[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AKZMPBPMXNGPQT3SE33J1":3,"skill-same:01M69AKZMPBPMXNGPQT3SE33J1":89},{"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},"01M69AKZMPBPMXNGPQT3SE33J1","azure-kusto-graph",null,"Build and query Kusto graphs from natural language. Covers transient graphs (make-graph), persistent graph models\u002Fsnapshots, pattern matching (graph-match), shortest paths, connected components, and graph-to-table export. Generates the edges-first thinking: define edges, define node lookups, union, make-graph. WHEN: make-graph, graph-match, graph-shortest-paths, graph-to-table, graph-mark-components, persistent graph, graph model, graph snapshot, build a graph from data, find paths between nodes, pattern matching in graph, connected components, transient graph, Kusto graph, KQL graph.","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-graph\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,9,39,40,41,42,43],"azure kusto graph","azure kusto","azure","graph","snapshot","when","union","make","paths","pattern matching","pattern","query","thinking","snapshots","export","node","model","table","data","components","2026-11-10 10:12:30",false,"---\nname: azure-kusto-graph\ndescription: \"Build and query Kusto graphs from natural language. Covers transient graphs (make-graph), persistent graph models\u002Fsnapshots, pattern matching (graph-match), shortest paths, connected components, and graph-to-table export. Generates the edges-first thinking: define edges, define node lookups, union, make-graph. WHEN: make-graph, graph-match, graph-shortest-paths, graph-to-table, graph-mark-components, persistent graph, graph model, graph snapshot, build a graph from data, find paths between nodes, pattern matching in graph, connected components, transient graph, Kusto graph, KQL graph.\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.2.1\"\n---\n\n# Kusto Graph Semantics\n\nBuild transient and persistent graphs from tabular data using KQL graph operators. This skill translates natural language into the edges-first graph construction pattern and graph query operators.\n\n## Activation Triggers\n\nUse this skill when the user:\n- Wants to build a graph from tabular data (`make-graph`)\n- Asks to find patterns, paths, or relationships in data\n- Mentions `graph-match`, `graph-shortest-paths`, `graph-to-table`, `graph-mark-components`\n- Wants to create a persistent graph model or snapshot\n- Says \"build a graph\", \"find the shortest path\", \"find connected components\", \"show relationships\"\n- Asks about transient vs persistent graphs\n\n**Not a natural-language-to-KQL converter.** The input should generally be a working KQL query whose results the user wants converted to a graph, plus a natural-language description of the desired graph structure. Basic NL source requests are supported only when they map directly to a known table with obvious columns. For general NL-to-KQL conversion, use a dedicated query-generation skill (available separately).\n\n**Complementary skills:**\n- `azure-kusto-irql` -- composable security query primitives that produce the tabular inputs for graphs\n- `azure-kusto-irql-graph` -- IRQL's `Lift_To_Graph` JSON mapping system for richly-typed, icon-decorated graphs in Kusto Explorer\n\n## The Edges-First Approach\n\nThe fundamental pattern for building graphs in Kusto:\n\n```\n1. Define your EDGES       -> src --> dest, with relationship type\u002Fproperties\n2. Define your NODE LOOKUPS -> display names, types, properties for each node ID\n3. Union edge types         -> if you have multiple relationship types\n4. Union node lookups       -> if you have multiple node types\n5. Call make-graph          -> edges | make-graph Source --> Target with nodes on nodeId\n```\n\nThis is how to think in `make-graph`. Edges are the relationships you care about. Nodes are lookup tables that give those IDs a face -- display names, types, properties.