[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71BYW86K4D7D9PSGH10HGD3":3,"skill-same:01M71BYW86K4D7D9PSGH10HGD3":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M71BYW86K4D7D9PSGH10HGD3","image-utils",null,"Classic image manipulation with Python Pillow - resize, crop, composite, format conversion, watermarks, brightness\u002Fcontrast adjustments, and web optimization. Use this skill when post-processing AI-generated images, preparing images for web delivery, batch processing image directories, creating responsive image variants, or performing any deterministic pixel-level image operation. Works standalone or alongside bria-ai for post-processing generated images.","strmt7\u002Fai_skills_collection_benchmarked","strmt7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F28989754?v=4","01M71929P914SWKQ7QJV24NBBY","Stratos","01M71929Q9VGKQ7PWYR95VSQQQ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcreative-media-design\u002Flatest-release-creative\u002Fimage-utils\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"image","image utils","utils","batch","conversion","operation","bria ai","when","use","generated","variants","pixel","python","Optimization","for","directories","processing","standalone","deterministic","images","2026-11-10 10:12:30",false,"---\nname: image-utils\ndescription: Classic image manipulation with Python Pillow - resize, crop, composite, format conversion, watermarks, brightness\u002Fcontrast adjustments, and web optimization. Use this skill when post-processing AI-generated images, preparing images for web delivery, batch processing image directories, creating responsive image variants, or performing any deterministic pixel-level image operation. Works standalone or alongside bria-ai for post-processing generated images.\nlicense: MIT\nmetadata:\n  author: Bria AI\n  version: \"1.3.1\"\n---\n\n# Image Utilities\n\nPillow-based utilities for deterministic pixel-level image operations. Use for resize, crop, composite, format conversion, watermarks, and other standard image processing tasks.\n\n## When to Use This Skill\n\n- **Post-processing AI-generated images**: Resize, crop, optimize for web after generation\n- **Format conversion**: PNG ↔ JPEG ↔ WEBP with quality control\n- **Compositing**: Overlay images, paste subjects onto backgrounds\n- **Batch processing**: Resize to multiple sizes, add watermarks\n- **Web optimization**: Compress and resize for fast delivery\n- **Social media preparation**: Crop to platform-specific aspect ratios\n\n## When NOT to Use This Skill — Use `bria-ai` Instead\n\nThis skill handles **deterministic pixel-level operations** only. For any **generative or AI-powered** image work, use the `bria-ai` skill instead:\n\n- **Generating images from text prompts** → use `bria-ai`\n- **AI background removal or replacement** → use `bria-ai`\n- **AI image editing (inpainting, object removal\u002Faddition)** → use `bria-ai`\n- **Style transfer or AI-driven visual effects** → use `bria-ai`\n- **Creating product lifestyle shots with AI** → use `bria-ai`\n- **Image upscaling with AI super-resolution** → use `bria-ai`\n\n**Rule of thumb**: If the task requires *creating new visual content* or *understanding image semantics*, use `bria-ai`. If the task requires *transforming existing pixels* (resize, crop, format convert, watermark), use this skill.