Run2 pdf parsing pro
[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_parsing_proAssembled 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
Advanced PDF parsing for calendar extraction, including sidebar filtering and color-based classification.
SKILL.md
0.6 KB, as published. Nobody here has run it
Advanced PDF Calendar Extraction
When parsing complex PDF calendars, filtering non-calendar elements (like sidebars) and accurately mapping coordinates to time is crucial.
Sidebar and Noise Filtering
- Identify the main calendar grid by filtering by x-coordinates (e.g.,
x1 > 500). - Filtering by height to avoid icons/small labels.
- Map vertical coordinates (
top) to minutes using a calibrated scale.