\n\n## Graph Operators Reference\n\n### `make-graph` -- Build a graph from tables\n\n```kql\nEdges | make-graph SourceId --> TargetId with Nodes on NodeId\n```\n\n- `Edges`: tabular source where each row is an edge\n- `SourceId --> TargetId`: columns containing source and target node IDs\n- `with Nodes on NodeId`: optional node property table joined by ID\n- Supports multiple node tables: `with Nodes1 on Id1, Nodes2 on Id2`\n- Nodes appearing in edges but missing from the node table get empty properties\n\n### `graph-match` -- Find patterns\n\n```kql\nG | graph-match (a)-[e]->(b) where \u003Cconstraints> project \u003Coutput>\n```\n\nPattern notation:\n\n| Element | Named | Anonymous |\n|---|---|---|\n| Node | `(n)` | `()` |\n| Edge left->right | `-[e]->` | `-->` |\n| Edge right->left | `\u003C-[e]-` | `\u003C--` |\n| Any direction | `-[e]-` | `--` |\n| Variable length | `-[e*1..5]->` | `-[*1..5]->` |\n\nMulti-hop patterns: `(a)-[e1]->(b)-[e2]->(c)`\nStar patterns: `(a)--(center)--(b), (c)--(center)--(d)`\nCycles control: `cycles = all | none | unique_edges` (default: `unique_edges`)\n\n### `graph-shortest-paths` -- Find shortest paths\n\n```kql\nG | graph-shortest-paths (start)-[e*1..20]->(end)\n      where start.name == \"Alice\" and end.name == \"Server01\"\n      project Path = e, Length = array_length(e)\n```\n\n- Requires at least one variable-length edge\n- `output = any` (default, one path per pair) or `output = all` (all equal-length shortest paths)\n- Variable-length edge properties returned as dynamic arrays\n\n### `graph-to-table` -- Export graph to tables\n\n```kql\nG | graph-to-table nodes                                     \u002F\u002F export nodes\nG | graph-to-table edges                                     \u002F\u002F export edges\nG | graph-to-table nodes as N, edges as E                    \u002F\u002F export both\nG | graph-to-table nodes with_node_id=Id                     \u002F\u002F include node hash ID\nG | graph-to-table edges with_source_id=Src with_target_id=Tgt  \u002F\u002F include edge endpoint IDs\n```\n\n### `graph-mark-components` -- Find connected components\n\n```kql\nG | graph-mark-components with_component_id=ComponentId\n  | graph-to-table nodes\n  | summarize Members = make_list(name) by ComponentId\n```\n\nAssigns a `ComponentId` to each node. Nodes in the same connected component share the same ID.\n\n### `graph()` function -- Query persistent graphs\n\n```kql\ngraph(\"MyGraphModel\")                              \u002F\u002F latest snapshot\ngraph(\"MyGraphModel\", \"Snapshot_2025_01\")           \u002F\u002F specific snapshot\ngraph(\"MyGraphModel\", true)                         \u002F\u002F transient from model definition\n```\n\n## Transient Graphs\n\nCreated dynamically during query execution. No setup required. Ideal for ad-hoc analysis, exploration, and prototyping.\n\n### Template: Basic two-entity graph\n\n```kql\n\u002F\u002F 1. Define edges\nlet edges = \u003CSourceTable>\n    | summarize \u003Caggregations> by SourceCol, TargetCol;\n\u002F\u002F 2. Define node lookups\nlet source_nodes = edges\n    | distinct SourceCol\n    | project nodeId = SourceCol, label = SourceCol, nodeType = \"\u003CSourceType>\";\nlet target_nodes = edges\n    | distinct TargetCol\n    | project nodeId = TargetCol, label = TargetCol, nodeType = \"\u003CTargetType>\";\nlet all_nodes = union source_nodes, target_nodes;\n\u002F\u002F 3. Build and query the graph\nedges\n| make-graph SourceCol --> TargetCol with all_nodes on nodeId\n| graph-match (s)-[e]->(t)\n    where \u003Cconstraints>\n    project Source = s.label, Target = t.label, \u003Cedge