Run3 skill 1
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.From the repository description
npx -y skills add cxcscmu/SkillLearnBench --skill run3_skill-1Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
0.6 KB, 151 tokens by cl100k_base, as published. Nobody here has run it
[SKILL]
name: robust_text_extraction description: Extracts text from PDFs, PPTX, DOCX, and other documents robustly using CLI tools like pdftotext and markitdown. Includes proper exception handling, timeouts, and fallbacks to ensure the extraction loop does not fail on complex encodings or shapes.
import subprocess
import os
def extract_text_robustly(file_path, max_length=50000):
"""
Robust text extraction handling various formats gracefully.
Uses pdftotext for PDFs and markitdown for PPTX/DOCX.
Returns the extracted text, capped at max_length to save memory during classification.
"""
ext = file
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.