[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-error-exploration":3,"mdc-h1nv9s-key":35,"related-org-microsoft-error-exploration":617,"related-repo-microsoft-error-exploration":812},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":25,"topics":29,"repo":30,"sourceUrl":33,"mdContent":34},"error-exploration","investigate errors in Application Insights","Explore errors in Application Insights — exceptions, failed requests, and failed dependencies. Use this when asked to find errors, investigate failures, identify reliability issues, or recommend which errors to fix.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"microsoft","Microsoft","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmicrosoft.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"Application Insights","application-insights",{"name":20,"slug":21,"type":15},"Azure","azure",{"name":23,"slug":24,"type":15},"Debugging","debugging",2,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcode-optimizations-skills","2026-07-03T16:32:18.458603",null,[],{"repoUrl":26,"stars":25,"forks":25,"topics":31,"description":32},[],"GitHub Copilot CLI skill plugin for code optimizations based on Profiler and Telemtries.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fcode-optimizations-skills\u002Ftree\u002FHEAD\u002Fskills\u002Ferror-exploration","---\nname: error-exploration\ncategory: exploring\ndescription: Explore errors in Application Insights — exceptions, failed requests, and failed dependencies. Use this when asked to find errors, investigate failures, identify reliability issues, or recommend which errors to fix.\n---\n\n# Analysis\n\nWhen asked to explore errors or investigate failures in Application Insights, follow these steps:\n\n1. **Check investigation notes and gather inputs** — Follow the [Standard Skill Preamble](..\u002Fshared\u002Fstandard-skill-preamble.md) to check for existing investigation context and gather inputs.\n\n2. **Identify the Application Insights resource** — If the investigation notes didn't have the resource or the user wants a different one, follow the steps in [Identify Application Insights Resource](..\u002Fperf-optimization\u002Freferences\u002Fidentify-appinsights-resource.md). After the resource is confirmed, **write or update `investigation-notes.md`** with the confirmed values. If only a resource ID is available, resolve the app ID using [resolve-app-id.md](..\u002Fshared\u002Fresolve-app-id.md).\n\n3. **Query for exceptions** — Run the script in [query-exceptions.md](scripts\u002Fquery-exceptions.md) to find the most frequent exceptions, grouped by type and calling method. The query includes trend analysis (increasing\u002Fdecreasing\u002Fstable) and problem IDs for drill-down. The default lookback is 24 hours — adjust the `$lookbackHours` parameter to widen or narrow the window as needed.\n\n   > **⚠️ CLI query pitfalls**: Before running or modifying any query script, read [az CLI query pitfalls](..\u002Fshared\u002Faz-cli-query-pitfalls.md). Key points: (1) `--offset` is **mandatory**, (2) always use `--output json`, (3) flatten KQL to a single line.\n\n4. **Query for failed requests** — Run the script in [query-failed-requests.md](scripts\u002Fquery-failed-requests.md) to find failed HTTP requests (status code ≥ 400 or `success == false`), grouped by operation name and result code. This surfaces user-facing failures with duration statistics that can reveal timeout patterns.\n\n5. **Query for failed dependencies** — Run the script in [query-failed-dependencies.md](scripts\u002Fquery-failed-dependencies.md) to find failed dependency calls (HTTP, SQL, storage, etc.), grouped by type, target, and result code. The query includes `AffectedOperations` to measure blast radius — how many distinct operations are impacted by each dependency failure.\n\n   > **Running all three queries**: Run steps 3, 4, and 5 in sequence. Each query targets a different telemetry table and provides a different perspective on errors. Together, they give a comprehensive picture of the application's error landscape.