[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76XKR4GJMJSZ4EBWBJNZ3KM":3,"skill-same:01M76XKR4GJMJSZ4EBWBJNZ3KM":48},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M76XKR4GJMJSZ4EBWBJNZ3KM","scikit-image",null,"A collection of algorithms for image processing in Python. Built on NumPy, SciPy, and Cython. It focuses on scientific image analysis including segmentation, geometric transformations, color space manipulation, analysis, and filtering.","stanfish06\u002Fskillquarium","stanfish06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93099613?v=4","01M75F1CK4ZW109ZK3T26VN52F","Zhiyuan","01M75F1CM53VH6F79DZ8GXKKES",12,"BSD-3-Clause","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fscikit-image\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: scikit-image\ndescription: A collection of algorithms for image processing in Python. Built on NumPy, SciPy, and Cython. It focuses on scientific image analysis including segmentation, geometric transformations, color space manipulation, analysis, and filtering.\nauthor: tondevrel\nversion: 0.22\nlicense: BSD-3-Clause\n---\n\n# scikit-image - Scientific Image Processing\n\nscikit-image treats images as NumPy arrays. It provides a comprehensive suite of algorithms for filtering, feature detection, and object measurement, making it the standard for research-grade image analysis.\n\n## When to Use\n\n- Preprocessing scientific images (noise reduction, contrast enhancement).\n- Image segmentation (separating cells, particles, or regions of interest).\n- Feature extraction (detecting edges, corners, blobs, or textures).\n- Geometric transformations (rescaling, rotating, warping).\n- Morphological operations (thinning, skeletonization, hole filling).\n- Measuring object properties (area, perimeter, eccentricity).\n- Restoring degraded images (deconvolution, inpainting).\n\n## Reference Documentation\n\n**Official docs**: https:\u002F\u002Fscikit-image.org\u002F  \n**User Guide**: https:\u002F\u002Fscikit-image.org\u002Fdocs\u002Fstable\u002Fuser_guide.html  \n**Search patterns**: `skimage.filters`, `skimage.segmentation`, `skimage.feature`, `skimage.morphology`\n\n## Core Principles\n\n### Images are NumPy Arrays\nA grayscale image is a 2D array (M, N). A color image is a 3D array (M, N, 3). A multichannel 3D volume is (P, M, N, C).\n\n### Coordinate System\nThe origin (0, 0) is at the top-left corner. Coordinates are always represented as (row, column).\n\n### Data Types and Ranges\nscikit-image handles various dtypes with specific ranges:\n- `uint8`: 0 to 255\n- `uint16`: 0 to 65535\n- `float`: -1 to 1 or 0 to 1\n\n## Quick Reference\n\n### Installation\n\n```bash\npip install scikit-image\n```\n\n### Standard Imports\n\n```python\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom skimage import io, filters, segmentation, feature, measure, morphology, color, util\n```\n\n### Basic Pattern - Load and Filter\n\n```python\nfrom skimage import io, filters, color\n\n# Load image\nimage = io.imread('data.png')\n\n# Convert to grayscale if needed\ngray_image = color.rgb2gray(image)\n\n# Apply a filter (e.g., Gaussian blur)\nblurred = filters.gaussian(gray_image, sigma=2.0)\n\n# Display\nio.imshow(blurred)\nio.show()\n```\n\n## Critical Rules\n\n### ✅ DO\n\n- **Use utility functions for conversion** - Use `util.img_as_float`, `util.img_as_ubyte` to handle rescaling automatically when changing dtypes.\n- **Grayscale for analysis** - Most feature extraction and segmentation algorithms expect 2D grayscale arrays.\n- **Check image shape** - Always verify `image.shape` and `image.dtype` before processing.\n- **Vectorize** - Use NumPy operations instead of loops over pixels.\n- **Apply filters before segmentation** - Denoising (Gaussian, Median) significantly improves segmentation results.\n- **Use label for object counting** - `measure.label` is the standard way to identify connected components.\n\n### ❌ DON'T\n\n- **Manually rescale dtypes** - Avoid `image \u002F 255.0`; use `util.img_as_float`.\n- **Ignore the \"Coordinate Warning\"** - Be careful with (x, y) vs (row, col). scikit-image uses (row, col).