[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69B3PY8ZZB6GTYZB765WAYA":3,"skill-same:01M69B3PY8ZZB6GTYZB765WAYA":71},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M69B3PY8ZZB6GTYZB765WAYA","continual-learning",null,"Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for agents.","microsoft\u002Fskills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AJYYW4E1RMSYCQDJ4FJSH",3202,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcontinual-learning\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"continual learning","learning","use","when","for","implementing","patterns","reflection","ai coding","hooks","up","coding agents","guide","scoping","coding","infrastructure","ai coding agents","memory","2026-11-10 10:12:30",false,"---\nname: continual-learning\ndescription: Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for agents.\n---\n\n# Continual Learning for AI Coding Agents\n\nYour agent forgets everything between sessions. Continual learning fixes that.\n\n## The Loop\n\n```\nExperience → Capture → Reflect → Persist → Apply\n     ↑                                       │\n     └───────────────────────────────────────┘\n```\n\n## Quick Start\n\nInstall the hook (one step):\n```bash\ncp -r hooks\u002Fcontinual-learning .github\u002Fhooks\u002F\n```\n\nAuto-initializes on first session. No config needed.\n\n## Two-Tier Memory\n\n**Global** (`~\u002F.copilot\u002Flearnings.db`) — follows you across all projects:\n- Tool patterns (which tools fail, which work)\n- Cross-project conventions\n- General coding preferences\n\n**Local** (`.copilot-memory\u002Flearnings.db`) — stays with this repo:\n- Project-specific conventions\n- Common mistakes for this codebase\n- Team preferences\n\n## How Learnings Get Stored\n\n### Automatic (via hooks)\nThe hook observes tool outcomes and detects failure patterns:\n```\nSession 1: bash tool fails 4 times → learning stored: \"bash frequently fails\"\nSession 2: hook surfaces that learning at start → agent adjusts approach\n```\n\n### Agent-native (via store_memory \u002F SQL)\nThe agent can write learnings directly:\n```sql\nINSERT INTO learnings (scope, category, content, source)\nVALUES ('local', 'convention', 'This project uses Result\u003CT> not exceptions', 'user_correction');\n```\n\nCategories: `pattern`, `mistake`, `preference`, `tool_insight`\n\n### Manual (memory files)\nFor human-readable, version-controlled knowledge:\n```markdown\n# .copilot-memory\u002Fconventions.md\n- Use DefaultAzureCredential for all Azure auth\n- Parameter is semantic_configuration_name=, not semantic_configuration=\n```\n\n## Compaction\n\nLearnings decay over time:\n- Entries older than 60 days with low hit count are pruned\n- High-value learnings (frequently referenced) persist indefinitely\n- Tool logs are pruned after 7 days\n\nThis prevents unbounded growth while preserving what matters.\n\n## Best Practices\n\n1. **One step to install** — if it takes more than `cp -r`, it won't get adopted\n2. **Scope correctly** — global for tool patterns, local for project conventions\n3. **Be specific** — `\"Use semantic_configuration_name=\"` beats `\"use the right parameter\"`\n4. **Let it compound** — small improvements per session create exponential gains over weeks\n","# Continual Learning for AI Coding Agents\n\nYour agent forgets everything between sessions. Continual learning fixes that.\n\n## The Loop\n\n```\nExperience → Capture → Reflect → Persist → Apply\n     ↑                                       │\n     └───────────────────────────────────────┘\n```\n\n## Quick Start\n\nInstall the hook (one step):\n```bash\ncp -r hooks\u002Fcontinual-learning .github\u002Fhooks\u002F\n```\n\nAuto-initializes on first session. No config needed.\n\n## Two-Tier Memory\n\n**Global** (`~\u002F.copilot\u002Flearnings.db`) — follows you across all projects:\n- Tool patterns (which tools fail, which work)\n- Cross-project conventions\n- General coding preferences\n\n**Local** (`.copilot-memory\u002Flearnings.db`) — stays with this repo:\n- Project-specific conventions\n- Common mistakes for this codebase\n- Team preferences\n\n## How Learnings Get Stored\n\n### Automatic (via hooks)\nThe hook observes tool outcomes and detects failure patterns:\n```\nSession 1: bash tool fails 4 times → learning stored: \"bash frequently fails\"\nSession 2: hook surfaces that learning at start → agent adjusts approach\n```\n\n### Agent-native (via store_memory \u002F SQL)\nThe agent can write learnings directly:\n```sql\nINSERT INTO learnings (scope, category, content, source)\nVALUES ('local', 'convention', 'This project uses Result\u003CT> not exceptions', 'user_correction');\n```\n\nCategories: `pattern`, `mistake`, `preference`, `tool_insight`\n\n### Manual (memory files)\nFor human-readable, version-controlled knowledge:\n```markdown\n# .copilot-memory\u002Fconventions.md\n- Use DefaultAzureCredential for all Azure auth\n- Parameter is semantic_configuration_name=, not semantic_configuration=\n```\n\n## Compaction\n\nLearnings decay over time:\n- Entries older than 60 days with low hit count are pruned\n- High-value learnings (frequently referenced) persist indefinitely\n- Tool logs are pruned after 7 days\n\nThis prevents unbounded growth while preserving what matters.