[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71GAYG2G2SJVFFFK91P5ZPV":3,"skill-same:01M71GAYG2G2SJVFFFK91P5ZPV":94},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M71GAYG2G2SJVFFFK91P5ZPV","pathml",null,"Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunofluorescence (CODEX, Vectra), spatial proteomics, nucleus detection\u002Fsegmentation, tissue graph construction, or training ML models on pathology data. Supports 160+ slide formats including Aperio SVS, NDPI, DICOM, OME-TIFF for digital pathology workflows.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"when","detection","analyzing","proteomics","models","codex","imaging","with","toolkit","ml","workflows","computational","use","pathology","training","for","slides","segmentation","images","2026-11-10 10:12:30",false,"---\nname: pathml\ndescription: Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunofluorescence (CODEX, Vectra), spatial proteomics, nucleus detection\u002Fsegmentation, tissue graph construction, or training ML models on pathology data. Supports 160+ slide formats including Aperio SVS, NDPI, DICOM, OME-TIFF for digital pathology workflows.\n---\n\n# PathML\n\n## Overview\n\nPathML is a comprehensive Python toolkit for computational pathology workflows, designed to facilitate machine learning and image analysis for whole-slide pathology images. The framework provides modular, composable tools for loading diverse slide formats, preprocessing images, constructing spatial graphs, training deep learning models, and analyzing multiparametric imaging data from technologies like CODEX and multiplex immunofluorescence.\n\n## When to Use This Skill\n\nApply this skill for:\n- Loading and processing whole-slide images (WSI) in various proprietary formats\n- Preprocessing H&E stained tissue images with stain normalization\n- Nucleus detection, segmentation, and classification workflows\n- Building cell and tissue graphs for spatial analysis\n- Training or deploying machine learning models (HoVer-Net, HACTNet) on pathology data\n- Analyzing multiparametric imaging (CODEX, Vectra, MERFISH) for spatial proteomics\n- Quantifying marker expression from multiplex immunofluorescence\n- Managing large-scale pathology datasets with HDF5 storage\n- Tile-based analysis and stitching operations\n\n## Core Capabilities\n\nPathML provides six major capability areas documented in detail within reference files:\n\n### 1. Image Loading & Formats\n\nLoad whole-slide images from 160+ proprietary formats including Aperio SVS, Hamamatsu NDPI, Leica SCN, Zeiss ZVI, DICOM, and OME-TIFF. PathML automatically handles vendor-specific formats and provides unified interfaces for accessing image pyramids, metadata, and regions of interest.\n\n**See:** `references\u002Fimage_loading.md` for supported formats, loading strategies, and working with different slide types.\n\n### 2. Preprocessing Pipelines\n\nBuild modular preprocessing pipelines by composing transforms for image manipulation, quality control, stain normalization, tissue detection, and mask operations. PathML's Pipeline architecture enables reproducible, scalable preprocessing across large datasets.\n\n**Key transforms:**\n- `StainNormalizationHE` - Macenko\u002FVahadane stain normalization\n- `TissueDetectionHE`, `NucleusDetectionHE` - Tissue\u002Fnucleus segmentation\n- `MedianBlur`, `GaussianBlur` - Noise reduction\n- `LabelArtifactTileHE` - Quality control for artifacts\n\n**See:** `references\u002Fpreprocessing.md` for complete transform catalog, pipeline construction, and preprocessing workflows.\n\n### 3. Graph Construction\n\nConstruct spatial graphs representing cellular and tissue-level relationships. Extract features from segmented objects to create graph-based representations suitable for graph neural networks and spatial analysis.\n\n**See:** `references\u002Fgraphs.md` for graph construction methods, feature extraction, and spatial analysis workflows.\n\n### 4. Machine Learning\n\nTrain and deploy deep learning models for nucleus detection, segmentation, and classification. PathML integrates PyTorch with pre-built models (HoVer-Net, HACTNet), custom DataLoaders, and ONNX support for inference.\n\n**Key models:**\n- **HoVer-Net** - Simultaneous nucleus segmentation and classification\n- **HACTNet** - Hierarchical cell-type classification\n\n**See:** `references\u002Fmachine_learning.md` for model training, evaluation, inference workflows, and working with public datasets.\n\n### 5. Multiparametric Imaging\n\nAnalyze spatial proteomics and gene expression data from CODEX, Vectra, MERFISH, and other multiplex imaging platforms. PathML provides specialized slide classes and transforms for processing multiparametric data, cell segmentation with Mesmer, and quantification workflows.