[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AM4V7KQGGRKNZHN2YGA2Y":3,"skill-same:01M69AM4V7KQGGRKNZHN2YGA2Y":85},{"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},"01M69AM4V7KQGGRKNZHN2YGA2Y","azure-kusto-irql",null,"Compose IRQL (Incident Response Query Language) queries for Kusto cybersecurity investigations. Translates natural language hunting questions into composable IRQL pipelines using Get_*, Extract_*, and Enrich_* functions. WHEN: IRQL query, security hunt, threat hunting KQL, incident response query, compose hunting pipeline, failed logins, phishing investigation, lateral movement, process execution, file creation events.","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\u002Fazure-kusto-graph-skills\u002Fskills\u002Fazure-kusto-irql\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,9,41,42,43],"azure kusto irql","azure kusto","azure","query","investigations","when","process execution","lateral movement","hunting","enrich","events","creation","get","incident","security","threat","pipeline","threat hunting","incident response","cybersecurity","2026-11-10 10:12:30",false,"---\nname: azure-kusto-irql\ndescription: \"Compose IRQL (Incident Response Query Language) queries for Kusto cybersecurity investigations. Translates natural language hunting questions into composable IRQL pipelines using Get_*, Extract_*, and Enrich_* functions. WHEN: IRQL query, security hunt, threat hunting KQL, incident response query, compose hunting pipeline, failed logins, phishing investigation, lateral movement, process execution, file creation events.\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.2.1\"\n---\n\n# IRQL -- Incident Response Query Language\n\nCompose IRQL function pipelines from selector, extractor, and enricher building blocks. IRQL wraps raw KQL security tables behind intent-revealing, composable functions so analysts (and LLMs) can express hunts without memorizing schemas, cluster locations, or join keys.\n\n## Activation Triggers\n\nUse this skill when the user:\n- Explicitly mentions IRQL, `Get_*`, `Extract_*`, or `Enrich_*` functions\n- Says \"use IRQL\" or \"write an IRQL query\"\n- Requests a composable hunting pipeline using known IRQL selectors\n\nDo **not** activate for generic security queries (e.g. \"find failed logins\") unless the user explicitly asks for IRQL. Route those to `azure-kusto` instead.\n\n**Not a natural-language-to-IRQL converter.** This skill composes IRQL function pipelines and may handle basic natural-language requests that map directly to known selectors and simple filters. For general NL-to-KQL or NL-to-IRQL conversion, use a dedicated query-generation skill (available separately).\n\n## IRQL Function Preflight\n\nBefore generating a pipeline, verify IRQL is available on the target database:\n\n```kql\n.show functions\n| where Name startswith \"Get_\" or Name startswith \"Extract_\" or Name startswith \"Enrich_\"\n| project Name\n```\n\nIf no IRQL functions are found, inform the user that IRQL is not deployed on the target database and suggest using `azure-kusto` for raw KQL queries instead. IRQL functions are a prerequisite -- this skill does not deploy base IRQL selectors.\n\n## What IRQL Is\n\nIRQL is a **function-based dialect on top of KQL**. It provides:\n\n1. **Unified schema** -- disparate security tables project into consistent column names regardless of the underlying data source\n2. **Composability** -- small functions chain via `| invoke` to build complex hunts from simple steps\n3. **Portability** -- the same IRQL pipeline works across different clusters\u002Fdatabases; only the `Get_*` primitives need re-pointing\n\nIRQL is not a separate language. It's KQL functions you invoke. Any valid KQL works alongside IRQL functions.