Run3 csv generation
Aggregate object counts into a structured CSV file.From its SKILL.md
npx -y skills add cxcscmu/SkillLearnBench --skill run3_csv_generationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
0.9 KB, 196 tokens by cl100k_base, as published. Nobody here has run it
Iterate through the sorted list of frame files, perform object detection for each, and write the data to /root/counting_results.csv with the header: frame_id,coins,enemies,turtles.
import csv
import glob
import subprocess
files = sorted(glob.glob('/root/keyframes_*.png'))
with open('/root/counting_results.csv', 'w', newline='') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(['frame_id', 'coins', 'enemies', 'turtles'])
for file_path in files:
counts = []
for template in ['/root/coin.png', '/root/enemy.png', '/root/turtle.png']:
result = subprocess.run(['python3', 'scripts/count_objects.py', '--image', file_path, '--template', template], capture_output=True, text=True)
counts.append(result.stdout.strip())
writer.writerow([file_path] + counts)
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.