\n\n**See:** `references\u002Fmultiparametric.md` for CODEX\u002FVectra workflows, cell segmentation, marker quantification, and integration with AnnData.\n\n### 6. Data Management\n\nEfficiently store and manage large pathology datasets using HDF5 format. PathML handles tiles, masks, metadata, and extracted features in unified storage structures optimized for machine learning workflows.\n\n**See:** `references\u002Fdata_management.md` for HDF5 integration, tile management, dataset organization, and batch processing strategies.\n\n## Quick Start\n\n### Installation\n\n```bash\n# Install PathML\nuv pip install pathml\n\n# With optional dependencies for all features\nuv pip install pathml[all]\n```\n\n### Basic Workflow Example\n\n```python\nfrom pathml.core import SlideData\nfrom pathml.preprocessing import Pipeline, StainNormalizationHE, TissueDetectionHE\n\n# Load a whole-slide image\nwsi = SlideData.from_slide(\"path\u002Fto\u002Fslide.svs\")\n\n# Create preprocessing pipeline\npipeline = Pipeline([\n    TissueDetectionHE(),\n    StainNormalizationHE(target='normalize', stain_estimation_method='macenko')\n])\n\n# Run pipeline\npipeline.run(wsi)\n\n# Access processed tiles\nfor tile in wsi.tiles:\n    processed_image = tile.image\n    tissue_mask = tile.masks['tissue']\n```\n\n### Common Workflows\n\n**H&E Image Analysis:**\n1. Load WSI with appropriate slide class\n2. Apply tissue detection and stain normalization\n3. Perform nucleus detection or train segmentation models\n4. Extract features and build spatial graphs\n5. Conduct downstream analysis\n\n**Multiparametric Imaging (CODEX):**\n1. Load CODEX slide with `CODEXSlide`\n2. Collapse multi-run channel data\n3. Segment cells using Mesmer model\n4. Quantify marker expression\n5. Export to AnnData for single-cell analysis\n\n**Training ML Models:**\n1. Prepare dataset with public pathology data\n2. Create PyTorch DataLoader with PathML datasets\n3. Train HoVer-Net or custom models\n4. Evaluate on held-out test sets\n5. Deploy with ONNX for inference\n\n## References to Detailed Documentation\n\nWhen working on specific tasks, refer to the appropriate reference file for comprehensive information:\n\n- **Loading images:** `references\u002Fimage_loading.md`\n- **Preprocessing workflows:** `references\u002Fpreprocessing.md`\n- **Spatial analysis:** `references\u002Fgraphs.md`\n- **Model training:** `references\u002Fmachine_learning.md`\n- **CODEX\u002Fmultiplex IF:** `references\u002Fmultiparametric.md`\n- **Data storage:** `references\u002Fdata_management.md`\n\n## Resources\n\nThis skill includes comprehensive reference documentation organized by capability area. Each reference file contains detailed API information, workflow examples, best practices, and troubleshooting guidance for specific PathML functionality.\n\n### references\u002F\n\nDocumentation files providing in-depth coverage of PathML capabilities:\n\n- `image_loading.md` - Whole-slide image formats, loading strategies, slide classes\n- `preprocessing.md` - Complete transform catalog, pipeline construction, preprocessing workflows\n- `graphs.md` - Graph construction methods, feature extraction, spatial analysis\n- `machine_learning.md` - Model architectures, training workflows, evaluation, inference\n- `multiparametric.md` - CODEX, Vectra, multiplex IF analysis, cell segmentation, quantification\n- `data_management.md` - HDF5 storage, tile management, batch processing, dataset organization\n\nLoad these references as needed when working on specific computational pathology tasks.\n","# PathML\n\n## Overview\n\nPathML is a comprehensive Python toolkit for computational pathology workflows, designed to facilitate machine learning and image analysis for whole-slide pathology images. The framework provides modular, composable tools for loading diverse slide formats, preprocessing images, constructing spatial graphs, training deep learning models, and analyzing multiparametric imaging data from technologies like CODEX and multiplex immunofluorescence.\n\n## When to Use This Skill\n\nApply this skill for:\n- Loading and processing whole-slide images (WSI) in various proprietary formats\n- Preprocessing H&E stained tissue images with stain normalization\n- Nucleus detection, segmentation, and classification workflows\n- Building cell and tissue graphs for spatial analysis\n- Training or deploying machine learning models (HoVer-Net, HACTNet) on pathology data\n- Analyzing multiparametric imaging (CODEX, Vectra, MERFISH) for spatial proteomics\n- Quantifying marker expression from multiplex immunofluorescence\n- Managing large-scale pathology datasets with HDF5 storage\n- Tile-based analysis and stitching operations\n\n## Core Capabilities\n\nPathML provides six major capability areas documented in detail within reference files:\n\n### 1. Image Loading & Formats\n\nLoad whole-slide images from 160+ proprietary formats including Aperio SVS, Hamamatsu NDPI, Leica SCN, Zeiss ZVI, DICOM, and OME-TIFF. PathML automatically handles vendor-specific formats and provides unified interfaces for accessing image pyramids, metadata, and regions of interest.