\n- **Modify the input image** - Most functions return a new array; work with copies if you need to mutate.\n- **Apply color-sensitive filters to grayscale** - Some filters behave differently on 3D vs 2D arrays.\n\n## Anti-Patterns (NEVER)\n\n```python\n# ❌ BAD: Manual dtype conversion (doesn't handle scaling)\nimage_float = image.astype(float) # Values stay 0-255 but as floats\n\n# ✅ GOOD: Safe utility conversion\nfrom skimage import util\nimage_float = util.img_as_float(image) # Values scaled to 0.0-1.0\n\n# ❌ BAD: Looping over pixels\nfor r in range(rows):\n    for c in range(cols):\n        if image[r, c] > 128:\n            image[r, c] = 255\n\n# ✅ GOOD: Vectorized thresholding\nimage[image > 0.5] = 1.0\n\n# ❌ BAD: Plotting multiple images without a shared axis\nplt.imshow(img1); plt.show()\nplt.imshow(img2); plt.show()\n\n# ✅ GOOD: Using subplots for comparison\nfig, ax = plt.subplots(1, 2)\nax[0].imshow(img1, cmap='gray')\nax[1].imshow(img2, cmap='gray')\n```\n\n## Filtering and Restoration (skimage.filters)\n\n### Denoising and Edge Detection\n\n```python\nfrom skimage import filters\n\n# Edge detection\nedges_sobel = filters.sobel(image)\nedges_canny = feature.canny(image, sigma=3)\n\n# Denoising\ndenoised = filters.median(image, morphology.disk(3))\n\n# Thresholding (Automatic)\nval = filters.threshold_otsu(image)\nbinary = image > val\n```\n\n## Morphology (skimage.morphology)\n\n### Shaping and Structural Analysis\n\n```python\nfrom skimage import morphology\n\n# Binary morphology\nstruct_element = morphology.disk(5)\neroded = morphology.erosion(binary, struct_element)\ndilated = morphology.dilation(binary, struct_element)\nopened = morphology.opening(binary, struct_element) # Erosion then Dilation\n\n# Skeletonization (Reducing objects to 1-pixel width)\nskeleton = morphology.skeletonize(binary)\n\n# Removing small objects\nclean_binary = morphology.remove_small_objects(binary, min_size=64)\n```\n\n## Segmentation (skimage.segmentation)\n\n### Separating Objects\n\n```python\nfrom skimage import segmentation, color\n\n# Watershed Segmentation (Marker-based)\nfrom scipy import ndimage as ndi\ndistance = ndi.distance_transform_edt(binary)\ncoords = feature.peak_local_max(distance, footprint=np.ones((3, 3)), labels=binary)\nmask = np.zeros(distance.shape, dtype=bool)\nmask[tuple(coords.T)] = True\nmarkers, _ = ndi.label(mask)\nlabels = segmentation.watershed(-distance, markers, mask=binary)\n\n# SLIC (Superpixels)\nsegments = segmentation.slic(image, n_segments=100, compactness=10)\nout = color.label2rgb(segments, image, kind='avg')\n```\n\n## Feature Detection (skimage.feature)\n\n### Keypoints and Textures\n\n```python\nfrom skimage import feature\n\n# Local Binary Patterns (Texture analysis)\nlbp = feature.local_binary_pattern(image, P=8, R=1)\n\n# Corner detection (Harris)\ncoords = feature.corner_peaks(feature.corner_harris(image), min_distance=5)\n\n# Blob detection (Difference of Gaussian)\nblobs = feature.blob_dog(image, max_sigma=30, threshold=.1)\n# blobs: array of [row, col, sigma]\n```\n\n## Measurements (skimage.measure)\n\n### Quantifying Results\n\n```python\nfrom skimage import measure\n\n# Label connected components\nlabels = measure.label(binary)\n\n# Calculate properties\nprops = measure.regionprops(labels)\n\nfor prop in props:\n    print(f\"Label: {prop.label}\")\n    print(f\"Area: {prop.area}\")\n    print(f\"Centroid: {prop.centroid}\")\n    print(f\"Eccentricity: {prop.eccentricity}\")\n\n# Find contours\ncontours = measure.find_contours(binary, 0.8)\n```\n\n## Practical Workflows\n\n### 1. Particle Counting Pipeline\n\n```python\ndef count_particles(image_path):\n    # 1. Load and grayscale\n    img = color.rgb2gray(io.imread(image_path))\n    \n    # 2. Denoise\n    img_denoised = filters.gaussian(img, sigma=1)\n    \n    # 3. Threshold\n    thresh = filters.threshold_otsu(img_denoised)\n    binary = img_denoised \u003C thresh # Assuming dark particles\n    \n    # 4. Morphological cleaning\n    binary = morphology.remove_small_objects(binary, 50)\n    binary = morphology.closing(binary, morphology.disk(3))\n    \n    # 5. Label and measure\n    labels = measure.label(binary)\n    return measure.regionprops(labels), labels\n\n# properties, label_img = count_particles('samples.tif')\n```\n\n### 2. Micrograph Analysis (Nuclei Segmentation)\n\n```python\ndef segment_nuclei(dna_image):\n    \"\"\"Identify nuclei in a DAPI\u002FHoechst stained image.