[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skills:sce6":3,"skills:stats":50,"skills:pro6":55,"skills:creators9":100,"skills:all:stars:186:":195},[4,15,22,29,36,43],{"categoryNo":5,"taxonomyType":6,"taxonomyTypeDesc":7,"categoryName":8,"categoryNameEn":9,"description":10,"level":11,"skillCount":12,"parentNo":13,"parentName":13,"children":14},"01JBSEEDCAT000000000000022","SCENARIO","使用场景","智能体与自动化","Agents & Automation","Skill、MCP、智能体与工作流自动化",1,39458,null,[],{"categoryNo":16,"taxonomyType":6,"taxonomyTypeDesc":7,"categoryName":17,"categoryNameEn":18,"description":19,"level":11,"skillCount":20,"parentNo":13,"parentName":13,"children":21},"01JBSEEDCAT000000000000006","软件开发","Software Development","编码、测试、部署等软件研发任务",26531,[],{"categoryNo":23,"taxonomyType":6,"taxonomyTypeDesc":7,"categoryName":24,"categoryNameEn":25,"description":26,"level":11,"skillCount":27,"parentNo":13,"parentName":13,"children":28},"01JBSEEDCAT000000000000014","设计创意","Design & Creative","视觉设计、品牌与多媒体创作",13569,[],{"categoryNo":30,"taxonomyType":6,"taxonomyTypeDesc":7,"categoryName":31,"categoryNameEn":32,"description":33,"level":11,"skillCount":34,"parentNo":13,"parentName":13,"children":35},"01JBSEEDCAT000000000000001","办公效率","Office Productivity","日常办公文档、表格、演示与沟通类任务",6289,[],{"categoryNo":37,"taxonomyType":6,"taxonomyTypeDesc":7,"categoryName":38,"categoryNameEn":39,"description":40,"level":11,"skillCount":41,"parentNo":13,"parentName":13,"children":42},"01JBSEEDCAT000000000000017","内容创作","Content Creation","写作、文案与营销内容生产",6029,[],{"categoryNo":44,"taxonomyType":6,"taxonomyTypeDesc":7,"categoryName":45,"categoryNameEn":46,"description":47,"level":11,"skillCount":48,"parentNo":13,"parentName":13,"children":49},"01JBSEEDCAT000000000000020","研究与学习","Research & Learning","资料检索、知识整理与学习辅导",5531,[],{"skillCount":51,"professionCount":52,"scenarioCount":53,"creatorCount":54},196852,11,7,1926,[56,65,72,79,86,93],{"categoryNo":57,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":60,"categoryNameEn":61,"description":62,"level":11,"skillCount":63,"parentNo":13,"parentName":13,"children":64},"01JBSEEDCAT000000000000030","PROFESSION","适用职业","开发工程师","Software Engineer","从事软件编码、测试与运维的工程师",13274,[],{"categoryNo":66,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":67,"categoryNameEn":68,"description":69,"level":11,"skillCount":70,"parentNo":13,"parentName":13,"children":71},"01JBSEEDCAT000000000000032","设计师","Designer","视觉、交互与品牌设计人员",7775,[],{"categoryNo":73,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":74,"categoryNameEn":75,"description":76,"level":11,"skillCount":77,"parentNo":13,"parentName":13,"children":78},"01JBSEEDCAT000000000000033","数据分析师","Data Analyst","数据分析、报表与商业智能人员",4988,[],{"categoryNo":80,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":81,"categoryNameEn":82,"description":83,"level":11,"skillCount":84,"parentNo":13,"parentName":13,"children":85},"01JBSEEDCAT000000000000036","内容创作者","Content Creator","作者、编辑与自媒体创作者",3940,[],{"categoryNo":87,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":88,"categoryNameEn":89,"description":90,"level":11,"skillCount":91,"parentNo":13,"parentName":13,"children":92},"01JBSEEDCAT000000000000035","市场营销","Marketer","市场推广、增长与品牌运营人员",3446,[],{"categoryNo":94,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":95,"categoryNameEn":96,"description":97,"level":11,"skillCount":98,"parentNo":13,"parentName":13,"children":99},"01JBSEEDCAT000000000000037","律师与法务","Legal","合同、合规与法律事务人员",3316,[],{"records":101,"total":54,"current":11,"size":194},[102,114,123,133,143,153,163,172,182],{"accountNo":103,"login":104,"displayName":105,"avatarUrl":106,"accountType":107,"accountTypeDesc":108,"profileDescription":109,"skillCount":110,"repoCount":111,"professionCount":52,"scenarioCount":53,"totalStars":112,"updatedAt":113},"01M698VYDXZ6JW5WH3CRV650R8","microsoft","Microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","ORGANIZATION","组织","Open