, Claim Amount).
- Populate: Use
pdftk /root/sc100-blank.pdf fill_form data.fdf output /root/sc100-filled.pdfor an equivalent Python library likepypdfto inject the data. - Verification: Always inspect the output file to ensure that long strings (like addresses) are not truncated and that formatting (like date strings) matches the required format (YYYY-MM-DD).