\"\"\"\n    # Local thresholding for uneven illumination\n    local_thresh = filters.threshold_local(dna_image, block_size=35)\n    binary = dna_image > local_thresh\n    \n    # Fill holes\n    filled = ndi.binary_fill_holes(binary)\n    \n    # Separate touching nuclei\n    distance = ndi.distance_transform_edt(filled)\n    coords = feature.peak_local_max(distance, footprint=np.ones((15, 15)), labels=filled)\n    local_maxi = np.zeros_like(distance, dtype=bool)\n    local_maxi[tuple(coords.T)] = True\n    markers = measure.label(local_maxi)\n    labels = segmentation.watershed(-distance, markers, mask=filled)\n    \n    return labels\n```\n\n### 3. Change Detection (Image Subtraction)\n\n```python\ndef detect_change(img_before, img_after, threshold=0.1):\n    # Ensure float\n    im1 = util.img_as_float(color.rgb2gray(img_before))\n    im2 = util.img_as_float(color.rgb2gray(img_after))\n    \n    # Difference\n    diff = np.abs(im1 - im2)\n    \n    # Filter noise in difference\n    diff_clean = filters.median(diff, morphology.disk(2))\n    \n    return diff_clean > threshold\n```\n\n## Performance Optimization\n\n### Using skimage.util.view_as_windows\n\n```python\nfrom skimage.util import view_as_windows\n\n# Create overlapping patches without copying data (using strides)\n# Fast for local neighborhood calculations\npatches = view_as_windows(image, (64, 64), step=32)\n# Shape: (n_patches_r, n_patches_c, 64, 64)\n```\n\n### Parallel Processing\n\n```python\n# Many skimage functions are already Cython-optimized.\n# For batch processing, use standard joblib or multiprocessing.\nfrom joblib import Parallel, delayed\n\nresults = Parallel(n_jobs=-1)(delayed(filters.gaussian)(img) for img in image_list)\n```\n\n## Common Pitfalls and Solutions\n\n### Handling Multichannel Images\n\n```python\n# ❌ Problem: Filters failing on RGB images\n# result = filters.median(rgb_image) # Raises error\n\n# ✅ Solution: Filter per channel or convert\n# filters.median(color.rgb2gray(rgb_image))\n# OR apply to each channel\n# result = np.stack([filters.median(rgb_image[..., i]) for i in range(3)], axis=-1)\n```\n\n### Memory issues with label\n\n```python\n# ❌ Problem: Large noisy images produce millions of 1-pixel labels\n# ✅ Solution: Clear small noise before labeling\nbinary = morphology.remove_small_objects(binary, min_size=10)\nlabels = measure.label(binary)\n```\n\n### Coordinates: (X, Y) vs (Row, Col) confusion\n\n```python\n# ❌ Problem: Points appear swapped on plot\n# Matplotlib: plt.plot(x, y)\n# scikit-image: image[row, col]\n\n# ✅ Solution: Explicitly swap for visualization\ncoords = feature.peak_local_max(img) # Returns [row, col]\nplt.plot(coords[:, 1], coords[:, 0], 'r.') # Plot as [x, y]\n```\n\nscikit-image provides the mathematical rigor needed for scientific discovery. By building on the NumPy ecosystem, it allows for a seamless workflow from raw sensor data to quantifiable insights.\n","# scikit-image - Scientific Image Processing\n\nscikit-image treats images as NumPy arrays. It provides a comprehensive suite of algorithms for filtering, feature detection, and object measurement, making it the standard for research-grade image analysis.\n\n## When to Use\n\n- Preprocessing scientific images (noise reduction, contrast enhancement).\n- Image segmentation (separating cells, particles, or regions of interest).\n- Feature extraction (detecting edges, corners, blobs, or textures).\n- Geometric transformations (rescaling, rotating, warping).\n- Morphological operations (thinning, skeletonization, hole filling).\n- Measuring object properties (area, perimeter, eccentricity).\n- Restoring degraded images (deconvolution, inpainting).