source projects and samples from Microsoft",4160,229,828772,"2026-11-13 04:10:52",{"accountNo":115,"login":116,"displayName":116,"avatarUrl":117,"accountType":107,"accountTypeDesc":108,"profileDescription":118,"skillCount":119,"repoCount":120,"professionCount":53,"scenarioCount":53,"totalStars":121,"updatedAt":122},"01M698P3FSAZ6B4R928ZF19KPT","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","Your personal, open source AI assistant.",362,32,437711,"2026-11-13 03:02:05",{"accountNo":124,"login":125,"displayName":126,"avatarUrl":127,"accountType":107,"accountTypeDesc":108,"profileDescription":13,"skillCount":128,"repoCount":129,"professionCount":53,"scenarioCount":130,"totalStars":131,"updatedAt":132},"01M6AC29YGCR4S2NTJFV0G8B81","openai","OpenAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14957082?v=4",171,23,6,342695,"2026-11-13 04:03:41",{"accountNo":134,"login":135,"displayName":136,"avatarUrl":137,"accountType":107,"accountTypeDesc":108,"profileDescription":13,"skillCount":138,"repoCount":139,"professionCount":140,"scenarioCount":53,"totalStars":141,"updatedAt":142},"01M6AC83E6K4FDKK7HZ8WNMQKE","apache","The Apache Software Foundation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F47359?v=4",420,75,8,298176,"2026-11-13 03:14:28",{"accountNo":144,"login":145,"displayName":146,"avatarUrl":147,"accountType":107,"accountTypeDesc":108,"profileDescription":148,"skillCount":149,"repoCount":150,"professionCount":52,"scenarioCount":53,"totalStars":151,"updatedAt":152},"01M698VYEFDM0VJBZDYYJ2T83S","google","Google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","Google ❤️ Open Source",535,48,242366,"2026-11-13 04:17:09",{"accountNo":154,"login":155,"displayName":156,"avatarUrl":157,"accountType":107,"accountTypeDesc":108,"profileDescription":158,"skillCount":159,"repoCount":160,"professionCount":52,"scenarioCount":53,"totalStars":161,"updatedAt":162},"01M6AC83DS133TPXFSP1DHNCC6","github","GitHub","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","How people build software.",940,28,238441,"2026-11-13 03:57:35",{"accountNo":164,"login":165,"displayName":166,"avatarUrl":167,"accountType":107,"accountTypeDesc":108,"profileDescription":13,"skillCount":168,"repoCount":169,"professionCount":52,"scenarioCount":53,"totalStars":170,"updatedAt":171},"01M697XGDPXJAVQ8391V2BCYTE","anthropics","Anthropic","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4",674,17,231826,"2026-11-13 04:18:26",{"accountNo":173,"login":174,"displayName":175,"avatarUrl":176,"accountType":107,"accountTypeDesc":108,"profileDescription":13,"skillCount":177,"repoCount":178,"professionCount":179,"scenarioCount":53,"totalStars":180,"updatedAt":181},"01M6AC83EPDGBFN19MWYRREJD0","Significant-Gravitas","AutoGPT","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130738209?v=4",86,2,10,188014,"2026-11-13 02:38:59",{"accountNo":183,"login":184,"displayName":185,"avatarUrl":186,"accountType":187,"accountTypeDesc":188,"profileDescription":189,"skillCount":190,"repoCount":191,"professionCount":130,"scenarioCount":53,"totalStars":192,"updatedAt":193},"01M6DJCCDDG53MTYYRTXAXFG17","garrytan","Garry Tan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F19957?v=4","USER","个人作者","Writes software, dreams. ",324,3,174614,"2026-11-13 04:05:07",9,{"records":196,"total":51,"current":612,"size":613},[197,231,259,286,310,326,347,362,384,422,449,472,492,504,531,551,571,595],{"skillNo":198,"name":199,"nameZh":13,"description":200,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":209,"categories":210,"keywords":214,"publishedAt":230},"01M6ADZ38FXB69CZ6YHPRSCGXE","research-engineer","An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33418,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fresearch-engineer\u002FSKILL.md",[211],{"categoryNo":212,"categoryName":213,"taxonomyType":6,"taxonomyTypeDesc":7},"01JBSEEDCAT000000000000021","资料检索与研究",[215,216,217,218,219,220,221,222,223,224,225,226,227,228,229],"research","research