\n\n## Deploying IRQL\n\nIRQL functions are stored KQL functions (`.create-or-alter function`). They must already be deployed to the target database before this skill can generate pipelines.\n\n**Public example cluster** (functions pre-deployed):\n- Cluster: `https:\u002F\u002Fkc7001.eastus.kusto.windows.net`\n- Databases: `ValdyTimes`, `JoJosHospital`\n\nTo port IRQL to a new cluster\u002Fdatabase, create `Get_*` selectors that project your source tables into the unified schema (column names below), then deploy extractors and enrichers. The extractors and enrichers work unchanged as long as the input schema matches.\n\n## Function Catalog\n\n### 1. Selectors -- `Get_*`\n\nReturn projected, schema-unified views of source tables. Use the minimal form by default; use `_All` when extra columns are needed.\n\n| Function | Columns |\n|---|---|\n| `Get_Event_Authentication` | `EnvTime`, `Hostname`, `ClientIp`, `Username`, `Result` |\n| `Get_Event_Authentication_All` | + `Description`, `UserAgent`, `PasswordHash` |\n| `Get_Email` | `EnvTime`, `EmailSender`, `EmailRecipient`, `Subject`, `Url` |\n| `Get_Email_All` | + `ReplyTo`, `Verdict` |\n| `Get_Employees` | `Name`, `ClientIp`, `Email`, `Username`, `Hostname`, `Role` |\n| `Get_Employees_All` | + `HireDate`, `UserAgent`, `Domain` |\n| `Get_Event_FileCreation` | `EnvTime`, `Hostname`, `Filename`, `Path` |\n| `Get_Event_FileCreation_All` | + `Username`, `Sha256`, `ProcessName` |\n| `Get_Event_NetworkInbound` | `EnvTime`, `ClientIp`, `Url` |\n| `Get_Event_NetworkInbound_All` | + `Method`, `UserAgent`, `StatusCode` |\n| `Get_Event_NetworkOutbound` | `EnvTime`, `ClientIp`, `Url` |\n| `Get_Event_NetworkOutbound_All` | + `Method`, `UserAgent` |\n| `Get_Dns_All` | `EnvTime`, `Domain`, `ClientIp` |\n| `Get_Event_Process` | `EnvTime`, `ProcessCommandLine`, `ProcessName`, `Hostname`, `Username` |\n| `Get_Event_Process_All` | + `ParentProcessName`, `ParentProcessHash`, `ProcessHash` |\n| `Get_SecurityAlerts_All` | `EnvTime`, `AlertType`, `Severity`, `Description`, `Indicators` |\n| `Get_Network_Connection_All` | `EnvTime`, `SourceIp`, `SourcePort`, `DestinationIp`, `DestinationPort`, `Protocol`, `Bytes` |\n\n### 2. Extractors -- `Extract_*`\n\nDerive a new column from an existing one. Invoke after a selector.\n\n| Function | Input Column | Adds |\n|---|---|---|\n| `Extract_Email_Sender_Domain(T)` | `EmailSender` | `Domain` |\n| `Extract_Employee_Firstname(T)` | `Name` | `Firstname` |\n| `Extract_Event_Network_Domain(T)` | `Url` | `DomainName` |\n\n### 3. Enrichers -- `Enrich_*`\n\nLeft-join helpers that attach context from a related table.\n\n| Function | Key Column | Enriches With |\n|---|---|---|\n| `Enrich_Event_Authentication_Username(T)` | `Username` | Auth events for user |\n| `Enrich_Ip_Employee(T)` | `ClientIp` | Employee identity from IP |\n| `Enrich_Username_Employee(T)` | `Username` | Employee identity from username |\n| `Enrich_Ip_Domain(T)` | `ClientIp` | DNS domains resolved to IP |\n| `Enrich_Ip_Event_NetworkOutbound(T)` | `ClientIp` | Outbound network from IP |\n| `Enrich_Ip_Network_Connection(T)` | `ClientIp` | Network flows from IP |\n\n### 4. External Enrichment\n\n| Function | Source | Requirement |\n|---|---|---|\n| `Enrich_Sha256_VirusTotal(T)` | VirusTotal file report | API key + callout policy |\n| `Get_CISA_KEV()` \u002F `Enrich_CISA_KEV(T)` | CISA KEV catalog | Callout policy |\n\n## Composition Rules\n\n```\nSelector -> Extract -> Filter -> Enrich -> Summarize\u002FProject\n```\n\n1. **Start with a Selector**: `Get_Event_Authentication`, `Get_Email`, etc.