properties>\n```\n\n### Template: Multi-relationship graph\n\n```kql\n\u002F\u002F Multiple edge types -> union them with a common schema\nlet auth_edges = AuthEvents\n    | project Source = username, Target = hostname, edgeType = \"authenticates\", ts = timestamp;\nlet net_edges = NetworkEvents\n    | project Source = src_ip, Target = url, edgeType = \"connects\", ts = timestamp;\nlet all_edges = union auth_edges, net_edges;\n\u002F\u002F Node lookups from all sources\nlet user_nodes = Employees | project nodeId = username, label = name, nodeType = \"User\";\nlet host_nodes = AuthEvents | distinct hostname | project nodeId = hostname, label = hostname, nodeType = \"Host\";\nlet all_nodes = union user_nodes, host_nodes;\nall_edges\n| make-graph Source --> Target with all_nodes on nodeId\n```\n\n## Persistent Graphs\n\nFor large-scale, reusable graphs. Stored in database metadata. Support snapshots for historical comparison.\n\n> **Safety:** Creating or altering graph models and snapshots modifies the database. Always show the exact command and confirm with the user before executing `.create-or-alter graph_model` or `.make graph_snapshot`.\n\n### Step 1: Create a graph model\n\n```kql\n.create-or-alter graph_model SecurityGraph\n{\n  \"Schema\": {\n    \"Nodes\": {\n      \"User\": {\"name\": \"string\", \"role\": \"string\"},\n      \"Host\": {\"hostname\": \"string\"},\n      \"IP\":   {\"ip\": \"string\"}\n    },\n    \"Edges\": {\n      \"AuthenticatesTo\": {\"timestamp\": \"datetime\", \"result\": \"string\"},\n      \"ConnectsFrom\":    {\"timestamp\": \"datetime\"}\n    }\n  },\n  \"Definition\": {\n    \"Steps\": [\n      {\n        \"Kind\": \"AddNodes\",\n        \"Query\": \"Employees | project name, role\",\n        \"NodeIdColumn\": \"name\",\n        \"Labels\": [\"User\"]\n      },\n      {\n        \"Kind\": \"AddNodes\",\n        \"Query\": \"AuthenticationEvents | distinct hostname | project hostname\",\n        \"NodeIdColumn\": \"hostname\",\n        \"Labels\": [\"Host\"]\n      },\n      {\n        \"Kind\": \"AddEdges\",\n        \"Query\": \"AuthenticationEvents | project username, hostname, timestamp, result\",\n        \"SourceColumn\": \"username\",\n        \"TargetColumn\": \"hostname\",\n        \"Labels\": [\"AuthenticatesTo\"]\n      }\n    ]\n  }\n}\n```\n\n### Step 2: Create a snapshot\n\n```kql\n.make graph_snapshot SecurityGraph Snapshot_2025_07\n```\n\n### Step 3: Query the snapshot\n\n```kql\ngraph(\"SecurityGraph\")\n| graph-match (user)-[auth]->(host)\n    where user.role == \"Admin\" and auth.result == \"Failed Login\"\n    project User = user.name, Host = host.hostname, Time = auth.timestamp\n```\n\n### Management commands\n\n> **Safety:** All control commands below modify or delete database objects. Never execute `.drop`, `.create-or-alter graph_model`, or `.make graph_snapshot` automatically. Always show the exact command, cluster, database, and affected object, then require explicit user confirmation before execution.\n\n```kql\n.show graph_models                        \u002F\u002F list all models\n.show graph_model SecurityGraph           \u002F\u002F show model details\n.show graph_snapshots SecurityGraph       \u002F\u002F list snapshots\n.drop graph_snapshot SecurityGraph Snapshot_2025_07  \u002F\u002F delete a snapshot (CONFIRM FIRST)\n.drop graph_model SecurityGraph           \u002F\u002F delete model and all snapshots (CONFIRM FIRST)\n```\n\n## Transient vs Persistent: When to Use Which\n\n| Factor | Transient (`make-graph`) | Persistent (`graph()`) |\n|---|---|---|\n| Setup | None -- inline in query | Create model + snapshot |\n| Lifetime | Query execution only | Stored in database metadata |\n| Data freshness | Always current | Snapshot at creation time |\n| Scale | Limited by query