\n\n## Reference Documentation\n\n**Official docs**: https:\u002F\u002Fscikit-image.org\u002F  \n**User Guide**: https:\u002F\u002Fscikit-image.org\u002Fdocs\u002Fstable\u002Fuser_guide.html  \n**Search patterns**: `skimage.filters`, `skimage.segmentation`, `skimage.feature`, `skimage.morphology`\n\n## Core Principles\n\n### Images are NumPy Arrays\nA grayscale image is a 2D array (M, N). A color image is a 3D array (M, N, 3). A multichannel 3D volume is (P, M, N, C).\n\n### Coordinate System\nThe origin (0, 0) is at the top-left corner. Coordinates are always represented as (row, column).\n\n### Data Types and Ranges\nscikit-image handles various dtypes with specific ranges:\n- `uint8`: 0 to 255\n- `uint16`: 0 to 65535\n- `float`: -1 to 1 or 0 to 1\n\n## Quick Reference\n\n### Installation\n\n```bash\npip install scikit-image\n```\n\n### Standard Imports\n\n```python\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom skimage import io, filters, segmentation, feature, measure, morphology, color, util\n```\n\n### Basic Pattern - Load and Filter\n\n```python\nfrom skimage import io, filters, color\n\n# Load image\nimage = io.imread('data.png')\n\n# Convert to grayscale if needed\ngray_image = color.rgb2gray(image)\n\n# Apply a filter (e.g., Gaussian blur)\nblurred = filters.gaussian(gray_image, sigma=2.0)\n\n# Display\nio.imshow(blurred)\nio.show()\n```\n\n## Critical Rules\n\n### ✅ DO\n\n- **Use utility functions for conversion** - Use `util.img_as_float`, `util.img_as_ubyte` to handle rescaling automatically when changing dtypes.\n- **Grayscale for analysis** - Most feature extraction and segmentation algorithms expect 2D grayscale arrays.\n- **Check image shape** - Always verify `image.shape` and `image.dtype` before processing.\n- **Vectorize** - Use NumPy operations instead of loops over pixels.\n- **Apply filters before segmentation** - Denoising (Gaussian, Median) significantly improves segmentation results.\n- **Use label for object counting** - `measure.label` is the standard way to identify connected components.\n\n### ❌ DON'T\n\n- **Manually rescale dtypes** - Avoid `image \u002F 255.0`; use `util.img_as_float`.\n- **Ignore the \"Coordinate Warning\"** - Be careful with (x, y) vs (row, col). scikit-image uses (row, col).\n- **Modify the input image** - Most functions return a new array; work with copies if you need to mutate.\n- **Apply color-sensitive filters to grayscale** - Some filters behave differently on 3D vs 2D arrays.\n\n## Anti-Patterns (NEVER)\n\n```python\n# ❌ BAD: Manual dtype conversion (doesn't handle scaling)\nimage_float = image.astype(float) # Values stay 0-255 but as floats\n\n# ✅ GOOD: Safe utility conversion\nfrom skimage import util\nimage_float = util.img_as_float(image) # Values scaled to 0.0-1.0\n\n# ❌ BAD: Looping over pixels\nfor r in range(rows):\n    for c in range(cols):\n        if image[r, c] > 128:\n            image[r, c] = 255\n\n# ✅ GOOD: Vectorized thresholding\nimage[image > 0.5] = 1.0\n\n# ❌ BAD: Plotting multiple images without a shared axis\nplt.imshow(img1); plt.show()\nplt.imshow(img2); plt.show()\n\n# ✅ GOOD: Using subplots for comparison\nfig, ax = plt.subplots(1, 2)\nax[0].imshow(img1, cmap='gray')\nax[1].imshow(img2, cmap='gray')\n```\n\n## Filtering and Restoration (skimage.filters)\n\n### Denoising and Edge Detection\n\n```python\nfrom skimage import filters\n\n# Edge detection\nedges_sobel = filters.sobel(image)\nedges_canny = feature.canny(image, sigma=3)\n\n# Denoising\ndenoised = filters.median(image, morphology.disk(3))\n\n# Thresholding (Automatic)\nval = filters.threshold_otsu(image)\nbinary = image > val\n```\n\n## Morphology (skimage.morphology)\n\n### Shaping and Structural Analysis\n\n```python\nfrom skimage import morphology\n\n# Binary morphology\nstruct_element = morphology.disk(5)\neroded = morphology.erosion(binary, struct_element)\ndilated = morphology.dilation(binary, struct_element)\nopened = morphology.opening(binary, struct_element) # Erosion then Dilation\n\n# Skeletonization (Reducing objects to 1-pixel width)\nskeleton = morphology.skeletonize(binary)\n\n# Removing small objects\nclean_binary = morphology.remove_small_objects(binary, min_size=64)\n```\n\n## Segmentation (skimage.segmentation)\n\n### Separating Objects\n\n```python\nfrom skimage import segmentation, color\n\n# Watershed Segmentation (Marker-based)\nfrom scipy import ndimage as ndi\ndistance = ndi.distance_transform_edt(binary)\ncoords = feature.peak_local_max(distance, footprint=np.ones((3, 3)), labels=binary)\nmask = np.zeros(distance.shape, dtype=bool)\nmask[tuple(coords.T)] = True\nmarkers, _ = ndi.label(mask)\nlabels = segmentation.watershed(-distance, markers, mask=binary)\n\n# SLIC (Superpixels)\nsegments = segmentation.slic(image, n_segments=100, compactness=10)\nout = color.label2rgb(segments, image, kind='avg')\n```\n\n## Feature Detection (skimage.feature)\n\n### Keypoints and Textures\n\n```python\nfrom skimage import feature\n\n# Local Binary Patterns (Texture analysis)\nlbp = feature.local_binary_pattern(image, P=8, R=1)\n\n# Corner detection (Harris)\ncoords = feature.corner_peaks(feature.corner_harris(image), min_distance=5)\n\n# Blob detection (Difference of Gaussian)\nblobs = feature.blob_dog(image, max_sigma=30, threshold=.1)\n# blobs: array of [row, col, sigma]\n```\n\n## Measurements (skimage.measure)\n\n### Quantifying Results\n\n```python\nfrom skimage import measure\n\n# Label connected components\nlabels = measure.label(binary)\n\n# Calculate properties\nprops = measure.regionprops(labels)\n\nfor prop in props:\n    print(f\"Label: {prop.label}\")\n    print(f\"Area: {prop.area}\")\n    print(f\"Centroid: {prop.centroid}\")\n    print(f\"Eccentricity: {prop.eccentricity}\")\n\n# Find contours\ncontours = measure.find_contours(binary, 0.8)\n```\n\n## Practical Workflows\n\n### 1. Particle Counting Pipeline\n\n```python\ndef count_particles(image_path):\n    # 1. Load and grayscale\n    img = color.rgb2gray(io.imread(image_path))\n    \n    # 2. Denoise\n    img_denoised = filters.gaussian(img, sigma=1)\n    \n    # 3. Threshold\n    thresh = filters.threshold_otsu(img_denoised)\n    binary = img_denoised \u003C thresh # Assuming dark particles\n    \n    # 4. Morphological cleaning\n    binary = morphology.remove_small_objects(binary, 50)\n    binary = morphology.closing(binary, morphology.disk(3))\n    \n    # 5. Label and measure\n    labels = measure.label(binary)\n    return measure.regionprops(labels), labels\n\n# properties, label_img = count_particles('samples.tif')\n```\n\n### 2. Micrograph Analysis (Nuclei Segmentation)\n\n```python\ndef segment_nuclei(dna_image):\n    \"\"\"Identify nuclei in a DAPI\u002FHoechst stained image.\"\"\"\n    # Local thresholding for uneven illumination\n    local_thresh = filters.threshold_local(dna_image, block_size=35)\n    binary = dna_image > local_thresh\n    \n    # Fill holes\n    filled = ndi.binary_fill_holes(binary)\n    \n    # Separate touching nuclei\n    distance = ndi.distance_transform_edt(filled)\n    coords = feature.peak_local_max(distance, footprint=np.ones((15, 15)), labels=filled)\n    local_maxi = np.zeros_like(distance, dtype=bool)\n    local_maxi[tuple(coords.T)] = True\n    markers = measure.label(local_maxi)\n    labels = segmentation.watershed(-distance, markers, mask=filled)\n    \n    return labels\n```\n\n### 3. Change Detection (Image Subtraction)\n\n```python\ndef detect_change(img_before, img_after, threshold=0.1):\n    # Ensure float\n    im1 = util.img_as_float(color.rgb2gray(img_before))\n    im2 = util.img_as_float(color.rgb2gray(img_after))\n    \n    # Difference\n    diff = np.abs(im1 - im2)\n    \n    # Filter noise in difference\n    diff_clean = filters.median(diff, morphology.disk(2))\n    \n    return diff_clean > threshold\n```\n\n## Performance Optimization\n\n### Using skimage.util.view_as_windows\n\n```python\nfrom skimage.util import view_as_windows\n\n# Create overlapping patches without copying data (using strides)\n# Fast for local neighborhood calculations\npatches = view_as_windows(image, (64, 64), step=32)\n# Shape: (n_patches_r, n_patches_c, 64, 64)\n```\n\n### Parallel Processing\n\n```python\n# Many skimage functions are already Cython-optimized.\n# For batch processing, use standard joblib or multiprocessing.