\n\n6. **Present unified error report and recommend priorities** — After collecting results from all three queries, synthesize the findings into a prioritized error report. Use the [Error Prioritization Guide](references\u002Ferror-prioritization-guide.md) to rank errors by impact. Present the report to the user with clear recommendations.\n\n   **How to present the results:**\n   - **Lead with a summary** — State the total counts across all three categories (e.g., \"Found 12 exception groups, 8 failed request patterns, and 5 failed dependency groups in the last 24 hours\").\n   - **Highlight the top 2–3 issues to fix** — For each, explain:\n     - What the error is (type, operation, target)\n     - How often it occurs and the trend direction\n     - Why it matters (user impact, blast radius, severity class)\n     - What to investigate next\n   - **Correlate across categories** — Look for patterns where exceptions, failed requests, and failed dependencies are related (e.g., a `TimeoutException` in the caller correlates with a failed HTTP dependency to the same target). These correlated patterns are the most actionable.\n   - **Rank by composite priority** — Use the prioritization framework: 🔴 Fix immediately (increasing 5xx, cascading failures), 🟡 Fix soon (stable high-frequency errors), 🟢 Monitor (decreasing trends, expected 4xx).\n\n   > **Why present before deep-diving**: The user may have context about which errors are known issues, which are expected, and which are the most impactful. Let them choose what to investigate further.\n\n7. **Offer deep-dive options** — Based on the user's selection, offer these investigation paths:\n\n   - **View exception details**: Query for full stack traces and variable context for a specific exception group. Use the `problemId` to filter: `exceptions | where problemId == \"\u003CPROBLEM_ID>\" | take 5 | project timestamp, outerMessage, details`.\n   - **Trace a specific failed request**: Use the `deep-analysis` skill with a specific operation ID to see the full distributed trace for a failed request — including all dependency calls and their timing.\n   - **Investigate performance + errors**: If failed requests also show high latency, hand off to the `perf-optimization` skill to correlate error patterns with profiler data and identify whether the failures are timeout-related.\n   - **Check downstream dependency health**: For failed dependencies, investigate whether the target service has its own App Insights resource. If so, suggest using the `deep-analysis` skill to trace the operation from the caller's perspective into the downstream service.\n   - **Widen the time range**: If the current results show a trend, offer to re-run the queries with a wider lookback (7 or 30 days) to establish a historical baseline.\n\n## Tips\n\n- Always confirm the Application Insights resource with the user before proceeding with analysis.\n- Start with the default 24-hour lookback for an overview, then narrow or widen based on findings.\n- When presenting results, focus on actionable insights rather than raw data. The user wants to know \"what's broken and what should I fix first,\" not just \"here are the numbers.\"\n- Correlating across error categories produces the most valuable insights. A failed dependency that causes exceptions that cause request failures tells a clear story.\n- Not all 4xx errors are problems — 404s on optional resources, 401s before authentication, and 409s on idempotent retries may be expected. Ask the user before classifying these as issues.\n- **Distributed trace analysis**: If a failed request involves calls to downstream services, suggest the `deep-analysis` skill with the operation ID to trace the full request flow across services.\n- **Performance correlation**: If errors cluster around specific operations that are also slow, suggest the `perf-optimization` skill to check whether the errors are timeout-related.\n\n## References\n\nFor the investigation notes format and read\u002Fwrite protocol, see:\n- [Investigation Notes](..\u002Fshared\u002Finvestigation-notes.md)\n\nFor known `az monitor app-insights query` CLI issues, see:\n- [az CLI Query Pitfalls](..\u002Fshared\u002Faz-cli-query-pitfalls.md)\n\nFor detailed guidance on finding Application Insights resources, see:\n- [Identify Application Insights Resource](..