Run2 pdf field mapping

[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 run2_pdf-field-mapping

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

Techniques for mapping case descriptions to PDF form fields.

0.7 KB, as published. Nobody here has run it

When mapping case data to PDF fields:

Analyze Field IDs: Look for keywords in the field_id (e.g., PlaintiffName, DefendantAddress, ClaimAmount).
Use Bounding Boxes: If IDs are cryptic, use the rect (bounding box) and the page number to identify the field's position on the form.
Handle Checkboxes: Identify the checked_value for "Yes" or "No" options. Usually, /1 is Yes and /2 or /Off is No, but verify in field_info.json.
Consistency Check: Ensure that data like names and addresses are consistent across different sections of the form (e.g., caption vs. detailed info).