[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFHNDB3HZ04QN53JR1SFVG":3,"skill-same:01M6AFHNDB3HZ04QN53JR1SFVG":99},{"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":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6AFHNDB3HZ04QN53JR1SFVG","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.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"when","codex","pathology","for","formats","with","imaging","computational","images","use","slides","segmentation","detection","data","analyzing","graph","toolkit","training","ml","workflows","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","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add davila7\u002Fclaude-code-templates --skill pathml",{"tool":65,"command":66},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill pathml",{"tool":68,"command":69},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill pathml","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml\u002FSKILL.md",true,[73,79,83,87,91,95],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fdata_management.md","REFERENCE","参考文档",19018,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml\u002Freferences\u002Fdata_management.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fgraphs.md",16726,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml\u002Freferences\u002Fgraphs.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fimage_loading.md",12146,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml\u002Freferences\u002Fimage_loading.md",{"path":88,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fmachine_learning.md",19946,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml\u002Freferences\u002Fmachine_learning.md",{"path":92,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fmultiparametric.md",18199,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml\u002Freferences\u002Fmultiparametric.md",{"path":96,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fpreprocessing.md",18209,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpathml\u002Freferences\u002Fpreprocessing.md",[100,124,151,184,219,242],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":107,"publishedAt":44},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[106],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[108,109,110,111,112,27,113,114,33,24,115,29,116,117,118,119,120,121,122,123],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","reduce","record","track","verdict","evm","solana","how","public","look",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":44},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[130],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[132,133,134,135,136,137,138,139,140,141,142,24,143,144,145,146,147,148,149,150],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":166,"publishedAt":44},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[157,160,161],{"categoryNo":158,"categoryName":159,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":162,"categoryName":163,"taxonomyType":164,"taxonomyTypeDesc":165},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[167,168,169,170,171,172,173,27,174,175,176,177,178,179,180,33,181,182,24,183],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":188,"licenseFileUrl":189,"sourceHtmlUrl":190,"categories":191,"keywords":195,"publishedAt":44},"01M6AFY6F7CC2BBZP1QD6VTNVC","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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[192],{"categoryNo":193,"categoryName":194,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,27,218],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":188,"licenseFileUrl":223,"sourceHtmlUrl":224,"categories":225,"keywords":230,"publishedAt":44},"01M6AFWF33SFV9Z3SF4PEEE4BF","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\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[226,229],{"categoryNo":227,"categoryName":228,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":193,"categoryName":194,"taxonomyType":21,"taxonomyTypeDesc":22},[231,232,233,234,235,197,236,206,207,237,40,238,239,27,240,29,241],"webapp testing","testing","webapp","browser","playwright","applications","debugging","logs","screenshots","local","behavior",{"skillNo":243,"name":244,"nameZh":6,"description":245,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":188,"licenseFileUrl":246,"sourceHtmlUrl":247,"categories":248,"keywords":256,"publishedAt":44},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[249,252,253],{"categoryNo":250,"categoryName":251,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":254,"categoryName":255,"taxonomyType":164,"taxonomyTypeDesc":165},"01JBSEEDCAT000000000000036","内容创作者",[257,258,259,260,261,262,37,263,199,264,209,143,265,266,267,268,269,179,270,24,271,272,273,274,275,121,276],"discernment nudge","nudge","interpretation","help","run","reasoning","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]