\u002Fperf-optimization\u002Freferences\u002Fidentify-appinsights-resource.md)\n\nFor how to rank and prioritize errors, see:\n- [Error Prioritization Guide](references\u002Ferror-prioritization-guide.md)\n",{"data":36,"body":38},{"name":4,"category":37,"description":6},"exploring",{"type":39,"children":40},"root",[41,50,56,471,478,540,546,551,563,576,587,592,602,607],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"analysis",[47],{"type":48,"value":49},"text","Analysis",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"When asked to explore errors or investigate failures in Application Insights, follow these steps:",{"type":42,"tag":57,"props":58,"children":59},"ol",{},[60,81,121,192,217,255,370],{"type":42,"tag":61,"props":62,"children":63},"li",{},[64,70,72,79],{"type":42,"tag":65,"props":66,"children":67},"strong",{},[68],{"type":48,"value":69},"Check investigation notes and gather inputs",{"type":48,"value":71}," — Follow the ",{"type":42,"tag":73,"props":74,"children":76},"a",{"href":75},"..\u002Fshared\u002Fstandard-skill-preamble.md",[77],{"type":48,"value":78},"Standard Skill Preamble",{"type":48,"value":80}," to check for existing investigation context and gather inputs.",{"type":42,"tag":61,"props":82,"children":83},{},[84,89,91,97,99,111,113,119],{"type":42,"tag":65,"props":85,"children":86},{},[87],{"type":48,"value":88},"Identify the Application Insights resource",{"type":48,"value":90}," — If the investigation notes didn't have the resource or the user wants a different one, follow the steps in ",{"type":42,"tag":73,"props":92,"children":94},{"href":93},"..\u002Fperf-optimization\u002Freferences\u002Fidentify-appinsights-resource.md",[95],{"type":48,"value":96},"Identify Application Insights Resource",{"type":48,"value":98},". After the resource is confirmed, ",{"type":42,"tag":65,"props":100,"children":101},{},[102,104],{"type":48,"value":103},"write or update ",{"type":42,"tag":105,"props":106,"children":108},"code",{"className":107},[],[109],{"type":48,"value":110},"investigation-notes.md",{"type":48,"value":112}," with the confirmed values. If only a resource ID is available, resolve the app ID using ",{"type":42,"tag":73,"props":114,"children":116},{"href":115},"..\u002Fshared\u002Fresolve-app-id.md",[117],{"type":48,"value":118},"resolve-app-id.md",{"type":48,"value":120},".",{"type":42,"tag":61,"props":122,"children":123},{},[124,129,131,137,139,145,147],{"type":42,"tag":65,"props":125,"children":126},{},[127],{"type":48,"value":128},"Query for exceptions",{"type":48,"value":130}," — Run the script in ",{"type":42,"tag":73,"props":132,"children":134},{"href":133},"scripts\u002Fquery-exceptions.md",[135],{"type":48,"value":136},"query-exceptions.md",{"type":48,"value":138}," to find the most frequent exceptions, grouped by type and calling method. The query includes trend analysis (increasing\u002Fdecreasing\u002Fstable) and problem IDs for drill-down. The default lookback is 24 hours — adjust the ",{"type":42,"tag":105,"props":140,"children":142},{"className":141},[],[143],{"type":48,"value":144},"$lookbackHours",{"type":48,"value":146}," parameter to widen or narrow the window as needed.",{"type":42,"tag":148,"props":149,"children":150},"blockquote",{},[151],{"type":42,"tag":51,"props":152,"children":153},{},[154,159,161,167,169,175,177,182,184,190],{"type":42,"tag":65,"props":155,"children":156},{},[157],{"type":48,"value":158},"⚠️ CLI query pitfalls",{"type":48,"value":160},": Before running or modifying any query script, read ",{"type":42,"tag":73,"props":162,"children":164},{"href":163},"..