memory | Enterprise-scale |\n| Reuse | Rebuilt every query | Shared across users\u002Fqueries |\n| Best for | Ad-hoc hunts, prototyping | Production workflows, dashboards |\n\n## Security & Threat Hunting Examples\n\n### Authentication graph: who logged into what from where\n\n```kql\nlet auth_edges = AuthenticationEvents\n    | summarize\n        logins = count(),\n        fails = countif(result == \"Failed Login\")\n      by src_ip, username, hostname;\nlet ip_nodes = auth_edges | distinct src_ip\n    | project nodeId = src_ip, label = src_ip, nodeType = \"IP\";\nlet user_nodes = auth_edges | distinct username\n    | project nodeId = username, label = username, nodeType = \"User\";\nlet host_nodes = auth_edges | distinct hostname\n    | project nodeId = hostname, label = hostname, nodeType = \"Host\";\nlet all_nodes = union ip_nodes, user_nodes, host_nodes;\n\u002F\u002F IP -> User edges\nlet ip_user = auth_edges\n    | project Source = src_ip, Target = username, logins, fails;\n\u002F\u002F User -> Host edges\nlet user_host = auth_edges\n    | project Source = username, Target = hostname, logins, fails;\nunion ip_user, user_host\n| make-graph Source --> Target with all_nodes on nodeId\n| graph-match (ip)-[e1]->(user)-[e2]->(host)\n    where e2.fails > 20\n    project\n        IP = ip.label,\n        User = user.label,\n        Host = host.label,\n        Failures = e2.fails\n| order by Failures desc\n```\n\n### Lateral movement detection: users sharing compromised hosts\n\n```kql\n\u002F\u002F Pattern: (user1)-[auth1]->(host)\u003C-[auth2]-(user2)\n\u002F\u002F Two users both failing on the same host = possible credential spray\nlet edges = AuthenticationEvents\n    | summarize fails = countif(result == \"Failed Login\"), logins = count()\n      by username, hostname;\nlet nodes = union\n    (edges | distinct username | project nodeId = username, nodeType = \"User\"),\n    (edges | distinct hostname | project nodeId = hostname, nodeType = \"Host\");\nedges\n| make-graph username --> hostname with nodes on nodeId\n| graph-match (u1)-[e1]->(h)\u003C-[e2]-(u2)\n    where u1.nodeId != u2.nodeId and e1.fails > 10 and e2.fails > 10\n    project\n        User1 = u1.nodeId, User2 = u2.nodeId,\n        SharedHost = h.nodeId,\n        User1Fails = e1.fails, User2Fails = e2.fails\n| distinct User1, SharedHost, User2, User1Fails, User2Fails\n| order by User1Fails + User2Fails desc\n```\n\n### Shortest attack path\n\n```kql\nlet edges = SecurityEvents\n    | project Source = source_entity, Target = target_entity, action, timestamp;\nlet nodes = union\n    (edges | distinct Source | project nodeId = Source),\n    (edges | distinct Target | project nodeId = Target);\nedges\n| make-graph Source --> Target with nodes on nodeId\n| graph-shortest-paths (start)-[e*1..10]->(end)\n    where start.nodeId == \"ExternalIP_1.2.3.4\" and end.nodeId == \"DatabaseServer\"\n    project\n        PathLength = array_length(e),\n        Actions = e.action,\n        Hops = e.Target\n```\n\n### Connected components: find isolated clusters\n\n```kql\nlet edges = NetworkFlows\n    | project Source = src_ip, Target = dst_ip;\nlet nodes = union\n    (edges | distinct Source | project nodeId = Source),\n    (edges | distinct Target | project nodeId = Target);\nedges\n| make-graph Source --> Target with nodes on nodeId\n| graph-mark-components with_component_id = ComponentId\n| graph-to-table nodes\n| summarize Members = make_list(nodeId), Size = count() by ComponentId\n| order by Size desc\n```\n\n### Visualize in Kusto Explorer\n\nEnd a query at `make-graph` (without piping to `graph-match`) to trigger Kusto Explorer's interactive graph visualization window:\n\n```kql\nedges\n| make-graph Source --> Target with all_nodes on nodeId\n\u002F\u002F \u003C- stop here. Kusto Explorer renders the graph visually.