Agent Skills: Image Processing

Process, transform, and analyze images using common operations

UncategorizedID: tatat/agents-playground/image-processing

Skill Files

Browse the full folder contents for image-processing.

Download Skill

Loading file tree…

skills/image-processing/SKILL.md

Skill Metadata

Name
image-processing
Description
Process, transform, and analyze images using common operations

Image Processing

Process and transform images.

Capabilities

  • Resize and crop images
  • Apply filters and adjustments
  • Convert between formats
  • Extract metadata and analyze content

Common Operations

Resize

from PIL import Image

img = Image.open("input.jpg")
img_resized = img.resize((800, 600), Image.LANCZOS)
img_resized.save("output.jpg")

Crop

# Crop box: (left, upper, right, lower)
img_cropped = img.crop((100, 100, 500, 400))

Format Conversion

img = Image.open("input.png")
img.convert("RGB").save("output.jpg", quality=85)

Filters

| Filter | Use Case | |--------|----------| | Blur | Reduce noise, privacy | | Sharpen | Enhance details | | Grayscale | Simplify, reduce size | | Contrast | Improve visibility |

Supported Formats

  • Input: JPEG, PNG, GIF, WebP, BMP, TIFF
  • Output: JPEG, PNG, WebP

Best Practices

  1. Preserve aspect ratio when resizing
  2. Use appropriate quality settings (JPEG: 80-90)
  3. Strip metadata for privacy if needed
  4. Consider WebP for web delivery (smaller size)

Metadata Extraction

from PIL.ExifTags import TAGS

exif = img._getexif()
for tag_id, value in exif.items():
    tag = TAGS.get(tag_id, tag_id)
    print(f"{tag}: {value}")