\u002Fshared\u002Faz-cli-query-pitfalls.md",[165],{"type":48,"value":166},"az CLI query pitfalls",{"type":48,"value":168},". Key points: (1) ",{"type":42,"tag":105,"props":170,"children":172},{"className":171},[],[173],{"type":48,"value":174},"--offset",{"type":48,"value":176}," is ",{"type":42,"tag":65,"props":178,"children":179},{},[180],{"type":48,"value":181},"mandatory",{"type":48,"value":183},", (2) always use ",{"type":42,"tag":105,"props":185,"children":187},{"className":186},[],[188],{"type":48,"value":189},"--output json",{"type":48,"value":191},", (3) flatten KQL to a single line.",{"type":42,"tag":61,"props":193,"children":194},{},[195,200,201,207,209,215],{"type":42,"tag":65,"props":196,"children":197},{},[198],{"type":48,"value":199},"Query for failed requests",{"type":48,"value":130},{"type":42,"tag":73,"props":202,"children":204},{"href":203},"scripts\u002Fquery-failed-requests.md",[205],{"type":48,"value":206},"query-failed-requests.md",{"type":48,"value":208}," to find failed HTTP requests (status code ≥ 400 or ",{"type":42,"tag":105,"props":210,"children":212},{"className":211},[],[213],{"type":48,"value":214},"success == false",{"type":48,"value":216},"), grouped by operation name and result code. This surfaces user-facing failures with duration statistics that can reveal timeout patterns.",{"type":42,"tag":61,"props":218,"children":219},{},[220,225,226,232,234,240,242],{"type":42,"tag":65,"props":221,"children":222},{},[223],{"type":48,"value":224},"Query for failed dependencies",{"type":48,"value":130},{"type":42,"tag":73,"props":227,"children":229},{"href":228},"scripts\u002Fquery-failed-dependencies.md",[230],{"type":48,"value":231},"query-failed-dependencies.md",{"type":48,"value":233}," to find failed dependency calls (HTTP, SQL, storage, etc.), grouped by type, target, and result code. The query includes ",{"type":42,"tag":105,"props":235,"children":237},{"className":236},[],[238],{"type":48,"value":239},"AffectedOperations",{"type":48,"value":241}," to measure blast radius — how many distinct operations are impacted by each dependency failure.",{"type":42,"tag":148,"props":243,"children":244},{},[245],{"type":42,"tag":51,"props":246,"children":247},{},[248,253],{"type":42,"tag":65,"props":249,"children":250},{},[251],{"type":48,"value":252},"Running all three queries",{"type":48,"value":254},": Run steps 3, 4, and 5 in sequence. Each query targets a different telemetry table and provides a different perspective on errors. Together, they give a comprehensive picture of the application's error landscape.",{"type":42,"tag":61,"props":256,"children":257},{},[258,263,265,271,273,277,282,357],{"type":42,"tag":65,"props":259,"children":260},{},[261],{"type":48,"value":262},"Present unified error report and recommend priorities",{"type":48,"value":264}," — After collecting results from all three queries, synthesize the findings into a prioritized error report. Use the ",{"type":42,"tag":73,"props":266,"children":268},{"href":267},"references\u002Ferror-prioritization-guide.md",[269],{"type":48,"value":270},"Error Prioritization Guide",{"type":48,"value":272}," to rank errors by impact. Present the report to the user with clear recommendations.",{"type":42,"tag":274,"props":275,"children":276},"br",{},[],{"type":42,"tag":65,"props":278,"children":279},{},[280],{"type":48,"value":281},"How to present the results:",{"type":42,"tag":283,"props":284,"children":285},"ul",{},[286,296,329,347],{"type":42,"tag":61,"props":287,"children":288},{},[289,294],{"type":42,"tag":65,"props":290,"children":291},{},[292],{"type":48,"value":293},"Lead with a summary",{"type":48,"value":295}," — State the total counts across all three categories (e.g., \"Found 12 exception groups, 8 failed request patterns, and 5 failed dependency groups in the last 24 hours\").",{"type":42,"tag":61,"props":297,"children":298},{},[299,304,306],{"type":42,"tag":65,"props":300,"children":301},{},[302],{"type":48,"value":303},"Highlight the top 2–3 issues to fix",{"type":48,"value":305}," — For each, explain:\n",{"type":42,"tag":283,"props":307,"children":308},{},[309,314,319,324],{"type":42,"tag":61,"props":310,"children":311},{},[312],{"type":48,"value":313},"What the error is (type, operation, target)",{"type":42,"tag":61,"props":315,"children":316},{},[317],{"type":48,"value":318},"How often it occurs and the trend direction",{"type":42,"tag":61,"props":320,"children":321},{},[322],{"type":48,"value":323},"Why it matters (user impact, blast radius, severity class)",{"type":42,"tag":61,"props":325,"children":326},{},[327],{"type":48,"value":328},"What to investigate next",{"type":42,"tag":61,"props":330,"children":331},{},[332,337,339,345],{"type":42,"tag":65,"props":333,"children":334},{},[335],{"type":48,"value":336},"Correlate across