\n\nIf `bria-ai` is not available, install it with:\n```bash\nnpx skills add bria-ai\u002Fbria-skill\n```\n\n## Quick Reference\n\n| Operation | Method | Description |\n|-----------|--------|-------------|\n| **Loading** | `load(source)` | Load from URL, path, bytes, or base64 |\n| | `load_from_url(url)` | Download image from URL |\n| **Saving** | `save(image, path)` | Save with format auto-detection |\n| | `to_bytes(image, format)` | Convert to bytes |\n| | `to_base64(image, format)` | Convert to base64 string |\n| **Resizing** | `resize(image, width, height)` | Resize to exact dimensions |\n| | `scale(image, factor)` | Scale by factor (0.5 = half) |\n| | `thumbnail(image, size)` | Fit within size, maintain aspect |\n| **Cropping** | `crop(image, left, top, right, bottom)` | Crop to region |\n| | `crop_center(image, width, height)` | Crop from center |\n| | `crop_to_aspect(image, ratio)` | Crop to aspect ratio |\n| **Compositing** | `paste(bg, fg, position)` | Overlay at coordinates |\n| | `composite(bg, fg, mask)` | Alpha composite |\n| | `fit_to_canvas(image, w, h)` | Fit onto canvas size |\n| **Borders** | `add_border(image, width, color)` | Add solid border |\n| | `add_padding(image, padding)` | Add whitespace padding |\n| **Transforms** | `rotate(image, angle)` | Rotate by degrees |\n| | `flip_horizontal(image)` | Mirror horizontally |\n| | `flip_vertical(image)` | Flip vertically |\n| **Watermarks** | `add_text_watermark(image, text)` | Add text overlay |\n| | `add_image_watermark(image, logo)` | Add logo watermark |\n| **Adjustments** | `adjust_brightness(image, factor)` | Lighten\u002Fdarken |\n| | `adjust_contrast(image, factor)` | Adjust contrast |\n| | `adjust_saturation(image, factor)` | Adjust color saturation |\n| | `blur(image, radius)` | Apply Gaussian blur |\n| **Web** | `optimize_for_web(image, max_size)` | Optimize for delivery |\n| **Info** | `get_info(image)` | Get dimensions, format, mode |\n\n## Requirements\n\n```bash\npip install Pillow requests\n```\n\n## Basic Usage\n\n```python\nfrom image_utils import ImageUtils\n\n# Load from URL\nimage = ImageUtils.load_from_url(\"https:\u002F\u002Fexample.com\u002Fimage.jpg\")\n\n# Or load from various sources\nimage = ImageUtils.load(\"\u002Fpath\u002Fto\u002Fimage.png\")         # File path\nimage = ImageUtils.load(image_bytes)                  # Bytes\nimage = ImageUtils.load(\"data:image\u002Fpng;base64,...\")  # Base64\n\n# Resize and save\nresized = ImageUtils.resize(image, width=800, height=600)\nImageUtils.save(resized, \"output.webp\", quality=90)\n\n# Get image info\ninfo = ImageUtils.get_info(image)\nprint(f\"{info['width']}x{info['height']} {info['mode']}\")\n```\n\n## Resizing & Scaling\n\n```python\n# Resize to exact dimensions\nresized = ImageUtils.resize(image, width=800, height=600)\n\n# Resize maintaining aspect ratio (fit within bounds)\nfitted = ImageUtils.resize(image, width=800, height=600, maintain_aspect=True)\n\n# Resize by width only (height auto-calculated)\nresized = ImageUtils.resize(image, width=800)\n\n# Scale by factor\nhalf = ImageUtils.scale(image, 0.5)    # 50% size\ndouble = ImageUtils.scale(image, 2.0)  # 200% size\n\n# Create thumbnail\nthumb = ImageUtils.thumbnail(image, (150, 150))\n```\n\n## Cropping\n\n```python\n# Crop to specific region\ncropped = ImageUtils.crop(image, left=100, top=50, right=500, bottom=350)\n\n# Crop from center\ncenter = ImageUtils.crop_center(image, width=400, height=400)\n\n# Crop to aspect ratio (for social media)\nsquare = ImageUtils.crop_to_aspect(image, \"1:1\")      # Instagram\nwide = ImageUtils.crop_to_aspect(image, \"16:9\")       # YouTube thumbnail\nstory = ImageUtils.crop_to_aspect(image, \"9:16\")      # Stories\u002FReels\n\n# Control crop anchor\ntop_crop = ImageUtils.crop_to_aspect(image, \"16:9\", anchor=\"top\")\nbottom_crop = ImageUtils.crop_to_aspect(image, \"16:9\", anchor=\"bottom\")\n```\n\n## Compositing\n\n```python\n# Paste foreground onto background\nresult = ImageUtils.paste(background, foreground, position=(100, 50))\n\n# Alpha composite (foreground must have transparency)\nresult = ImageUtils.composite(background, foreground)\n\n# Fit image onto canvas with letterboxing\ncanvas = ImageUtils.fit_to_canvas(\n    image,\n    width=1200,\n    height=800,\n    background_color=(255, 255, 255, 255),  # White\n    position=\"center\"  # or \"top\", \"bottom\"\n)\n```\n\n## Format Conversion\n\n```python\n# Convert to different formats\npng_bytes = ImageUtils.to_bytes(image, \"PNG\")\njpeg_bytes = ImageUtils.to_bytes(image, \"JPEG\", quality=85)\nwebp_bytes = ImageUtils.to_bytes(image, \"WEBP\", quality=90)\n\n# Get base64 for data URLs\nbase64_str = ImageUtils.to_base64(image, \"PNG\")\ndata_url = ImageUtils.to_base64(image, \"PNG\", include_data_url=True)\n# Returns: \"data:image\u002Fpng;base64,...\"\n\n# Save with format auto-detected from extension\nImageUtils.save(image, \"output.png\")\nImageUtils.save(image, \"output.jpg\", quality=85)\nImageUtils.save(image, \"output.webp\", quality=90)\n```\n\n## Watermarks\n\n```python\n# Text watermark\nwatermarked = ImageUtils.add_text_watermark(\n    image,\n    text=\"© 2024 My Company\",\n    position=\"bottom-right\",  # bottom-left, top-right, top-left, center\n    font_size=24,\n    color=(255, 255, 255, 128),  # Semi-transparent white\n    margin=20\n)\n\n# Logo\u002Fimage watermark\nlogo = ImageUtils.load(\"logo.png\")\nwatermarked = ImageUtils.add_image_watermark(\n    image,\n    watermark=logo,\n    position=\"bottom-right\",\n    opacity=0.5,\n    scale=0.15,  # 15% of image width\n    margin=20\n)\n```\n\n## Adjustments\n\n```python\n# Brightness (1.0 = original, \u003C1 darker, >1 lighter)\nbright = ImageUtils.adjust_brightness(image, 1.3)\ndark = ImageUtils.adjust_brightness(image, 0.7)\n\n# Contrast (1.0 = original)\nhigh_contrast = ImageUtils.adjust_contrast(image, 1.5)\n\n# Saturation (0 = grayscale, 1.0 = original, >1 more vivid)\nvivid = ImageUtils.adjust_saturation(image, 1.3)\ngrayscale = ImageUtils.adjust_saturation(image, 0)\n\n# Sharpness\nsharp = ImageUtils.adjust_sharpness(image, 2.0)\n\n# Blur\nblurred = ImageUtils.blur(image, radius=5)\n```\n\n## Transforms\n\n```python\n# Rotate (counter-clockwise, degrees)\nrotated = ImageUtils.rotate(image, 45)\nrotated = ImageUtils.rotate(image, 90, expand=False)  # Don't expand canvas\n\n# Flip\nmirrored = ImageUtils.flip_horizontal(image)\nflipped = ImageUtils.flip_vertical(image)\n```\n\n## Borders & Padding\n\n```python\n# Add solid border\nbordered = ImageUtils.add_border(image, width=5, color=(0, 0, 0))\n\n# Add padding (whitespace)\npadded = ImageUtils.add_padding(image, padding=20)  # Uniform\npadded = ImageUtils.add_padding(image, padding=(10, 20, 10, 20))  # left, top, right, bottom\n```\n\n## Web Optimization\n\n```python\n# Optimize for web delivery\noptimized_bytes = ImageUtils.optimize_for_web(\n    image,\n    max_dimension=1920,  # Resize if larger\n    format=\"WEBP\",       # Best compression\n    quality=85\n)\n\n# Save optimized\nwith open(\"optimized.webp\", \"wb\") as f:\n    f.write(optimized_bytes)\n```\n\n## Integration with Bria AI\n\nUse alongside the **[bria-ai skill](https:\u002F\u002Fclawhub.ai\u002Fgalbria\u002Fbria-ai)** to post-process AI-generated images. Generate or edit images with Bria's API, then use image-utils for resizing, cropping, watermarking, and web optimization.