\nfrom joblib import Parallel, delayed\n\nresults = Parallel(n_jobs=-1)(delayed(filters.gaussian)(img) for img in image_list)\n```\n\n## Common Pitfalls and Solutions\n\n### Handling Multichannel Images\n\n```python\n# ❌ Problem: Filters failing on RGB images\n# result = filters.median(rgb_image) # Raises error\n\n# ✅ Solution: Filter per channel or convert\n# filters.median(color.rgb2gray(rgb_image))\n# OR apply to each channel\n# result = np.stack([filters.median(rgb_image[..., i]) for i in range(3)], axis=-1)\n```\n\n### Memory issues with label\n\n```python\n# ❌ Problem: Large noisy images produce millions of 1-pixel labels\n# ✅ Solution: Clear small noise before labeling\nbinary = morphology.remove_small_objects(binary, min_size=10)\nlabels = measure.label(binary)\n```\n\n### Coordinates: (X, Y) vs (Row, Col) confusion\n\n```python\n# ❌ Problem: Points appear swapped on plot\n# Matplotlib: plt.plot(x, y)\n# scikit-image: image[row, col]\n\n# ✅ Solution: Explicitly swap for visualization\ncoords = feature.peak_local_max(img) # Returns [row, col]\nplt.plot(coords[:, 1], coords[:, 0], 'r.') # Plot as [x, y]\n```\n\nscikit-image provides the mathematical rigor needed for scientific discovery. By building on the NumPy ecosystem, it allows for a seamless workflow from raw sensor data to quantifiable insights.\n",{"name":5,"author":24,"license":15,"version":25,"description":7},"tondevrel",0.22,"master","49e49abf2f670d429e0b7e2c0349739c3fdd5cbe","skills\u002Fscikit-image",5,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium","https:\u002F\u002Fgithub.com\u002Fstanfish06","https:\u002F\u002Fwww.stanfish.dev\u002F","2026-11-14 21:31:37",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add stanfish06\u002Fskillquarium --skill scikit-image",{"tool":40,"command":41},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill scikit-image",{"tool":43,"command":44},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill scikit-image","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fscikit-image\u002FSKILL.md",true,[],[49,57,66,73,80,87],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M76ZJTRVA456GD7K8Y3EP82H","zarr-python","Stores and queries chunked N-D scientific arrays with Zarr-Python 3, including codecs, sharding, S3\u002FGCS storage, and NumPy\u002FDask\u002FXarray integration. Use for array layout, bounded I\u002FO, format migration, or scientific metadata preservation.","MIT","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":62,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M76ZJQZ15Q1HKC5V85NHE325","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M76ZJ8ASZ4QYQ70Y6SBA4Z4S","xarray","N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF\u002FGRIB\u002FZarr files, climate\u002Fweather\u002Foceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fxarray\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M76ZHFBXD6VXPQ02VCEG202B","writing-mstest-tests","Use when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for \"review\" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected\u002Factual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext\u002Flifecycle; timeout\u002Fcancellation; OS\u002FCI conditions, retry, cleanup, parallelization, MSTest.Sdk project setup, and MSTESTxxxx. Honor the installed MSTest version. DO NOT USE to design new test cases (code-testing), perform report-only audits, create project files rather than explain MSTest setup, run tests, migrate frameworks, or handle non-MSTest\u002Fnon-.NET code.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-mstest-tests\u002FSKILL.md",[],[],{"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":53,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M76ZDFDF4N88RH6HSYGS7GP2","wgs-prs","End-to-end WGS to polygenic risk score pipeline. Takes paired-end FASTQ files (or a pre-existing VCF) through nf-core\u002Fsarek for variant calling, applies VCF QC (normalisation, hard filtering, Ti\u002FTv and Het\u002FHom checks), then computes polygenic risk scores via the PGS Catalog. Fills the FASTQ to VCF gap upstream of the gwas-prs skill.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwgs-prs\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M76ZCC1SC68J42QK4MDC8RCG","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.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[]]