\n2. **Extract** derived fields: `| invoke Extract_Email_Sender_Domain()`\n3. **Filter** to the signal: `| where Result == \"Failed Login\"`\n4. **Enrich** with context: `| invoke Enrich_Username_Employee()`\n5. **Summarize \u002F project** the answer\n\nAlways pipe (`|`) between steps. Extractors and Enrichers use `| invoke FunctionName()`.\n\n## Query Generation Guidelines\n\n- Use the **minimal selector** unless extra columns are needed -> then `_All`\n- Chain extractors before enrichers (extractors add columns enrichers may key on)\n- Place `where` filters as early as possible\n- Use `summarize` for aggregations, `project` for final column selection\n- End with `order by` + `take` to limit output\n\n## Examples\n\nFor additional prompts and worked examples, see [references\u002FEXAMPLES.md](references\u002FEXAMPLES.md).\n\n### Brute-force detection\n```kql\nGet_Event_Authentication\n| where Result == \"Failed Login\"\n| summarize FailedCount = count() by Username\n| where FailedCount > 19\n| invoke Enrich_Username_Employee()\n| project Username, Name, Role, Email, FailedCount\n| order by FailedCount desc\n```\n\n### Phishing triage by recipient seniority\n```kql\nGet_Email\n| invoke Extract_Email_Sender_Domain()\n| project EnvTime, EmailSender, Domain, Username = EmailRecipient, Subject, Url\n| invoke Enrich_Username_Employee()\n| extend Seniority = case(\n    Role has_any (\"CEO\", \"Chief\", \"Director\", \"VP\", \"President\"), 3,\n    Role has_any (\"Manager\", \"Lead\", \"Senior\"), 2,\n    1)\n| summarize\n    TotalEmails = count(),\n    SeniorityScore = sum(Seniority),\n    Recipients = make_set(Name, 50),\n    DistinctRecipients = dcount(Username)\n  by Domain\n| where DistinctRecipients >= 2\n| order by SeniorityScore desc\n| take 20\n```\n\n### Post-exploitation pivot from an indicator\n```kql\nlet victims =\n    Get_Event_FileCreation_All\n    | where Filename has \"\u003CINDICATOR>\"\n    | distinct Hostname;\nGet_Event_Process\n| where Hostname in (victims)\n| where ProcessCommandLine has_any (\"rundll32\", \"regsvr32\", \"powershell\", \"systeminfo\")\n| project EnvTime, Hostname, Username, ProcessName, ProcessCommandLine\n| order by EnvTime asc\n```\n\n### Suspicious outbound traffic enriched with identity\n```kql\nGet_Event_NetworkOutbound\n| invoke Extract_Event_Network_Domain()\n| where DomainName has_any (\"\u003CSUSPICIOUS_DOMAIN_1>\", \"\u003CSUSPICIOUS_DOMAIN_2>\")\n| invoke Enrich_Ip_Employee()\n| project EnvTime, Name, Role, DomainName, Url, ClientIp\n| order by EnvTime desc\n```\n\n### External IP authentication anomaly\n```kql\nGet_Event_Authentication_All\n| where not(ClientIp startswith \"10.\") and not(ClientIp startswith \"192.168.\")\n| summarize\n    Attempts = count(),\n    Failures = countif(Result == \"Failed Login\"),\n    Users = make_set(Username)\n  by ClientIp\n| order by Failures desc\n| take 20\n```\n\n## MCP Tools Used\n\n| Tool | Purpose |\n|------|---------|\n| `kusto_query` | Execute IRQL pipelines against a Kusto database |\n| `kusto_table_schema_get` | Discover available tables and columns |\n| `kusto_cluster_list` | List available ADX clusters |\n| `kusto_database_list` | List databases in a cluster |\n\n## Opening Queries in Kusto Explorer (Windows Only)\n\n> **Optional convenience feature.** The default workflow is to output the KQL in chat and let the user copy it into Kusto Explorer or the VS Code Kusto extension manually. Auto-launch is opt-in only.