categories",{"type":48,"value":338}," — Look for patterns where exceptions, failed requests, and failed dependencies are related (e.g., a ",{"type":42,"tag":105,"props":340,"children":342},{"className":341},[],[343],{"type":48,"value":344},"TimeoutException",{"type":48,"value":346}," in the caller correlates with a failed HTTP dependency to the same target). These correlated patterns are the most actionable.",{"type":42,"tag":61,"props":348,"children":349},{},[350,355],{"type":42,"tag":65,"props":351,"children":352},{},[353],{"type":48,"value":354},"Rank by composite priority",{"type":48,"value":356}," — Use the prioritization framework: 🔴 Fix immediately (increasing 5xx, cascading failures), 🟡 Fix soon (stable high-frequency errors), 🟢 Monitor (decreasing trends, expected 4xx).",{"type":42,"tag":148,"props":358,"children":359},{},[360],{"type":42,"tag":51,"props":361,"children":362},{},[363,368],{"type":42,"tag":65,"props":364,"children":365},{},[366],{"type":48,"value":367},"Why present before deep-diving",{"type":48,"value":369},": The user may have context about which errors are known issues, which are expected, and which are the most impactful. Let them choose what to investigate further.",{"type":42,"tag":61,"props":371,"children":372},{},[373,378,380],{"type":42,"tag":65,"props":374,"children":375},{},[376],{"type":48,"value":377},"Offer deep-dive options",{"type":48,"value":379}," — Based on the user's selection, offer these investigation paths:",{"type":42,"tag":283,"props":381,"children":382},{},[383,408,426,444,461],{"type":42,"tag":61,"props":384,"children":385},{},[386,391,393,399,401,407],{"type":42,"tag":65,"props":387,"children":388},{},[389],{"type":48,"value":390},"View exception details",{"type":48,"value":392},": Query for full stack traces and variable context for a specific exception group. Use the ",{"type":42,"tag":105,"props":394,"children":396},{"className":395},[],[397],{"type":48,"value":398},"problemId",{"type":48,"value":400}," to filter: ",{"type":42,"tag":105,"props":402,"children":404},{"className":403},[],[405],{"type":48,"value":406},"exceptions | where problemId == \"\u003CPROBLEM_ID>\" | take 5 | project timestamp, outerMessage, details",{"type":48,"value":120},{"type":42,"tag":61,"props":409,"children":410},{},[411,416,418,424],{"type":42,"tag":65,"props":412,"children":413},{},[414],{"type":48,"value":415},"Trace a specific failed request",{"type":48,"value":417},": Use the ",{"type":42,"tag":105,"props":419,"children":421},{"className":420},[],[422],{"type":48,"value":423},"deep-analysis",{"type":48,"value":425}," skill with a specific operation ID to see the full distributed trace for a failed request — including all dependency calls and their timing.",{"type":42,"tag":61,"props":427,"children":428},{},[429,434,436,442],{"type":42,"tag":65,"props":430,"children":431},{},[432],{"type":48,"value":433},"Investigate performance + errors",{"type":48,"value":435},": If failed requests also show high latency, hand off to the ",{"type":42,"tag":105,"props":437,"children":439},{"className":438},[],[440],{"type":48,"value":441},"perf-optimization",{"type":48,"value":443}," skill to correlate error patterns with profiler data and identify whether the failures are timeout-related.",{"type":42,"tag":61,"props":445,"children":446},{},[447,452,454,459],{"type":42,"tag":65,"props":448,"children":449},{},[450],{"type":48,"value":451},"Check downstream dependency health",{"type":48,"value":453},": For failed dependencies, investigate whether the target service has its own App Insights resource. If so, suggest using the ",{"type":42,"tag":105,"props":455,"children":457},{"className":456},[],[458],{"type":48,"value":423},{"type":48,"value":460}," skill to trace the operation from the caller's perspective into the downstream service.",{"type":42,"tag":61,"props":462,"children":463},{},[464,469],{"type":42,"tag":65,"props":465,"children":466},{},[467],{"type":48,"value":468},"Widen the time range",{"type":48,"value":470},": If the current results show a trend, offer to re-run the queries with a wider lookback (7 or 30 days) to establish a historical