\n```\n\nTo flatten back to a table for dashboards or export, pipe through `graph-match | project` or `graph-to-table`.\n\n## Using with IRQL\n\nWhen working with security data, consider using IRQL selectors (`Get_*`) from the `azure-kusto-irql` skill as the data source. IRQL gives you a unified schema without memorizing raw table names or column mappings. For rich visualization with icons and node folding, the `azure-kusto-irql-graph` skill's `Lift_To_Graph` is the faster path.\n\n| Approach | Best For |\n|---|---|\n| Raw `make-graph` (this skill) | Full control, persistent models, shortest paths, connected components, custom schemas |\n| `Lift_To_Graph` (`azure-kusto-irql-graph`) | Quick icon-decorated visualization in Kusto Explorer, node folding |\n| IRQL `Get_*` -> `make-graph` | IRQL's unified schema as input, then raw graph operators for analysis |\n| IRQL `Get_*` -> `Lift_To_Graph` -> `Graph_Render_View` | Fastest path from question to visual graph |\n\n> **Note:** `Lift_To_Graph`, `Graph_Render_View`, and `Graph_Fold_By_Property` are stored functions, not built-in operators. They are pre-deployed on the kc7001 example cluster but may need deployment on other clusters. See `azure-kusto-irql-graph\u002Freferences\u002FDEPLOY_IRQL_FUNCTIONS.md` for function definitions and deployment instructions.\n\n### Example: IRQL selectors -> make-graph -> shortest path\n\nIRQL handles the data retrieval; `make-graph` handles the graph analysis. This finds the shortest path from an external IP to a mail server through auth events:\n\n```kql\n\u002F\u002F IRQL provides unified columns (ClientIp, Hostname, Username, Result)\nlet auth = Get_Event_Authentication_All\n    | where Result == \"Failed Login\";\nlet edges = auth\n    | summarize Failures = count() by ClientIp, Hostname;\nlet nodes = union\n    (edges | distinct ClientIp | project nodeId = ClientIp, nodeType = \"IP\"),\n    (edges | distinct Hostname | project nodeId = Hostname, nodeType = \"Host\");\nedges\n| make-graph ClientIp --> Hostname with nodes on nodeId\n| graph-shortest-paths (src)-[e*1..5]->(dest)\n    where src.nodeType == \"IP\" and dest.nodeId == \"MAIL-SERVER01\"\n    project\n        SourceIP = src.nodeId,\n        PathLength = array_length(e),\n        Hops = e.Hostname\n```\n\n### Example: IRQL selectors -> make-graph -> connected components\n\nFind clusters of IPs and domains that are interconnected -- potential C2 infrastructure:\n\n```kql\nlet dns = Get_Dns_All;\nlet edges = dns | project Source = ClientIp, Target = Domain;\nlet nodes = union\n    (edges | distinct Source | project nodeId = Source, nodeType = \"IP\"),\n    (edges | distinct Target | project nodeId = Target, nodeType = \"Domain\");\nedges\n| make-graph Source --> Target with nodes on nodeId\n| graph-mark-components with_component_id = ComponentId\n| graph-to-table nodes\n| summarize\n    IPs = make_set_if(nodeId, nodeType == \"IP\"),\n    Domains = make_set_if(nodeId, nodeType == \"Domain\"),\n    Size = count()\n  by ComponentId\n| where Size > 3\n| order by Size desc\n```\n\n### Example: IRQL + make-graph integration\n\nSee [references\u002FEXAMPLES.md](references\u002FEXAMPLES.md) for multi-source investigation graphs combining IRQL selectors with `make-graph`, and `Lift_To_Graph` visual graph examples.