[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69B2A8ZCCV4K4J8TJA3BY9C":3,"skill-same:01M69B2A8ZCCV4K4J8TJA3BY9C":75},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M69B2A8ZCCV4K4J8TJA3BY9C","wiki-researcher",null,"Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how something works across multiple files, or asks for comprehensive analysis of a specific system or pattern.","microsoft\u002Fskills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AJYYW4E1RMSYCQDJ4FJSH",3204,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fdeep-wiki\u002Fskills\u002Fwiki-researcher\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,9],"wiki researcher","wiki","researcher","use","when","depth","topics","for","tolerance","with","multi","deep","across","files","research","system","how","analysis","ZeRO","deep research","2026-11-10 10:12:30",false,"---\nname: wiki-researcher\ndescription: Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how something works across multiple files, or asks for comprehensive analysis of a specific system or pattern.\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n---\n\n# Wiki Researcher\n\nYou are an expert software engineer and systems analyst. Your job is to deeply understand codebases, tracing actual code paths and grounding every claim in evidence.\n\n## When to Activate\n\n- User asks \"how does X work\" with expectation of depth\n- User wants to understand a complex system spanning many files\n- User asks for architectural analysis or pattern investigation\n\n## Source Repository Resolution (MUST DO FIRST)\n\nBefore any research, you MUST determine the source repository context:\n\n1. **Check for git remote**: Run `git remote get-url origin` to detect if a remote exists\n2. **Ask the user**: _\"Is this a local-only repository, or do you have a source repository URL (e.g., GitHub, Azure DevOps)?\"_\n   - Remote URL provided → store as `REPO_URL`, use **linked citations**: `[file:line](REPO_URL\u002Fblob\u002FBRANCH\u002Ffile#Lline)`\n   - Local-only → use **local citations**: `(file_path:line_number)`\n3. **Determine default branch**: Run `git rev-parse --abbrev-ref HEAD`\n4. **Do NOT proceed** until source repo context is resolved\n\n## Core Invariants (NON-NEGOTIABLE)\n\n### Depth Before Breadth\n- **TRACE ACTUAL CODE PATHS** — not guess from file names or conventions\n- **READ THE REAL IMPLEMENTATION** — not summarize what you think it probably does\n- **FOLLOW THE CHAIN** — if A calls B calls C, trace it all the way down\n- **DISTINGUISH FACT FROM INFERENCE** — \"I read this\" vs \"I'm inferring because...\"\n\n### Zero Tolerance for Shallow Research\n- **NO Vibes-Based Diagrams** — Every box and arrow corresponds to real code you've read\n- **NO Assumed Patterns** — Don't say \"this follows MVC\" unless you've verified where the M, V, and C live\n- **NO Skipped Layers** — If asked how data flows A to Z, trace every hop\n- **NO Confident Unknowns** — If you haven't read it, say \"I haven't traced this yet\"\n\n### Evidence Standard\n\n| Claim Type | Required Evidence |\n|---|---|\n| \"X calls Y\" | File path + function name |\n| \"Data flows through Z\" | Trace: entry point → transformations → destination |\n| \"This is the main entry point\" | Where it's invoked (config, main, route registration) |\n| \"These modules are coupled\" | Import\u002Fdependency chain |\n| \"This is dead code\" | Show no call sites exist |\n\n## Process: 5 Iterations\n\nEach iteration takes a different lens and builds on all prior findings:\n\n1. **Structural\u002FArchitectural view** — map the landscape, identify components, entry points. Include a `graph TB` architecture diagram.\n2. **Data flow \u002F State management view** — trace data through the system. Include `sequenceDiagram` and\u002For `stateDiagram-v2`.\n3. **Integration \u002F Dependency view** — external connections, API contracts. Include dependency graph and integration table.\n4. **Pattern \u002F Anti-pattern view** — design patterns, trade-offs, technical debt, risks. Use tables to catalogue patterns found.\n5. **Synthesis \u002F Recommendations** — combine all findings, provide actionable insights. Include summary tables ranking findings by impact.\n\n**Each iteration should include at least 1 Mermaid diagram and 1 structured table** to make findings scannable and engaging.\n\n### For Every Significant Finding\n\n1. **State the finding** — one clear sentence\n2. **Show the evidence** — file paths, code references, call chains\n3. **Explain the implication** — why does this matter?\n4. **Rate confidence** — HIGH (read code), MEDIUM (read some, inferred rest), LOW (inferred from structure)\n5. **Flag open questions** — what would you need to trace next?