\n\n**See:** `references\u002Fimage_loading.md` for supported formats, loading strategies, and working with different slide types.\n\n### 2. Preprocessing Pipelines\n\nBuild modular preprocessing pipelines by composing transforms for image manipulation, quality control, stain normalization, tissue detection, and mask operations. PathML's Pipeline architecture enables reproducible, scalable preprocessing across large datasets.\n\n**Key transforms:**\n- `StainNormalizationHE` - Macenko\u002FVahadane stain normalization\n- `TissueDetectionHE`, `NucleusDetectionHE` - Tissue\u002Fnucleus segmentation\n- `MedianBlur`, `GaussianBlur` - Noise reduction\n- `LabelArtifactTileHE` - Quality control for artifacts\n\n**See:** `references\u002Fpreprocessing.md` for complete transform catalog, pipeline construction, and preprocessing workflows.\n\n### 3. Graph Construction\n\nConstruct spatial graphs representing cellular and tissue-level relationships. Extract features from segmented objects to create graph-based representations suitable for graph neural networks and spatial analysis.\n\n**See:** `references\u002Fgraphs.md` for graph construction methods, feature extraction, and spatial analysis workflows.\n\n### 4. Machine Learning\n\nTrain and deploy deep learning models for nucleus detection, segmentation, and classification. PathML integrates PyTorch with pre-built models (HoVer-Net, HACTNet), custom DataLoaders, and ONNX support for inference.\n\n**Key models:**\n- **HoVer-Net** - Simultaneous nucleus segmentation and classification\n- **HACTNet** - Hierarchical cell-type classification\n\n**See:** `references\u002Fmachine_learning.md` for model training, evaluation, inference workflows, and working with public datasets.\n\n### 5. Multiparametric Imaging\n\nAnalyze spatial proteomics and gene expression data from CODEX, Vectra, MERFISH, and other multiplex imaging platforms. PathML provides specialized slide classes and transforms for processing multiparametric data, cell segmentation with Mesmer, and quantification workflows.\n\n**See:** `references\u002Fmultiparametric.md` for CODEX\u002FVectra workflows, cell segmentation, marker quantification, and integration with AnnData.\n\n### 6. Data Management\n\nEfficiently store and manage large pathology datasets using HDF5 format. PathML handles tiles, masks, metadata, and extracted features in unified storage structures optimized for machine learning workflows.\n\n**See:** `references\u002Fdata_management.md` for HDF5 integration, tile management, dataset organization, and batch processing strategies.\n\n## Quick Start\n\n### Installation\n\n```bash\n# Install PathML\nuv pip install pathml\n\n# With optional dependencies for all features\nuv pip install pathml[all]\n```\n\n### Basic Workflow Example\n\n```python\nfrom pathml.core import SlideData\nfrom pathml.preprocessing import Pipeline, StainNormalizationHE, TissueDetectionHE\n\n# Load a whole-slide image\nwsi = SlideData.from_slide(\"path\u002Fto\u002Fslide.svs\")\n\n# Create preprocessing pipeline\npipeline = Pipeline([\n    TissueDetectionHE(),\n    StainNormalizationHE(target='normalize', stain_estimation_method='macenko')\n])\n\n# Run pipeline\npipeline.run(wsi)\n\n# Access processed tiles\nfor tile in wsi.tiles:\n    processed_image = tile.image\n    tissue_mask = tile.masks['tissue']\n```\n\n### Common Workflows\n\n**H&E Image Analysis:**\n1. Load WSI with appropriate slide class\n2. Apply tissue detection and stain normalization\n3. Perform nucleus detection or train segmentation models\n4. Extract features and build spatial graphs\n5. Conduct downstream analysis\n\n**Multiparametric Imaging (CODEX):**\n1. Load CODEX slide with `CODEXSlide`\n2. Collapse multi-run channel data\n3. Segment cells using Mesmer model\n4. Quantify marker expression\n5. Export to AnnData for single-cell analysis\n\n**Training ML Models:**\n1. Prepare dataset with public pathology data\n2. Create PyTorch DataLoader with PathML datasets\n3. Train HoVer-Net or custom models\n4. Evaluate on held-out test sets\n5. Deploy with ONNX for inference\n\n## References to Detailed Documentation\n\nWhen working