\n\n```python\nimport requests\nfrom image_utils import ImageUtils\n\n# Generate with Bria AI (see bria-ai skill for full API reference)\nresponse = requests.post(\n    \"https:\u002F\u002Fengine.prod.bria-api.com\u002Fv2\u002Fimage\u002Fgenerate\",\n    headers={\"api_token\": BRIA_API_KEY, \"Content-Type\": \"application\u002Fjson\"},\n    json={\"prompt\": \"product photo of headphones\", \"aspect_ratio\": \"1:1\", \"sync\": True}\n)\nimage_url = response.json()[\"result\"][\"image_url\"]\n\n# Download and post-process\nimage = ImageUtils.load_from_url(image_url)\n\n# Create multiple sizes for responsive images\nsizes = {\n    \"large\": ImageUtils.resize(image, width=1200),\n    \"medium\": ImageUtils.resize(image, width=600),\n    \"thumb\": ImageUtils.thumbnail(image, (150, 150))\n}\n\n# Save all as optimized WebP\nfor name, img in sizes.items():\n    ImageUtils.save(img, f\"product_{name}.webp\", quality=85)\n```\n\n## Batch Processing Example\n\n```python\nfrom pathlib import Path\nfrom image_utils import ImageUtils\n\ndef process_catalog(input_dir, output_dir):\n    \"\"\"Process all images in a directory.\"\"\"\n    output_path = Path(output_dir)\n    output_path.mkdir(exist_ok=True)\n\n    for image_file in Path(input_dir).glob(\"*.{jpg,png,webp}\"):\n        image = ImageUtils.load(image_file)\n\n        # Crop to square\n        square = ImageUtils.crop_to_aspect(image, \"1:1\")\n\n        # Resize to standard size\n        resized = ImageUtils.resize(square, width=800, height=800)\n\n        # Add watermark\n        final = ImageUtils.add_text_watermark(resized, \"© My Brand\")\n\n        # Save optimized\n        output_file = output_path \u002F f\"{image_file.stem}.webp\"\n        ImageUtils.save(final, output_file, quality=85)\n\nprocess_catalog(\".\u002Fraw_images\", \".\u002Fprocessed\")\n```\n\n## API Reference\n\nSee [image_utils.py](.\u002Freferences\u002Fcode-examples\u002Fimage_utils.py) for complete implementation with docstrings.\n","# Image Utilities\n\nPillow-based utilities for deterministic pixel-level image operations. Use for resize, crop, composite, format conversion, watermarks, and other standard image processing tasks.\n\n## When to Use This Skill\n\n- **Post-processing AI-generated images**: Resize, crop, optimize for web after generation\n- **Format conversion**: PNG ↔ JPEG ↔ WEBP with quality control\n- **Compositing**: Overlay images, paste subjects onto backgrounds\n- **Batch processing**: Resize to multiple sizes, add watermarks\n- **Web optimization**: Compress and resize for fast delivery\n- **Social media preparation**: Crop to platform-specific aspect ratios\n\n## When NOT to Use This Skill — Use `bria-ai` Instead\n\nThis skill handles **deterministic pixel-level operations** only. For any **generative or AI-powered** image work, use the `bria-ai` skill instead:\n\n- **Generating images from text prompts** → use `bria-ai`\n- **AI background removal or replacement** → use `bria-ai`\n- **AI image editing (inpainting, object removal\u002Faddition)** → use `bria-ai`\n- **Style transfer or AI-driven visual effects** → use `bria-ai`\n- **Creating product lifestyle shots with AI** → use `bria-ai`\n- **Image upscaling with AI super-resolution** → use `bria-ai`\n\n**Rule of thumb**: If the task requires *creating new visual content* or *understanding image semantics*, use `bria-ai`. If the task requires *transforming existing pixels* (resize, crop, format convert, watermark), use this skill.