\n\nAlways output the complete KQL query in the chat response with Step 1 (connect) and Step 2 (query) clearly labeled:\n\n```\n\u002F\u002F Step 1: Connect to your cluster (skip if already connected)\n\u002F\u002F Example: uncomment to connect to the KC7 training cluster\n\u002F\u002F #connect cluster('kc7001.eastus.kusto.windows.net').database('ValdyTimes')\n\u002F\u002F Or replace with your own cluster:\n\u002F\u002F #connect cluster('\u003CYOUR_CLUSTER>').database('\u003CYOUR_DATABASE>')\n\n\u002F\u002F Step 2: Run the query below\n\u003CKQL_QUERY>\n```\n\nIf the user asks to save or open in Kusto Explorer, follow the procedure in [references\u002FKUSTO_EXPLORER_LAUNCH.md](references\u002FKUSTO_EXPLORER_LAUNCH.md). Key rules:\n\n- Use `ask_user` to confirm before writing files or launching executables\n- Display file contents in chat so the user can review before opening\n- Never use shell interpolation or here-strings — write files via `Set-Content`\u002F`Add-Content`\n- Never encode queries into browser URLs\n- On macOS\u002FLinux, save the `.kql` file and suggest the VS Code Kusto extension or ADX Web Explorer\n- For graph visualization from IRQL data, see `azure-kusto-graph` and `azure-kusto-irql-graph`\n","# IRQL -- Incident Response Query Language\n\nCompose IRQL function pipelines from selector, extractor, and enricher building blocks. IRQL wraps raw KQL security tables behind intent-revealing, composable functions so analysts (and LLMs) can express hunts without memorizing schemas, cluster locations, or join keys.\n\n## Activation Triggers\n\nUse this skill when the user:\n- Explicitly mentions IRQL, `Get_*`, `Extract_*`, or `Enrich_*` functions\n- Says \"use IRQL\" or \"write an IRQL query\"\n- Requests a composable hunting pipeline using known IRQL selectors\n\nDo **not** activate for generic security queries (e.g. \"find failed logins\") unless the user explicitly asks for IRQL. Route those to `azure-kusto` instead.\n\n**Not a natural-language-to-IRQL converter.** This skill composes IRQL function pipelines and may handle basic natural-language requests that map directly to known selectors and simple filters. For general NL-to-KQL or NL-to-IRQL conversion, use a dedicated query-generation skill (available separately).\n\n## IRQL Function Preflight\n\nBefore generating a pipeline, verify IRQL is available on the target database:\n\n```kql\n.show functions\n| where Name startswith \"Get_\" or Name startswith \"Extract_\" or Name startswith \"Enrich_\"\n| project Name\n```\n\nIf no IRQL functions are found, inform the user that IRQL is not deployed on the target database and suggest using `azure-kusto` for raw KQL queries instead. IRQL functions are a prerequisite -- this skill does not deploy base IRQL selectors.\n\n## What IRQL Is\n\nIRQL is a **function-based dialect on top of KQL**. It provides:\n\n1. **Unified schema** -- disparate security tables project into consistent column names regardless of the underlying data source\n2. **Composability** -- small functions chain via `| invoke` to build complex hunts from simple steps\n3. **Portability** -- the same IRQL pipeline works across different clusters\u002Fdatabases; only the `Get_*` primitives need re-pointing\n\nIRQL is not a separate language. It's KQL functions you invoke. Any valid KQL works alongside IRQL functions.\n\n## Deploying IRQL\n\nIRQL functions are stored KQL functions (`.create-or-alter function`). They must already be deployed to the target database before this skill can generate pipelines.\n\n**Public example cluster** (functions pre-deployed):\n- Cluster: `https:\u002F\u002Fkc7001.eastus.kusto.windows.net`\n- Databases: `ValdyTimes`, `JoJosHospital`\n\nTo port IRQL to a new cluster\u002Fdatabase, create `Get_*` selectors that project your source tables into the unified schema (column names below), then deploy extractors and enrichers. The extractors and enrichers work unchanged as long as the input schema matches.\n\n## Function Catalog\n\n### 1. Selectors -- `Get_*`\n\nReturn projected, schema-unified views of source tables. Use the minimal form by default; use `_All` when extra columns are needed.