engineer","engineer","verification","ZeRO","formal verification","implementation","technology","Academic","across","scientific","with","correctness","objective","academic research","2026-11-10 10:12:30",{"skillNo":232,"name":233,"nameZh":13,"description":234,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":235,"categories":236,"keywords":237,"publishedAt":230},"01M6ADZ0P4HD0H8YH2GD8PA1EG","rag-sentence-transformers","Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-sentence-transformers\u002FSKILL.md",[],[238,239,240,241,242,215,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258],"rag","Transformers","rag sentence transformers","sentence transformers","image","semantic search","tasks","state","framework","search","embeddings","multimodal","clustering","text","Art","multilingual","domain","domain-specific","embedding","orchestra","for",{"skillNo":260,"name":261,"nameZh":13,"description":262,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":263,"categories":264,"keywords":265,"publishedAt":230},"01M6ADYXG9X5KQHMKQ99WD0Y97","rag-qdrant","High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-qdrant\u002FSKILL.md",[],[238,266,267,268,215,269,270,243,247,271,248,272,273,274,275,276,277,278,279,280,281,282,257,258,283,284,285],"rag qdrant","performance","rust","storage","distributed","vector","fast","Vector Search","Qdrant","Similarity Search","HNSW","Production","filtering","use","high-performance","Hybrid Search","Scalable","hybrid","when","search engine",{"skillNo":287,"name":288,"nameZh":13,"description":289,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":290,"categories":291,"keywords":295,"publishedAt":230},"01M6ADYTJMZGMZV84SNC63FEHQ","rag-pinecone","Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (\u003C100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-pinecone\u002FSKILL.md",[292],{"categoryNo":293,"categoryName":294,"taxonomyType":6,"taxonomyTypeDesc":7},"01JBSEEDCAT000000000000010","后端与接口",[238,296,297,215,243,298,299,247,271,300,301,302,303,304,305,306,281,307,308,257,283,309],"rag pinecone","pinecone","infrastructure","database","metadata","vector database","auto","scaling","latency","recommendations","Managed Service","Auto-Scaling","at","managed",{"skillNo":311,"name":312,"nameZh":13,"description":313,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":314,"categories":315,"keywords":316,"publishedAt":230},"01M6ADYRPQDVH455TZSXAGWYHP","rag-implementation","Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-implementation\u002FSKILL.md",[],[238,317,221,243,135,247,271,248,318,273,319,279,320,321,322,323,324,325,284],"rag implementation","Optimization","vector stores","patterns","chunking","generation","semantic","retrieval","spawner",{"skillNo":327,"name":328,"nameZh":13,"description":329,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":330,"categories":331,"keywords":332,"publishedAt":230},"01M6ADYP2045Z4354V81XNG9XP","rag-faiss","Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-faiss\u002FSKILL.md",[],[238,333,334,267,215,335,336,247,271,337,300,338,272,250,280,339,340,341,342,343,344,345,346,257,284],"rag faiss","faiss","gpu","index","high performance","library","CPU","Facebook AI","GPU Acceleration","Billion-Scale","K-NN","Large Scale","types","you",{"skillNo":348,"name":349,"nameZh":13,"description":350,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":351,"categories":352,"keywords":353,"publishedAt":230},"01M6ADYKZ625JBQ9X2H1JXCMY1","rag-engineer","Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-engineer\u002FSKILL.md",[],[238,354,217,243,135,247,271,248,318,355,279,356,357,358,359,321,256,360,361,258,325,284],"rag engineer","applications","databases","expert","document","strategies","Document Retrieval","LLM