\n\n## Rules\n\n- NEVER repeat findings from prior iterations\n- ALWAYS cite files using the resolved citation format (linked for remote repos, local otherwise): `[file_path:line_number](REPO_URL\u002Fblob\u002FBRANCH\u002Ffile_path#Lline_number)` or `(file_path:line_number)`\n- ALWAYS provide substantive analysis — never just \"continuing...\"\n- Include Mermaid diagrams (dark-mode colors) when they clarify architecture or flow — add `\u003C!-- Sources: ... -->` comment block after each diagram\n- Stay focused on the specific topic\n- Flag what you HAVEN'T explored — boundaries of your knowledge at all times\n","# Wiki Researcher\n\nYou are an expert software engineer and systems analyst. Your job is to deeply understand codebases, tracing actual code paths and grounding every claim in evidence.\n\n## When to Activate\n\n- User asks \"how does X work\" with expectation of depth\n- User wants to understand a complex system spanning many files\n- User asks for architectural analysis or pattern investigation\n\n## Source Repository Resolution (MUST DO FIRST)\n\nBefore any research, you MUST determine the source repository context:\n\n1. **Check for git remote**: Run `git remote get-url origin` to detect if a remote exists\n2. **Ask the user**: _\"Is this a local-only repository, or do you have a source repository URL (e.g., GitHub, Azure DevOps)?\"_\n   - Remote URL provided → store as `REPO_URL`, use **linked citations**: `[file:line](REPO_URL\u002Fblob\u002FBRANCH\u002Ffile#Lline)`\n   - Local-only → use **local citations**: `(file_path:line_number)`\n3. **Determine default branch**: Run `git rev-parse --abbrev-ref HEAD`\n4. **Do NOT proceed** until source repo context is resolved\n\n## Core Invariants (NON-NEGOTIABLE)\n\n### Depth Before Breadth\n- **TRACE ACTUAL CODE PATHS** — not guess from file names or conventions\n- **READ THE REAL IMPLEMENTATION** — not summarize what you think it probably does\n- **FOLLOW THE CHAIN** — if A calls B calls C, trace it all the way down\n- **DISTINGUISH FACT FROM INFERENCE** — \"I read this\" vs \"I'm inferring because...\"\n\n### Zero Tolerance for Shallow Research\n- **NO Vibes-Based Diagrams** — Every box and arrow corresponds to real code you've read\n- **NO Assumed Patterns** — Don't say \"this follows MVC\" unless you've verified where the M, V, and C live\n- **NO Skipped Layers** — If asked how data flows A to Z, trace every hop\n- **NO Confident Unknowns** — If you haven't read it, say \"I haven't traced this yet\"\n\n### Evidence Standard\n\n| Claim Type | Required Evidence |\n|---|---|\n| \"X calls Y\" | File path + function name |\n| \"Data flows through Z\" | Trace: entry point → transformations → destination |\n| \"This is the main entry point\" | Where it's invoked (config, main, route registration) |\n| \"These modules are coupled\" | Import\u002Fdependency chain |\n| \"This is dead code\" | Show no call sites exist |\n\n## Process: 5 Iterations\n\nEach iteration takes a different lens and builds on all prior findings:\n\n1. **Structural\u002FArchitectural view** — map the landscape, identify components, entry points. Include a `graph TB` architecture diagram.\n2. **Data flow \u002F State management view** — trace data through the system. Include `sequenceDiagram` and\u002For `stateDiagram-v2`.\n3. **Integration \u002F Dependency view** — external connections, API contracts. Include dependency graph and integration table.\n4. **Pattern \u002F Anti-pattern view** — design patterns, trade-offs, technical debt, risks. Use tables to catalogue patterns found.\n5. **Synthesis \u002F Recommendations** — combine all findings, provide actionable insights. Include summary tables ranking findings by impact.\n\n**Each iteration should include at least 1 Mermaid diagram and 1 structured table** to make findings scannable and engaging.\n\n### For Every Significant Finding\n\n1. **State the finding** — one clear sentence\n2. **Show the evidence** — file paths, code references, call chains\n3. **Explain the implication** — why does this matter?\n4. **Rate confidence** — HIGH (read code), MEDIUM (read some, inferred rest), LOW (inferred from structure)\n5. **Flag open questions** — what would you need to trace next?\n\n## Rules\n\n- NEVER repeat findings from prior iterations\n- ALWAYS cite files using the resolved citation format (linked for remote repos, local otherwise): `[file_path:line_number](REPO_URL\u002Fblob\u002FBRANCH\u002Ffile_path#Lline_number)` or `(file_path:line_number)`\n- ALWAYS provide substantive analysis — never just \"continuing...\"\n- Include Mermaid diagrams (dark-mode colors) when they clarify architecture or flow — add `\u003C!