\n\n## Practical Usage Scenarios\n\nSee [references\u002FSCENARIOS.md](references\u002FSCENARIOS.md) for full worked examples including:\n- Reachability analysis (shortest paths to critical assets)\n- Network segmentation validation (connected components)\n- Blast radius of compromised accounts (variable-length path matching)\n- Persistent graph models for SOC teams (graph_model + snapshots)\n\n## MCP Tools Used\n\n| Tool | Purpose |\n|------|---------|\n| `kusto_query` | Execute KQL queries including `make-graph`, `graph-match`, and management commands |\n| `kusto_table_schema_get` | Discover table columns before building edge\u002Fnode projections |\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\n### Default: Output KQL in Chat\n\nAlways output the complete KQL 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 ending at make-graph>\n```\n\nThen immediately below, output an **ADX Web Explorer version** that appends `| graph-to-table nodes as N, edges as E` since ADX Web Explorer cannot render `make-graph` directly:\n\n```\n\u002F\u002F ADX Web Explorer version (tabular output):\n\u003CSAME_QUERY>\n| graph-to-table nodes as N, edges as E\n```\n\nThis ensures the output works in both Kusto Explorer (graph visualization) and ADX Web Explorer (tabular results) without the user having to modify anything.\n\n### Optional: Save and Launch\n\nIf the user asks to save or open the query in Kusto Explorer, follow the procedure in [references\u002FKUSTO_EXPLORER_LAUNCH.md](references\u002FKUSTO_EXPLORER_LAUNCH.md). Key rules:\n\n- **Always** use `ask_user` to confirm before writing files or launching executables\n- **Always** display the 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\nFor `make-graph` visualization (the graph window), the query must **end at `make-graph`** — do not pipe to `graph-match`. Kusto Explorer only opens the graph visualization window when the output is a graph object, not a table.\n","# Kusto Graph Semantics\n\nBuild transient and persistent graphs from tabular data using KQL graph operators. This skill translates natural language into the edges-first graph construction pattern and graph query operators.\n\n## Activation Triggers\n\nUse this skill when the user:\n- Wants to build a graph from tabular data (`make-graph`)\n- Asks to find patterns, paths, or relationships in data\n- Mentions `graph-match`, `graph-shortest-paths`, `graph-to-table`, `graph-mark-components`\n- Wants to create a persistent graph model or snapshot\n- Says \"build a graph\", \"find the shortest path\", \"find connected components\", \"show relationships\"\n- Asks about transient vs persistent graphs\n\n**Not a natural-language-to-KQL converter.** The input should generally be a working KQL query whose results the user wants converted to a graph, plus a natural-language description of the desired graph structure. Basic NL source requests are supported only when they map directly to a known table with obvious columns. For general NL-to-KQL conversion, use a dedicated query-generation skill (available separately).\n\n**Complementary skills:**\n- `azure-kusto-irql` -- composable security query primitives that produce the tabular inputs for graphs\n- `azure-kusto-irql-graph` -- IRQL's `Lift_To_Graph` JSON mapping system for richly-typed, icon-decorated graphs in Kusto Explorer\n\n## The Edges-First Approach\n\nThe fundamental pattern for building graphs in Kusto:\n\n```\n1. Define your EDGES       -> src --> dest, with relationship type\u002Fproperties\n2. Define your NODE LOOKUPS -> display names, types, properties for each node ID\n3. Union edge types         -> if you have multiple relationship types\n4. Union node lookups       -> if you have multiple node types\n5. Call make-graph          -> edges | make-graph Source --> Target with nodes on nodeId\n```\n\nThis is how to think in `make-graph`. Edges are the relationships you care about. Nodes are lookup tables that give those IDs a face -- display names, types, properties.