Applications",{"skillNo":363,"name":364,"nameZh":13,"description":365,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":366,"categories":367,"keywords":372,"publishedAt":230},"01M6ADYGR5EWZKC0V6BAJWQ83V","rag-chroma","Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Frag-chroma\u002FSKILL.md",[368,371],{"categoryNo":369,"categoryName":370,"taxonomyType":6,"taxonomyTypeDesc":7},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":293,"categoryName":294,"taxonomyType":6,"taxonomyTypeDesc":7},[238,373,374,215,243,375,299,247,271,248,300,376,239,377,378,379,251,301,380,381,382,256,383],"rag chroma","chroma","development","open source","api","open","projects","self","local","filter","source",{"skillNo":385,"name":386,"nameZh":13,"description":387,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":388,"categories":389,"keywords":400,"publishedAt":230},"01M6ADYDFH21JJET6198PF8AYE","qa-test-planner","Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fqa-test-planner\u002FSKILL.md",[390,393,396,399],{"categoryNo":391,"categoryName":392,"taxonomyType":6,"taxonomyTypeDesc":7},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":394,"categoryName":395,"taxonomyType":6,"taxonomyTypeDesc":7},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":66,"categoryName":67,"taxonomyType":58,"taxonomyTypeDesc":59},[401,402,403,404,405,406,407,408,409,410,411,412,413,414,415,416,417,418,258,419,420,421],"test","qa","qa test planner","qa test","planner","test planner","design","MCP","generate","validation","figma","integration","regression","regression test","bug","reports","plans","manual","test cases","manual test","figma mcp",{"skillNo":423,"name":424,"nameZh":13,"description":425,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":426,"categories":427,"keywords":429,"publishedAt":230},"01M6ADYAGXRBBCT3TANNAV2WYB","pydantic-ai","Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fpydantic-ai\u002FSKILL.md",[428],{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},[430,431,432,433,434,435,436,125,437,438,439,440,441,442,443,444,424,445,446,447,448],"Pydantic","pydantic ai","safe","gemini","python","ai agents","support","tool use","injection","tool","model","dependency","ready","multi-model","community","structured-output","dependency injection","production-ready","2026",{"skillNo":450,"name":451,"nameZh":13,"description":452,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":453,"categories":454,"keywords":457,"publishedAt":230},"01M6ADY7RFV8CYPA3XEWE6FN9B","prompt-library","Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fprompt-library\u002FSKILL.md",[455,456],{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},{"categoryNo":57,"categoryName":60,"taxonomyType":58,"taxonomyTypeDesc":59},[458,338,459,460,461,244,462,463,464,465,466,467,279,442,468,469,470,471,258,284],"prompt library","prompt","writing","prompt templates","play","examples","collection","analysis","coding","quality","task","Role-Based","high","techniques",{"skillNo":473,"name":474,"nameZh":13,"description":475,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":476,"categories":477,"keywords":479,"publishedAt":230},"01M6ADY5G9Y75QZ4EZP7YS7CF5","prompt-engineering","Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fprompt-engineering\u002FSKILL.md",[478],{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},[480,481,459,482,483,484,485,486,318,487,488,489,490,279,357,320,359,491,471,284],"prompt engineering","engineering","debug agent","debug","engineering patterns","learn","best practices","prompt engineering