agentsclimarketplace

Run3 convert keyframes to grayscale

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/video-object-counting/run3_convert-keyframes-to-grayscale

Use this skill to convert extracted keyframe PNG images to grayscale in-place using Python3 and PIL/Pillow. Only convert keyframe images, NOT template images (coin.png, enemy.png, turtle.png).From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run3_convert-keyframes-to-grayscale

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.2 KB, 250 tokens by cl100k_base, as published. Nobody here has run it

Convert keyframes to grayscale in-place

Important: Only convert the extracted keyframe images to grayscale. Do NOT convert the template images (coin.png, enemy.png, turtle.png) — those must remain in their original color format.

Using Python3 with Pillow

import glob
from PIL import Image

# Only convert keyframes, NOT templates
keyframe_files = sorted(glob.glob('/root/keyframes_*.png'))

for fpath in keyframe_files:
    img = Image.open(fpath).convert('L')  # Convert to grayscale
    img.save(fpath)  # Override in place
    print(f"Converted {fpath} to grayscale")

Alternative: Using a bash loop with Python3 one-liner

for f in /root/keyframes_*.png; do
    python3 -c "from PIL import Image; Image.open('$f').convert('L').save('$f')"
done

Verification

Check that the images are indeed grayscale:

from PIL import Image
img = Image.open('/root/keyframes_001.png')
print(img.mode)  # Should print 'L' for grayscale

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.