on specific tasks, refer to the appropriate reference file for comprehensive information:\n\n- **Loading images:** `references\u002Fimage_loading.md`\n- **Preprocessing workflows:** `references\u002Fpreprocessing.md`\n- **Spatial analysis:** `references\u002Fgraphs.md`\n- **Model training:** `references\u002Fmachine_learning.md`\n- **CODEX\u002Fmultiplex IF:** `references\u002Fmultiparametric.md`\n- **Data storage:** `references\u002Fdata_management.md`\n\n## Resources\n\nThis skill includes comprehensive reference documentation organized by capability area. Each reference file contains detailed API information, workflow examples, best practices, and troubleshooting guidance for specific PathML functionality.\n\n### references\u002F\n\nDocumentation files providing in-depth coverage of PathML capabilities:\n\n- `image_loading.md` - Whole-slide image formats, loading strategies, slide classes\n- `preprocessing.md` - Complete transform catalog, pipeline construction, preprocessing workflows\n- `graphs.md` - Graph construction methods, feature extraction, spatial analysis\n- `machine_learning.md` - Model architectures, training workflows, evaluation, inference\n- `multiparametric.md` - CODEX, Vectra, multiplex IF analysis, cell segmentation, quantification\n- `data_management.md` - HDF5 storage, tile management, batch processing, dataset organization\n\nLoad these references as needed when working on specific computational pathology tasks.\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add JSGforever\u002Fskillguard --skill pathml",{"tool":60,"command":61},"bunx","bunx skills add JSGforever\u002Fskillguard --skill pathml",{"tool":63,"command":64},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill pathml","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml\u002FSKILL.md",true,[68,74,78,82,86,90],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fdata_management.md","REFERENCE","参考文档",19018,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml\u002Freferences\u002Fdata_management.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fgraphs.md",16726,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml\u002Freferences\u002Fgraphs.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fimage_loading.md",12146,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml\u002Freferences\u002Fimage_loading.md",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fmachine_learning.md",19946,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml\u002Freferences\u002Fmachine_learning.md",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fmultiparametric.md",18199,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml\u002Freferences\u002Fmultiparametric.md",{"path":91,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fpreprocessing.md",18209,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fpathml\u002Freferences\u002Fpreprocessing.md",[95,121,137,164,186,207],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":102,"publishedAt":42},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[101],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[103,104,105,28,106,107,108,109,110,111,112,113,23,114,115,116,117,118,119,120],"scanner","skillguard codex scanner","skillguard","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":125,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":133,"publishedAt":42},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[128],{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[134,135,136],"data","data exfiltrator","files",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":42},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":173,"publishedAt":42},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[170],{"categoryNo":171,"categoryName":172,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[153,174,161,162,175,176,177,178,179,180,144,181,182,157,159,183,160,163,184,185],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":193,"publishedAt":42},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[192],{"categoryNo":171,"categoryName":172,"taxonomyType":20,"taxonomyTypeDesc":21},[194,163,195,196,197,198,153,144,199,200,201,159,160,161,202,162,203,204,205,206],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":220,"publishedAt":42},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[213,216,219],{"categoryNo":214,"categoryName":215,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":217,"categoryName":218,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[221,222,223,224,225,226,227,151,179,228,229,33,160,185,230,206,231,232,233,234],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","run","release","write","edit","git"]