baseline.",{"type":42,"tag":472,"props":473,"children":475},"h2",{"id":474},"tips",[476],{"type":48,"value":477},"Tips",{"type":42,"tag":283,"props":479,"children":480},{},[481,486,491,496,501,506,523],{"type":42,"tag":61,"props":482,"children":483},{},[484],{"type":48,"value":485},"Always confirm the Application Insights resource with the user before proceeding with analysis.",{"type":42,"tag":61,"props":487,"children":488},{},[489],{"type":48,"value":490},"Start with the default 24-hour lookback for an overview, then narrow or widen based on findings.",{"type":42,"tag":61,"props":492,"children":493},{},[494],{"type":48,"value":495},"When presenting results, focus on actionable insights rather than raw data. The user wants to know \"what's broken and what should I fix first,\" not just \"here are the numbers.\"",{"type":42,"tag":61,"props":497,"children":498},{},[499],{"type":48,"value":500},"Correlating across error categories produces the most valuable insights. A failed dependency that causes exceptions that cause request failures tells a clear story.",{"type":42,"tag":61,"props":502,"children":503},{},[504],{"type":48,"value":505},"Not all 4xx errors are problems — 404s on optional resources, 401s before authentication, and 409s on idempotent retries may be expected. Ask the user before classifying these as issues.",{"type":42,"tag":61,"props":507,"children":508},{},[509,514,516,521],{"type":42,"tag":65,"props":510,"children":511},{},[512],{"type":48,"value":513},"Distributed trace analysis",{"type":48,"value":515},": If a failed request involves calls to downstream services, suggest the ",{"type":42,"tag":105,"props":517,"children":519},{"className":518},[],[520],{"type":48,"value":423},{"type":48,"value":522}," skill with the operation ID to trace the full request flow across services.",{"type":42,"tag":61,"props":524,"children":525},{},[526,531,533,538],{"type":42,"tag":65,"props":527,"children":528},{},[529],{"type":48,"value":530},"Performance correlation",{"type":48,"value":532},": If errors cluster around specific operations that are also slow, suggest the ",{"type":42,"tag":105,"props":534,"children":536},{"className":535},[],[537],{"type":48,"value":441},{"type":48,"value":539}," skill to check whether the errors are timeout-related.",{"type":42,"tag":472,"props":541,"children":543},{"id":542},"references",[544],{"type":48,"value":545},"References",{"type":42,"tag":51,"props":547,"children":548},{},[549],{"type":48,"value":550},"For the investigation notes format and read\u002Fwrite protocol, see:",{"type":42,"tag":283,"props":552,"children":553},{},[554],{"type":42,"tag":61,"props":555,"children":556},{},[557],{"type":42,"tag":73,"props":558,"children":560},{"href":559},"..\u002Fshared\u002Finvestigation-notes.md",[561],{"type":48,"value":562},"Investigation Notes",{"type":42,"tag":51,"props":564,"children":565},{},[566,568,574],{"type":48,"value":567},"For known ",{"type":42,"tag":105,"props":569,"children":571},{"className":570},[],[572],{"type":48,"value":573},"az monitor app-insights query",{"type":48,"value":575}," CLI issues, see:",{"type":42,"tag":283,"props":577,"children":578},{},[579],{"type":42,"tag":61,"props":580,"children":581},{},[582],{"type":42,"tag":73,"props":583,"children":584},{"href":163},[585],{"type":48,"value":586},"az CLI Query Pitfalls",{"type":42,"tag":51,"props":588,"children":589},{},[590],{"type":48,"value":591},"For detailed guidance on finding Application Insights resources, see:",{"type":42,"tag":283,"props":593,"children":594},{},[595],{"type":42,"tag":61,"props":596,"children":597},{},[598],{"type":42,"tag":73,"props":599,"children":600},{"href":93},[601],{"type":48,"value":96},{"type":42,"tag":51,"props":603,"children":604},{},[605],{"type":48,"value":606},"For how to rank and prioritize errors, see:",{"type":42,"tag":283,"props":608,"children":609},{},[610],{"type":42,"tag":61,"props":611,"children":612},{},[613],{"type":42,"tag":73,"props":614,"children":615},{"href":267},[616],{"type":48,"value":270},{"items":618,"total":811},[619,641,660,681,696,713,724,737,752,767,786,799],{"slug":620,"name":620,"fn":621,"description":622,"org":623,"tags":624,"stars":638,"repoUrl":639,"updatedAt":640},"rushstack-best-practices","manage Rush monorepos