\n\nIf `bria-ai` is not available, install it with:\n```bash\nnpx skills add bria-ai\u002Fbria-skill\n```\n\n## Quick Reference\n\n| Operation | Method | Description |\n|-----------|--------|-------------|\n| **Loading** | `load(source)` | Load from URL, path, bytes, or base64 |\n| | `load_from_url(url)` | Download image from URL |\n| **Saving** | `save(image, path)` | Save with format auto-detection |\n| | `to_bytes(image, format)` | Convert to bytes |\n| | `to_base64(image, format)` | Convert to base64 string |\n| **Resizing** | `resize(image, width, height)` | Resize to exact dimensions |\n| | `scale(image, factor)` | Scale by factor (0.5 = half) |\n| | `thumbnail(image, size)` | Fit within size, maintain aspect |\n| **Cropping** | `crop(image, left, top, right, bottom)` | Crop to region |\n| | `crop_center(image, width, height)` | Crop from center |\n| | `crop_to_aspect(image, ratio)` | Crop to aspect ratio |\n| **Compositing** | `paste(bg, fg, position)` | Overlay at coordinates |\n| | `composite(bg, fg, mask)` | Alpha composite |\n| | `fit_to_canvas(image, w, h)` | Fit onto canvas size |\n| **Borders** | `add_border(image, width, color)` | Add solid border |\n| | `add_padding(image, padding)` | Add whitespace padding |\n| **Transforms** | `rotate(image, angle)` | Rotate by degrees |\n| | `flip_horizontal(image)` | Mirror horizontally |\n| | `flip_vertical(image)` | Flip vertically |\n| **Watermarks** | `add_text_watermark(image, text)` | Add text overlay |\n| | `add_image_watermark(image, logo)` | Add logo watermark |\n| **Adjustments** | `adjust_brightness(image, factor)` | Lighten\u002Fdarken |\n| | `adjust_contrast(image, factor)` | Adjust contrast |\n| | `adjust_saturation(image, factor)` | Adjust color saturation |\n| | `blur(image, radius)` | Apply Gaussian blur |\n| **Web** | `optimize_for_web(image, max_size)` | Optimize for delivery |\n| **Info** | `get_info(image)` | Get dimensions, format, mode |\n\n## Requirements\n\n```bash\npip install Pillow requests\n```\n\n## Basic Usage\n\n```python\nfrom image_utils import ImageUtils\n\n# Load from URL\nimage = ImageUtils.load_from_url(\"https:\u002F\u002Fexample.com\u002Fimage.jpg\")\n\n# Or load from various sources\nimage = ImageUtils.load(\"\u002Fpath\u002Fto\u002Fimage.png\")         # File path\nimage = ImageUtils.load(image_bytes)                  # Bytes\nimage = ImageUtils.load(\"data:image\u002Fpng;base64,...\")  # Base64\n\n# Resize and save\nresized = ImageUtils.resize(image, width=800, height=600)\nImageUtils.save(resized, \"output.webp\", quality=90)\n\n# Get image info\ninfo = ImageUtils.get_info(image)\nprint(f\"{info['width']}x{info['height']} {info['mode']}\")\n```\n\n## Resizing & Scaling\n\n```python\n# Resize to exact dimensions\nresized = ImageUtils.resize(image, width=800, height=600)\n\n# Resize maintaining aspect ratio (fit within bounds)\nfitted = ImageUtils.resize(image, width=800, height=600, maintain_aspect=True)\n\n# Resize by width only (height auto-calculated)\nresized = ImageUtils.resize(image, width=800)\n\n# Scale by factor\nhalf = ImageUtils.scale(image, 0.5)    # 50% size\ndouble = ImageUtils.scale(image, 2.0)  # 200% size\n\n# Create thumbnail\nthumb = ImageUtils.thumbnail(image, (150, 150))\n```\n\n## Cropping\n\n```python\n# Crop to specific region\ncropped = ImageUtils.crop(image, left=100, top=50, right=500, bottom=350)\n\n# Crop from center\ncenter = ImageUtils.crop_center(image, width=400, height=400)\n\n# Crop to aspect ratio (for social media)\nsquare = ImageUtils.crop_to_aspect(image, \"1:1\")      # Instagram\nwide = ImageUtils.crop_to_aspect(image, \"16:9\")       # YouTube thumbnail\nstory = ImageUtils.crop_to_aspect(image, \"9:16\")      # Stories\u002FReels\n\n# Control crop anchor\ntop_crop = ImageUtils.crop_to_aspect(image, \"16:9\", anchor=\"top\")\nbottom_crop = ImageUtils.crop_to_aspect(image, \"16:9\", anchor=\"bottom\")\n```\n\n## Compositing\n\n```python\n# Paste foreground onto background\nresult = ImageUtils.paste(background, foreground, position=(100, 50))\n\n# Alpha composite (foreground must have transparency)\nresult = ImageUtils.composite(background, foreground)\n\n# Fit image onto canvas with letterboxing\ncanvas = ImageUtils.fit_to_canvas(\n    image,\n    width=1200,\n    height=800,\n    background_color=(255, 255, 255, 255),  # White\n    position=\"center\"  # or \"top\", \"bottom\"\n)\n```\n\n## Format Conversion\n\n```python\n# Convert to different formats\npng_bytes = ImageUtils.to_bytes(image, \"PNG\")\njpeg_bytes = ImageUtils.to_bytes(image, \"JPEG\", quality=85)\nwebp_bytes = ImageUtils.to_bytes(image, \"WEBP\", quality=90)\n\n# Get base64 for data URLs\nbase64_str = ImageUtils.to_base64(image, \"PNG\")\ndata_url = ImageUtils.to_base64(image, \"PNG\", include_data_url=True)\n# Returns: \"data:image\u002Fpng;base64,...\"\n\n# Save with format auto-detected from extension\nImageUtils.save(image, \"output.png\")\nImageUtils.save(image, \"output.jpg\", quality=85)\nImageUtils.save(image, \"output.webp\", quality=90)\n```\n\n## Watermarks\n\n```python\n# Text watermark\nwatermarked = ImageUtils.add_text_watermark(\n    image,\n    text=\"© 2024 My Company\",\n    position=\"bottom-right\",  # bottom-left, top-right, top-left, center\n    font_size=24,\n    color=(255, 255, 255, 128),  # Semi-transparent white\n    margin=20\n)\n\n# Logo\u002Fimage watermark\nlogo = ImageUtils.load(\"logo.png\")\nwatermarked = ImageUtils.add_image_watermark(\n    image,\n    watermark=logo,\n    position=\"bottom-right\",\n    opacity=0.5,\n    scale=0.15,  # 15% of image width\n    margin=20\n)\n```\n\n## Adjustments\n\n```python\n# Brightness (1.0 = original, \u003C1 darker, >1 lighter)\nbright = ImageUtils.adjust_brightness(image, 1.3)\ndark = ImageUtils.adjust_brightness(image, 0.7)\n\n# Contrast (1.0 = original)\nhigh_contrast = ImageUtils.adjust_contrast(image, 1.5)\n\n# Saturation (0 = grayscale, 1.0 = original, >1 more vivid)\nvivid = ImageUtils.adjust_saturation(image, 1.3)\ngrayscale = ImageUtils.adjust_saturation(image, 0)\n\n# Sharpness\nsharp = ImageUtils.adjust_sharpness(image, 2.0)\n\n# Blur\nblurred = ImageUtils.blur(image, radius=5)\n```\n\n## Transforms\n\n```python\n# Rotate (counter-clockwise, degrees)\nrotated = ImageUtils.rotate(image, 45)\nrotated = ImageUtils.rotate(image, 90, expand=False)  # Don't expand canvas\n\n# Flip\nmirrored = ImageUtils.flip_horizontal(image)\nflipped = ImageUtils.flip_vertical(image)\n```\n\n## Borders & Padding\n\n```python\n# Add solid border\nbordered = ImageUtils.add_border(image, width=5, color=(0, 0, 0))\n\n# Add padding (whitespace)\npadded = ImageUtils.add_padding(image, padding=20)  # Uniform\npadded = ImageUtils.add_padding(image, padding=(10, 20, 10, 20))  # left, top, right, bottom\n```\n\n## Web Optimization\n\n```python\n# Optimize for web