Run2 pdf form filler
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill run2_pdf-form-fillerAssembled 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
Improved skill for filling XFA/non-standard PDFs using FreeText annotations when field mapping is unavailable.
SKILL.md
0.9 KB, as published. Nobody here has run it
PDF Form Filler Skill (Round 2)
This skill addresses XFA/complex PDF form challenges by using FreeText annotations for field population.
Usage
When field-based filling (via update_page_form_field_values) fails due to XFA structure or non-standard forms, utilize annotation-based filling.
Steps
- Identify fields manually or via
get_fields(). - Map fields to visual page coordinates.
- Use a script to overlay text using
FreeTextannotations. - Execute via the
scripts/fill_pdf_form_with_annotations.pyutility.
Example
# Create a JSON configuration mapping pages, bounding boxes, and field values.
# Use the annotation script:
# python scripts/fill_pdf_form_with_annotations.py input.pdf fields.json output.pdf