with best practices","Provides best practices and guidance for working with Rush monorepos. Use when the user is working in a Rush-based repository, asks about Rush commands (install, update, build, rebuild), needs help with project selection, dependency management, build caching, subspace configuration, or troubleshooting Rush-specific issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[625,628,631,632,635],{"name":626,"slug":627,"type":15},"Engineering","engineering",{"name":629,"slug":630,"type":15},"Local Development","local-development",{"name":9,"slug":8,"type":15},{"name":633,"slug":634,"type":15},"Project Management","project-management",{"name":636,"slug":637,"type":15},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":642,"name":642,"fn":643,"description":644,"org":645,"tags":646,"stars":657,"repoUrl":658,"updatedAt":659},"azure-ai-agents-persistent-dotnet","build AI agents with Azure .NET SDK","Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[647,650,653,654],{"name":648,"slug":649,"type":15},".NET","net",{"name":651,"slug":652,"type":15},"Agents","agents",{"name":20,"slug":21,"type":15},{"name":655,"slug":656,"type":15},"LLM","llm",2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-03T16:32:10.297433",{"slug":661,"name":661,"fn":662,"description":663,"org":664,"tags":665,"stars":657,"repoUrl":658,"updatedAt":680},"azure-ai-anomalydetector-java","build anomaly detection applications with Java","Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate\u002Fmultivariate anomaly detection, time-series analysis, or AI-powered monitoring.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[666,669,670,673,676,677],{"name":667,"slug":668,"type":15},"Analytics","analytics",{"name":20,"slug":21,"type":15},{"name":671,"slug":672,"type":15},"Data Analysis","data-analysis",{"name":674,"slug":675,"type":15},"Java","java",{"name":9,"slug":8,"type":15},{"name":678,"slug":679,"type":15},"Monitoring","monitoring","2026-05-13T06:14:16.261754",{"slug":682,"name":682,"fn":683,"description":684,"org":685,"tags":686,"stars":657,"repoUrl":658,"updatedAt":695},"azure-ai-contentsafety-java","build content moderation applications with Azure AI","Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[687,690,691,692],{"name":688,"slug":689,"type":15},"AI Infrastructure","ai-infrastructure",{"name":20,"slug":21,"type":15},{"name":674,"slug":675,"type":15},{"name":693,"slug":694,"type":15},"Security","security","2026-07-07T06:53:31.293235",{"slug":697,"name":697,"fn":698,"description":699,"org":700,"tags":701,"stars":657,"repoUrl":658,"updatedAt":712},"azure-ai-contentsafety-py","detect harmful content with Azure AI Content Safety","Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.\nTriggers: \"azure-ai-contentsafety\", \"ContentSafetyClient\", \"content moderation\", \"harmful content\", \"text analysis\", \"image analysis\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[702,703,706,707,708,711],{"name":20,"slug":21,"type":15},{"name":704,"slug":705,"type":15},"Compliance","compliance",{"name":655,"slug":656,"type":15},{"name":9,"slug":8,"type":15},{"name":709,"slug":710,"type":15},"Python","python",{"name":693,"slug":694,"type":15},"2026-07-18T05:14:23.017504",{"slug":714,"name":714,"fn":715,"description":716,"org":717,"tags":718,"stars":657,"repoUrl":658,"updatedAt":723},"azure-ai-language-conversations-py","implement conversational language understanding with Python","Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[719,720,721,722],{"name":667,"slug":668,"type":15},{"name":20,"slug":21,"type":15},{"name":655,"slug":656,"type":15},{"name":709,"slug":710,"type":15},"2026-07-31T05:54:29.068751",{"slug":725,"name":725,"fn":726,"description":727,"org":728,"tags":729,"stars":657,"repoUrl":658,"updatedAt":736},"azure-ai-translation-text-py","translate text using Azure AI services","Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications.\nTriggers: \"text translation\", \"translator\", \"translate text\", \"transliterate\", \"TextTranslationClient\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[730,733,734,735],{"name":731,"slug":732,"type":15},"API Development","api-development",{"name":20,"slug":21,"type":15},{"name":9,"slug":8,"type":15},{"name":709,"slug":710,"type":15},"2026-07-18T05:14:16.988376",{"slug":738,"name":738,"fn":739,"description":740,"org":741,"tags":742,"stars":657,"repoUrl":658,"updatedAt":751},"azure-ai-vision-imageanalysis-py","analyze images with Azure AI Vision","Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.\nTriggers: \"image analysis\", \"computer vision\", \"OCR\", \"object detection\", \"ImageAnalysisClient\", \"image caption\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[743,744,747,750],{"name":20,"slug":21,"type":15},{"name":745,"slug":746,"type":15},"Computer Vision","computer-vision",{"name":748,"slug":749,"type":15},"Images","images",{"name":709,"slug":710,"type":15},"2026-07-18T05:14:18.007737",{"slug":753,"name":753,"fn":754,"description":755,"org":756,"tags":757,"stars":657,"repoUrl":658,"updatedAt":766},"azure-appconfiguration-java","manage configuration with Azure App Configuration","Azure App Configuration SDK for Java. Centralized application configuration management with key-value settings, feature flags, and snapshots.\nTriggers: \"ConfigurationClient java\", \"app configuration java\", \"feature flag java\", \"configuration setting java\", \"azure config java\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[758,759,762,765],{"name":20,"slug":21,"type":15},{"name":760,"slug":761,"type":15},"Configuration","configuration",{"name":763,"slug":764,"type":15},"Feature Flags","feature-flags",{"name":674,"slug":675,"type":15},"2026-07-03T16:32:01.278468",{"slug":768,"name":768,"fn":769,"description":770,"org":771,"tags":772,"stars":657,"repoUrl":658,"updatedAt":785},"azure-cosmos-rust","build applications with Azure Cosmos DB","Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data.\nTriggers: \"cosmos db rust\", \"CosmosClient rust\", \"document crud rust\", \"NoSQL rust\", \"partition key rust\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[773,776,779,782],{"name":774,"slug":775,"type":15},"Cosmos DB","cosmos-db",{"name":777,"slug":778,"type":15},"Database","database",{"name":780,"slug":781,"type":15},"NoSQL","nosql",{"name":783,"slug":784,"type":15},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":787,"name":787,"fn":769,"description":788,"org":789,"tags":790,"stars":657,"repoUrl":658,"updatedAt":798},"azure-cosmos-ts","Azure Cosmos DB JavaScript\u002FTypeScript SDK (@azure\u002Fcosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management. Triggers: \"Cosmos DB\", \"@azure\u002Fcosmos\", \"CosmosClient\", \"document CRUD\", \"NoSQL queries\", \"bulk operations\", \"partition key\", \"container.items\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[791,792,793,794,795],{"name":774,"slug":775,"type":15},{"name":777,"slug":778,"type":15},{"name":9,"slug":8,"type":15},{"name":780,"slug":781,"type":15},{"name":796,"slug":797,"type":15},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":800,"name":800,"fn":801,"description":802,"org":803,"tags":804,"stars":657,"repoUrl":658,"updatedAt":810},"azure-data-tables-java","build table storage applications with Java","Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[805,806,807,808,809],{"name":20,"slug":21,"type":15},{"name":774,"slug":775,"type":15},{"name":777,"slug":778,"type":15},{"name":674,"slug":675,"type":15},{"name":780,"slug":781,"type":15},"2026-05-13T06:14:17.582229",267,{"items":813,"total":25},[814,821],{"slug":4,"name":4,"fn":5,"description":6,"org":815,"tags":816,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[817,818,819,820],{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"slug":441,"name":441,"fn":822,"description":823,"org":824,"tags":825,"stars":25,"repoUrl":26,"updatedAt":831},"analyze and optimize application performance","Guide for analyzing performance issues based on profiler and code optimizations, including CPU, latency, and throughput. Use this when asked to investigate performance bottlenecks or optimize application performance.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[826,827,828],{"name":23,"slug":24,"type":15},{"name":626,"slug":627,"type":15},{"name":829,"slug":830,"type":15},"Performance","performance","2026-07-07T06:53:42.045028"]