delivery\noptimized_bytes = ImageUtils.optimize_for_web(\n    image,\n    max_dimension=1920,  # Resize if larger\n    format=\"WEBP\",       # Best compression\n    quality=85\n)\n\n# Save optimized\nwith open(\"optimized.webp\", \"wb\") as f:\n    f.write(optimized_bytes)\n```\n\n## Integration with Bria AI\n\nUse alongside the **[bria-ai skill](https:\u002F\u002Fclawhub.ai\u002Fgalbria\u002Fbria-ai)** to post-process AI-generated images. Generate or edit images with Bria's API, then use image-utils for resizing, cropping, watermarking, and web optimization.\n\n```python\nimport requests\nfrom image_utils import ImageUtils\n\n# Generate with Bria AI (see bria-ai skill for full API reference)\nresponse = requests.post(\n    \"https:\u002F\u002Fengine.prod.bria-api.com\u002Fv2\u002Fimage\u002Fgenerate\",\n    headers={\"api_token\": BRIA_API_KEY, \"Content-Type\": \"application\u002Fjson\"},\n    json={\"prompt\": \"product photo of headphones\", \"aspect_ratio\": \"1:1\", \"sync\": True}\n)\nimage_url = response.json()[\"result\"][\"image_url\"]\n\n# Download and post-process\nimage = ImageUtils.load_from_url(image_url)\n\n# Create multiple sizes for responsive images\nsizes = {\n    \"large\": ImageUtils.resize(image, width=1200),\n    \"medium\": ImageUtils.resize(image, width=600),\n    \"thumb\": ImageUtils.thumbnail(image, (150, 150))\n}\n\n# Save all as optimized WebP\nfor name, img in sizes.items():\n    ImageUtils.save(img, f\"product_{name}.webp\", quality=85)\n```\n\n## Batch Processing Example\n\n```python\nfrom pathlib import Path\nfrom image_utils import ImageUtils\n\ndef process_catalog(input_dir, output_dir):\n    \"\"\"Process all images in a directory.\"\"\"\n    output_path = Path(output_dir)\n    output_path.mkdir(exist_ok=True)\n\n    for image_file in Path(input_dir).glob(\"*.{jpg,png,webp}\"):\n        image = ImageUtils.load(image_file)\n\n        # Crop to square\n        square = ImageUtils.crop_to_aspect(image, \"1:1\")\n\n        # Resize to standard size\n        resized = ImageUtils.resize(square, width=800, height=800)\n\n        # Add watermark\n        final = ImageUtils.add_text_watermark(resized, \"© My Brand\")\n\n        # Save optimized\n        output_file = output_path \u002F f\"{image_file.stem}.webp\"\n        ImageUtils.save(final, output_file, quality=85)\n\nprocess_catalog(\".\u002Fraw_images\", \".\u002Fprocessed\")\n```\n\n## API Reference\n\nSee [image_utils.py](.\u002Freferences\u002Fcode-examples\u002Fimage_utils.py) for complete implementation with docstrings.\n",{"name":5,"license":15,"metadata":49,"description":7},{"author":50,"version":51},"Bria AI","1.3.1","main","5c95bcac4646c5aed06bd9aed5235cfc7985aafc","included\u002Fskills\u002Fby-category\u002Fcreative-media-design\u002Flatest-release-creative\u002Fimage-utils",0,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked","https:\u002F\u002Fgithub.com\u002Fstrmt7","2026-11-11 04:18:12",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add strmt7\u002Fai_skills_collection_benchmarked --skill image-utils",{"tool":65,"command":66},"bunx","bunx skills add strmt7\u002Fai_skills_collection_benchmarked --skill image-utils",{"tool":68,"command":69},"pnpm","pnpm dlx skills add strmt7\u002Fai_skills_collection_benchmarked --skill