\n\n## Best Practices\n\n1. **One step to install** — if it takes more than `cp -r`, it won't get adopted\n2. **Scope correctly** — global for tool patterns, local for project conventions\n3. **Be specific** — `\"Use semantic_configuration_name=\"` beats `\"use the right parameter\"`\n4. **Let it compound** — small improvements per session create exponential gains over weeks\n",{"name":5,"description":7},"main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fskills\u002Fcontinual-learning",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 02:08:41",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add microsoft\u002Fskills --skill continual-learning",{"tool":63,"command":64},"bunx","bunx skills add microsoft\u002Fskills --skill continual-learning",{"tool":66,"command":67},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill continual-learning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcontinual-learning\u002FSKILL.md",true,[],[72,90,128,155,176,213],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":79,"publishedAt":42},"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",[78],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[80,81,35,9,82,83,40,84,85,38,36,26,32,86,87,28,88,27,89],"skill creator","creator","foundry","microsoft foundry","azure","services","with","sdks","Existing","new",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":106,"publishedAt":42},"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",[96,99,102,105],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":100,"categoryName":101,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[107,108,109,110,111,112,113,84,114,115,116,117,118,119,120,121,122,123,124,125,126,27,127],"podcast generation","podcast","generation","frontend","python","react","realtime","azure openai","generate","streaming","api","Audio","stack","text","model","fastapi","creation","python fastapi","narrative","features","fastapi backend",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":135,"publishedAt":42},"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",[134],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[136,9,137,138,139,140,141,142,143,144,145,84,146,147,148,26,149,60,150,151,152,153,154,28],"docs","microsoft docs","MCP","writing","cli","mcp server","windows","power platform","official","documentation","learn","best practices","question","power","back","technology","platform","learn mcp","concept",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":42},"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",[161],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[138,163,164,165,111,166,167,168,9,169,170,121,171,172,36,26,173,174,175,86,28,27],"mcp builder","builder","typescript","llms","sdk","model context protocol","fastmcp","Tools","node","context","integrate","mcp sdk","building mcp servers",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":194,"publishedAt":42},"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",[182,185,186,191],{"categoryNo":183,"categoryName":184,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":187,"categoryName":188,"taxonomyType":189,"taxonomyTypeDesc":190},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":192,"categoryName":193,"taxonomyType":189,"taxonomyTypeDesc":190},"01JBSEEDCAT000000000000036","内容创作者",[178,139,195,41,196,84,197,198,199,200,201,202,203,204,205,206,207,208,209,28,210,211,212],"summarize","analytics","vector","time series","tool","discipline","log","geo","exploration","pipe","time","project","regex","join","datetime","section","anomaly","parse",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":219,"publishedAt":42},"01M69B44HJQ7897EZ7NE7DWQX3","github-issue-creator","Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images\u002FGIFs for visual evidence.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fgithub-issue-creator\u002FSKILL.md",[],[220,221,222,223,81,224,225,226,227,228,229,230,26,231,232,233,234,235,236,28,27],"github","github issue creator","github issue","issue","issue creator","screenshots","notes","logs","error messages","messages","convert","evidence","reports","images","info","visual","error"]