\n\n| Function | Columns |\n|---|---|\n| `Get_Event_Authentication` | `EnvTime`, `Hostname`, `ClientIp`, `Username`, `Result` |\n| `Get_Event_Authentication_All` | + `Description`, `UserAgent`, `PasswordHash` |\n| `Get_Email` | `EnvTime`, `EmailSender`, `EmailRecipient`, `Subject`, `Url` |\n| `Get_Email_All` | + `ReplyTo`, `Verdict` |\n| `Get_Employees` | `Name`, `ClientIp`, `Email`, `Username`, `Hostname`, `Role` |\n| `Get_Employees_All` | + `HireDate`, `UserAgent`, `Domain` |\n| `Get_Event_FileCreation` | `EnvTime`, `Hostname`, `Filename`, `Path` |\n| `Get_Event_FileCreation_All` | + `Username`, `Sha256`, `ProcessName` |\n| `Get_Event_NetworkInbound` | `EnvTime`, `ClientIp`, `Url` |\n| `Get_Event_NetworkInbound_All` | + `Method`, `UserAgent`, `StatusCode` |\n| `Get_Event_NetworkOutbound` | `EnvTime`, `ClientIp`, `Url` |\n| `Get_Event_NetworkOutbound_All` | + `Method`, `UserAgent` |\n| `Get_Dns_All` | `EnvTime`, `Domain`, `ClientIp` |\n| `Get_Event_Process` | `EnvTime`, `ProcessCommandLine`, `ProcessName`, `Hostname`, `Username` |\n| `Get_Event_Process_All` | + `ParentProcessName`, `ParentProcessHash`, `ProcessHash` |\n| `Get_SecurityAlerts_All` | `EnvTime`, `AlertType`, `Severity`, `Description`, `Indicators` |\n| `Get_Network_Connection_All` | `EnvTime`, `SourceIp`, `SourcePort`, `DestinationIp`, `DestinationPort`, `Protocol`, `Bytes` |\n\n### 2. Extractors -- `Extract_*`\n\nDerive a new column from an existing one. Invoke after a selector.\n\n| Function | Input Column | Adds |\n|---|---|---|\n| `Extract_Email_Sender_Domain(T)` | `EmailSender` | `Domain` |\n| `Extract_Employee_Firstname(T)` | `Name` | `Firstname` |\n| `Extract_Event_Network_Domain(T)` | `Url` | `DomainName` |\n\n### 3. Enrichers -- `Enrich_*`\n\nLeft-join helpers that attach context from a related table.\n\n| Function | Key Column | Enriches With |\n|---|---|---|\n| `Enrich_Event_Authentication_Username(T)` | `Username` | Auth events for user |\n| `Enrich_Ip_Employee(T)` | `ClientIp` | Employee identity from IP |\n| `Enrich_Username_Employee(T)` | `Username` | Employee identity from username |\n| `Enrich_Ip_Domain(T)` | `ClientIp` | DNS domains resolved to IP |\n| `Enrich_Ip_Event_NetworkOutbound(T)` | `ClientIp` | Outbound network from IP |\n| `Enrich_Ip_Network_Connection(T)` | `ClientIp` | Network flows from IP |\n\n### 4. External Enrichment\n\n| Function | Source | Requirement |\n|---|---|---|\n| `Enrich_Sha256_VirusTotal(T)` | VirusTotal file report | API key + callout policy |\n| `Get_CISA_KEV()` \u002F `Enrich_CISA_KEV(T)` | CISA KEV catalog | Callout policy |\n\n## Composition Rules\n\n```\nSelector -> Extract -> Filter -> Enrich -> Summarize\u002FProject\n```\n\n1. **Start with a Selector**: `Get_Event_Authentication`, `Get_Email`, etc.\n2. **Extract** derived fields: `| invoke Extract_Email_Sender_Domain()`\n3. **Filter** to the signal: `| where Result == \"Failed Login\"`\n4. **Enrich** with context: `| invoke Enrich_Username_Employee()`\n5. **Summarize \u002F project** the answer\n\nAlways pipe (`|`) between steps. Extractors and Enrichers use `| invoke FunctionName()`.\n\n## Query Generation Guidelines\n\n- Use the **minimal selector** unless extra columns are needed -> then `_All`\n- Chain extractors before enrichers (extractors add columns enrichers may key on)\n- Place `where` filters as early as possible\n- Use `summarize` for aggregations, `project` for final column selection\n- End with `order by` + `take` to limit output\n\n## Examples\n\nFor additional prompts and worked examples, see [references\u002FEXAMPLES.md](references\u002FEXAMPLES.md).