patterns","improve","behavior","guide","prompting",{"skillNo":493,"name":494,"nameZh":13,"description":495,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":496,"categories":497,"keywords":499,"publishedAt":230},"01M6ADY2GN8KA4A9BZG6Y7RBY3","prompt-engineering-patterns","Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fprompt-engineering-patterns\u002FSKILL.md",[498],{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},[480,484,481,487,459,320,267,500,501,444,502,471,503,448],"reliability","master","advanced","unknown",{"skillNo":505,"name":506,"nameZh":13,"description":507,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":508,"categories":509,"keywords":511,"publishedAt":230},"01M6ADXYY9G48J4Q0R5DWVXF4G","prompt-engineering-outlines","Guarantee valid JSON\u002FXML\u002Fcode structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fprompt-engineering-outlines\u002FSKILL.md",[510],{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},[480,481,512,459,432,513,514,215,436,515,516,517,338,518,519,520,430,521,522,239,523,524,525,279,526,527,381,528,258,529,530],"prompt engineering outlines","inference","valid","json schema","code","xml","Structured Generation","vLLM","Outlines","Local Models","Grammar-Based Generation","Type Safety","Safety","json","models","structure","type","code structure","outputs",{"skillNo":532,"name":533,"nameZh":13,"description":534,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":535,"categories":536,"keywords":539,"publishedAt":230},"01M6ADXW0K0KMVCS3VHCTTDGMB","prompt-engineering-instructor","Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fprompt-engineering-instructor\u002FSKILL.md",[537,538],{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},{"categoryNo":73,"categoryName":74,"taxonomyType":58,"taxonomyTypeDesc":59},[480,481,540,459,541,542,215,410,125,543,544,338,545,430,524,525,546,528,547,548,549,550],"prompt engineering instructor","instructor","structured data","streaming","extraction","data","results","structured output","retry","stream","parse",{"skillNo":552,"name":553,"nameZh":13,"description":554,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":555,"categories":556,"keywords":559,"publishedAt":230},"01M6ADXRBP775CB9KCVANHMKFX","prompt-engineering-guidance","Control LLM output with regex and grammars, guarantee valid JSON\u002FXML\u002Fcode generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fprompt-engineering-guidance\u002FSKILL.md",[557,558],{"categoryNo":212,"categoryName":213,"taxonomyType":6,"taxonomyTypeDesc":7},{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},[480,481,560,459,561,514,215,104,562,516,410,246,517,563,239,564,565,566,567,547,568,569,570,257],"prompt engineering guidance","guidance","workflows","Code Generation","grammar","enforcement","enforce","regex","Constrained Generation","JSON Validation","formats",{"skillNo":572,"name":573,"nameZh":13,"description":574,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":575,"categories":576,"keywords":579,"publishedAt":230},"01M6ADXMZXX0ZV1DJCA7YKPEMW","prompt-engineering-dspy","Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fprompt-engineering-dspy\u002FSKILL.md",[577,578],{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},{"categoryNo":57,"categoryName":60,"taxonomyType":58,"taxonomyTypeDesc":59},[480,481,580,459,581,582,215,583,238,584,125,246,318,585,586,587,588,589,590,591,592,593,594],"prompt engineering dspy","dspy","nlp","modular","create","optimize","systematic","Declarative Programming","Prompt Optimization","LM Programming","Stanford NLP","Automatic Optimization","Modular AI","automatic","declarative",{"skillNo":596,"name":597,"nameZh":13,"description":598,"descriptionZh":13,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":13,"sourceHtmlUrl":599,"categories":600,"keywords":602,"publishedAt":230},"01M6ADXJY7CJZNZ7EGGNSADEX4","prompt-engineer","Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fprompt-engineer\u002FSKILL.md",[601],{"categoryNo":397,"categoryName":398,"taxonomyType":6,"taxonomyTypeDesc":7},[603,459,217,407,480,135,481,604,355,605,279,357,527,606,607,608,609,610,258,325,611,284],"prompt engineer","Evaluation","system","context management","chain","prompt design","output","system prompt","output formatting",186,18]