image-utils","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcreative-media-design\u002Flatest-release-creative\u002Fimage-utils\u002FSKILL.md",true,[73],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fcode-examples\u002Fimage_utils.py","SCRIPT","脚本",27716,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fcreative-media-design\u002Flatest-release-creative\u002Fimage-utils\u002Freferences\u002Fcode-examples\u002Fimage_utils.py",[80,111,140,165,190,218],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":94,"publishedAt":44},"01M71D4H3T6M57DFKN8HENAWRV","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fwebapp-testing\u002FSKILL.md",[88,91],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[95,96,97,38,98,99,100,101,102,103,104,105,106,107,108,109,110],"webapp","testing","webapp testing","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":121,"publishedAt":44},"01M71D4CQR2A2TB7GASCR5ZBG3","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fskill-creator-anthropics\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fskill-creator-anthropics\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[122,123,124,125,126,127,31,128,129,130,131,132,133,134,135,136,137,138,38,139],"skill creator","creator","performance","improve","run evals","new","analysis","create","optimize","variance analysis","run","edit","benchmark","a skill","existing skill","evals","modify","accuracy",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":148,"publishedAt":44},"01M71D488XHEZVXXSXFYP8ENMH","playwright-skill","Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, validate web functionality, or perform browser-based testing.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Flatest-release-browser-automation\u002Fplaywright-skill\u002FSKILL.md",[146,147],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},[106,149,150,151,96,152,153,31,154,104,155,156,157,158,159,160,161,162,163,164],"playwright skill","browser automation","flows","auto","access","Bash","website","ux","login","scripts","read","write","node","install","network","responsive",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":169,"sourceHtmlUrl":170,"categories":171,"keywords":173,"publishedAt":44},"01M71CY25GM939M6RES91QSG3T","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Fweb-artifacts-builder\u002FSKILL.md",[172],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},[174,175,176,107,177,178,179,38,180,181,100,182,32,183,184,185,186,187,188,189],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","file","components","react","multi","state","routing","state management",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":194,"sourceHtmlUrl":195,"categories":196,"keywords":206,"publishedAt":44},"01M71CXZB60QJJ1H4S3NN94WMZ","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Ffrontend-design\u002FSKILL.md",[197,198,201],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":199,"categoryName":200,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":202,"categoryName":203,"taxonomyType":204,"taxonomyTypeDesc":205},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[100,207,208,179,209,210,211,98,212,213,32,31,176,214,184,215,185,216,217,105],"design","frontend design","ui design","generic","aesthetics","landing","pages","code","web ui","react components","examples",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":224,"publishedAt":44},"01M71CVZ54WFBTVA7R16PFY1ZE","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fzarr-python\u002FSKILL.md",[],[225,36,226,227,228,229,230,231,232,38,233,234,235,236,237,238,239,240],"zarr python","zarr","arrays","Cloud Storage","scientific","storage","parallel","dask","numpy","gcs","s3","integration","scientific computing","cloud","scale","pipelines"]