\n\n### Brute-force detection\n```kql\nGet_Event_Authentication\n| where Result == \"Failed Login\"\n| summarize FailedCount = count() by Username\n| where FailedCount > 19\n| invoke Enrich_Username_Employee()\n| project Username, Name, Role, Email, FailedCount\n| order by FailedCount desc\n```\n\n### Phishing triage by recipient seniority\n```kql\nGet_Email\n| invoke Extract_Email_Sender_Domain()\n| project EnvTime, EmailSender, Domain, Username = EmailRecipient, Subject, Url\n| invoke Enrich_Username_Employee()\n| extend Seniority = case(\n    Role has_any (\"CEO\", \"Chief\", \"Director\", \"VP\", \"President\"), 3,\n    Role has_any (\"Manager\", \"Lead\", \"Senior\"), 2,\n    1)\n| summarize\n    TotalEmails = count(),\n    SeniorityScore = sum(Seniority),\n    Recipients = make_set(Name, 50),\n    DistinctRecipients = dcount(Username)\n  by Domain\n| where DistinctRecipients >= 2\n| order by SeniorityScore desc\n| take 20\n```\n\n### Post-exploitation pivot from an indicator\n```kql\nlet victims =\n    Get_Event_FileCreation_All\n    | where Filename has \"\u003CINDICATOR>\"\n    | distinct Hostname;\nGet_Event_Process\n| where Hostname in (victims)\n| where ProcessCommandLine has_any (\"rundll32\", \"regsvr32\", \"powershell\", \"systeminfo\")\n| project EnvTime, Hostname, Username, ProcessName, ProcessCommandLine\n| order by EnvTime asc\n```\n\n### Suspicious outbound traffic enriched with identity\n```kql\nGet_Event_NetworkOutbound\n| invoke Extract_Event_Network_Domain()\n| where DomainName has_any (\"\u003CSUSPICIOUS_DOMAIN_1>\", \"\u003CSUSPICIOUS_DOMAIN_2>\")\n| invoke Enrich_Ip_Employee()\n| project EnvTime, Name, Role, DomainName, Url, ClientIp\n| order by EnvTime desc\n```\n\n### External IP authentication anomaly\n```kql\nGet_Event_Authentication_All\n| where not(ClientIp startswith \"10.\") and not(ClientIp startswith \"192.168.\")\n| summarize\n    Attempts = count(),\n    Failures = countif(Result == \"Failed Login\"),\n    Users = make_set(Username)\n  by ClientIp\n| order by Failures desc\n| take 20\n```\n\n## MCP Tools Used\n\n| Tool | Purpose |\n|------|---------|\n| `kusto_query` | Execute IRQL pipelines against a Kusto database |\n| `kusto_table_schema_get` | Discover available tables and columns |\n| `kusto_cluster_list` | List available ADX clusters |\n| `kusto_database_list` | List databases in a cluster |\n\n## Opening Queries in Kusto Explorer (Windows Only)\n\n> **Optional convenience feature.** The default workflow is to output the KQL in chat and let the user copy it into Kusto Explorer or the VS Code Kusto extension manually. Auto-launch is opt-in only.\n\nAlways output the complete KQL query in the chat response with Step 1 (connect) and Step 2 (query) clearly labeled:\n\n```\n\u002F\u002F Step 1: Connect to your cluster (skip if already connected)\n\u002F\u002F Example: uncomment to connect to the KC7 training cluster\n\u002F\u002F #connect cluster('kc7001.eastus.kusto.windows.net').database('ValdyTimes')\n\u002F\u002F Or replace with your own cluster:\n\u002F\u002F #connect cluster('\u003CYOUR_CLUSTER>').database('\u003CYOUR_DATABASE>')\n\n\u002F\u002F Step 2: Run the query below\n\u003CKQL_QUERY>\n```\n\nIf the user asks to save or open in Kusto Explorer, follow the procedure in [references\u002FKUSTO_EXPLORER_LAUNCH.md](references\u002FKUSTO_EXPLORER_LAUNCH.md). Key rules:\n\n- Use `ask_user` to confirm before writing files or launching executables\n- Display file contents in chat so the user can review before opening\n- Never use shell interpolation or here-strings — write files via `Set-Content`\u002F`Add-Content`\n- Never encode queries into browser URLs\n- On macOS\u002FLinux, save the `.kql` file and suggest the VS Code Kusto extension or ADX Web Explorer\n- For graph visualization from IRQL data, see `azure-kusto-graph` and `azure-kusto-irql-graph`\n",{"name":5,"license":15,"metadata":49,"description":7},{"author":12,"version":50},"1.2.1","main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fazure-kusto-graph-skills\u002Fskills\u002Fazure-kusto-irql",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 azure-kusto-irql",{"tool":67,"command":68},"bunx","bunx skills add microsoft\u002Fskills --skill azure-kusto-irql",{"tool":70,"command":71},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill azure-kusto-irql","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-kusto-graph-skills\u002Fskills\u002Fazure-kusto-irql\u002FSKILL.md",true,[75,81],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002FEXAMPLES.md","REFERENCE","参考文档",2284,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-kusto-graph-skills\u002Fskills\u002Fazure-kusto-irql\u002Freferences\u002FEXAMPLES.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002FKUSTO_EXPLORER_LAUNCH.md",2659,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-kusto-graph-skills\u002Fskills\u002Fazure-kusto-irql\u002Freferences\u002FKUSTO_EXPLORER_LAUNCH.md",[86,94,118,155,182,203],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":93},"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":101,"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",[100],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[102,103,104,105,9,26,106,107,108,109,110,111,112,113,114,29,115,116,117],"skill creator","creator","ai coding agents","coding agents","foundry","microsoft foundry","coding","guide","for","use","Existing","services","new","sdks","with","ai coding",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":134,"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",[124,127,130,133],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":128,"categoryName":129,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":131,"categoryName":132,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,137,138,26,139,140,141,142,143,35,144,145,146,147,29,148,149,150,151,152,153,154],"podcast generation","generation","podcast","frontend","azure openai","realtime","react","python","Audio","model","fastapi backend","python fastapi","fastapi","api","streaming","text","narrative","stack","generate","features",{"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":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",[161],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[163,9,164,165,166,167,168,26,169,170,171,172,173,174,175,176,110,177,64,178,111,179,180,181],"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":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":189,"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",[188],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[190,169,191,192,193,9,142,194,195,144,196,29,197,198,199,109,200,201,110,202,111,116],"mcp builder","builder","llms","sdk","typescript","model context protocol","building mcp servers","node","integrate","Tools","context","fastmcp","mcp sdk",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":221,"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",[209,212,213,218],{"categoryNo":210,"categoryName":211,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":214,"categoryName":215,"taxonomyType":216,"taxonomyTypeDesc":217},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":219,"categoryName":220,"taxonomyType":216,"taxonomyTypeDesc":217},"01JBSEEDCAT000000000000036","内容创作者",[205,26,170,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,110,238,239,240],"analytics","memory","summarize","exploration","parse","project","time","vector","join","log","pipe","datetime","discipline","time series","regex","anomaly","section","tool","geo"]