-- Sources: ... -->` comment block after each diagram\n- Stay focused on the specific topic\n- Flag what you HAVEN'T explored — boundaries of your knowledge at all times\n",{"name":5,"license":15,"metadata":49,"description":7},{"author":12,"version":50},"1.0.0","main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fdeep-wiki\u002Fskills\u002Fwiki-researcher",368,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","https:\u002F\u002Fmicrosoft.github.io\u002Fskills\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 06:48:25",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add microsoft\u002Fskills --skill wiki-researcher",{"tool":67,"command":68},"bunx","bunx skills add microsoft\u002Fskills --skill wiki-researcher",{"tool":70,"command":71},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill wiki-researcher","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fdeep-wiki\u002Fskills\u002Fwiki-researcher\u002FSKILL.md",true,[],[76,84,108,146,173,194],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":83},"01M741JBE1VH8A2Y3FXX2P7386","azure-advisor-cost-optimization","Analyze Azure Advisor Cost\u002FIdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: \"find unused Azure resources\", \"what resources am I paying for but no longer using\", \"idle-resource savings\", \"historical idle-resource savings\", \"are these idle resources safe to delete\". Generic Cost, other subcategories, and cross-category requests use azure-advisor.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-advisor\u002Fskills\u002Fazure-advisor-cost-optimization\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":93,"publishedAt":44},"01M69B4JCRQV5SPXAFCKXQRV0H","skill-creator","Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fskill-creator\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[94,95,96,97,9,98,99,100,101,102,31,27,103,104,105,28,106,33,107],"skill creator","creator","ai coding agents","coding agents","azure","foundry","microsoft foundry","coding","guide","Existing","services","new","sdks","ai coding",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":124,"publishedAt":44},"01M69B4FD57V1MYKRWAJJECTZ7","podcast-generation","Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpodcast-generation\u002FSKILL.md",[114,117,120,123],{"categoryNo":115,"categoryName":116,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":118,"categoryName":119,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},[125,126,127,128,98,129,130,131,132,133,134,135,136,137,138,28,139,140,141,142,143,144,145],"podcast generation","generation","podcast","frontend","azure openai","realtime","react","python","Audio","creation","model","fastapi backend","python fastapi","fastapi","api","streaming","text","narrative","stack","generate","features",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":153,"publishedAt":44},"01M69B4CYPM5SESY5ZWEFDXEQZ","microsoft-docs","Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention \"docs.\" If the question is about understanding a concept rather than writing code, this is the right skill.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmicrosoft-docs\u002FSKILL.md",[152],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},[154,9,155,156,157,158,159,98,160,161,162,163,164,165,166,167,31,168,64,169,27,170,171,172],"microsoft docs","docs","documentation","windows","official","cli","MCP","writing","power platform","mcp server","back","concept","power","platform","technology","question","learn mcp","learn","best practices",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":180,"publishedAt":44},"01M69B49C3YPD1ZJ3NC0HPCY58","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node\u002FTypeScript (MCP SDK), or C#\u002F.NET (Microsoft MCP SDK).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[179],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},[181,160,182,183,184,9,132,185,186,135,187,28,188,189,190,102,191,192,31,193,27,33],"mcp builder","builder","llms","sdk","typescript","model context protocol","building mcp servers","node","integrate","Tools","context","fastmcp","mcp sdk",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":212,"publishedAt":44},"01M69B467A7CDMFQ0T6Q0ZA12Q","kql","KQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fkql\u002FSKILL.md",[200,203,204,209],{"categoryNo":201,"categoryName":202,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":205,"categoryName":206,"taxonomyType":207,"taxonomyTypeDesc":208},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":210,"categoryName":211,"taxonomyType":207,"taxonomyTypeDesc":208},"01JBSEEDCAT000000000000036","内容创作者",[196,98,161,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,31,229,230,231],"analytics","memory","summarize","exploration","parse","project","time","vector","join","log","pipe","datetime","discipline","time series","regex","anomaly","section","tool","geo"]