\n\n## Graph Operators Reference\n\n### `make-graph` -- Build a graph from tables\n\n```kql\nEdges | make-graph SourceId --> TargetId with Nodes on NodeId\n```\n\n- `Edges`: tabular source where each row is an edge\n- `SourceId --> TargetId`: columns containing source and target node IDs\n- `with Nodes on NodeId`: optional node property table joined by ID\n- Supports multiple node tables: `with Nodes1 on Id1, Nodes2 on Id2`\n- Nodes appearing in edges but missing from the node table get empty properties\n\n### `graph-match` -- Find patterns\n\n```kql\nG | graph-match (a)-[e]->(b) where \u003Cconstraints> project \u003Coutput>\n```\n\nPattern notation:\n\n| Element | Named | Anonymous |\n|---|---|---|\n| Node | `(n)` | `()` |\n| Edge left->right | `-[e]->` | `-->` |\n| Edge right->left | `\u003C-[e]-` | `\u003C--` |\n| Any direction | `-[e]-` | `--` |\n| Variable length | `-[e*1..5]->` | `-[*1..5]->` |\n\nMulti-hop patterns: `(a)-[e1]->(b)-[e2]->(c)`\nStar patterns: `(a)--(center)--(b), (c)--(center)--(d)`\nCycles control: `cycles = all | none | unique_edges` (default: `unique_edges`)\n\n### `graph-shortest-paths` -- Find shortest paths\n\n```kql\nG | graph-shortest-paths (start)-[e*1..20]->(end)\n      where start.name == \"Alice\" and end.name == \"Server01\"\n      project Path = e, Length = array_length(e)\n```\n\n- Requires at least one variable-length edge\n- `output = any` (default, one path per pair) or `output = all` (all equal-length shortest paths)\n- Variable-length edge properties returned as dynamic arrays\n\n### `graph-to-table` -- Export graph to tables\n\n```kql\nG | graph-to-table nodes                                     \u002F\u002F export nodes\nG | graph-to-table edges                                     \u002F\u002F export edges\nG | graph-to-table nodes as N, edges as E                    \u002F\u002F export both\nG | graph-to-table nodes with_node_id=Id                     \u002F\u002F include node hash ID\nG | graph-to-table edges with_source_id=Src with_target_id=Tgt  \u002F\u002F include edge endpoint IDs\n```\n\n### `graph-mark-components` -- Find connected components\n\n```kql\nG | graph-mark-components with_component_id=ComponentId\n  | graph-to-table nodes\n  | summarize Members = make_list(name) by ComponentId\n```\n\nAssigns a `ComponentId` to each node. Nodes in the same connected component share the same ID.\n\n### `graph()` function -- Query persistent graphs\n\n```kql\ngraph(\"MyGraphModel\")                              \u002F\u002F latest snapshot\ngraph(\"MyGraphModel\", \"Snapshot_2025_01\")           \u002F\u002F specific snapshot\ngraph(\"MyGraphModel\", true)                         \u002F\u002F transient from model definition\n```\n\n## Transient Graphs\n\nCreated dynamically during query execution. No setup required. Ideal for ad-hoc analysis, exploration, and prototyping.\n\n### Template: Basic two-entity graph\n\n```kql\n\u002F\u002F 1. Define edges\nlet edges = \u003CSourceTable>\n    | summarize \u003Caggregations> by SourceCol, TargetCol;\n\u002F\u002F 2. Define node lookups\nlet source_nodes = edges\n    | distinct SourceCol\n    | project nodeId = SourceCol, label = SourceCol, nodeType = \"\u003CSourceType>\";\nlet target_nodes = edges\n    | distinct TargetCol\n    | project nodeId = TargetCol, label = TargetCol, nodeType = \"\u003CTargetType>\";\nlet all_nodes = union source_nodes, target_nodes;\n\u002F\u002F 3. Build and query the graph\nedges\n| make-graph SourceCol --> TargetCol with all_nodes on nodeId\n| graph-match (s)-[e]->(t)\n    where \u003Cconstraints>\n    project Source = s.label, Target = t.label, \u003Cedge properties>\n```\n\n### Template: Multi-relationship graph\n\n```kql\n\u002F\u002F Multiple edge types -> union them with a common schema\nlet auth_edges = AuthEvents\n    | project Source = username, Target = hostname, edgeType = \"authenticates\", ts = timestamp;\nlet net_edges = NetworkEvents\n    | project Source = src_ip, Target = url, edgeType = \"connects\", ts = timestamp;\nlet all_edges = union auth_edges, net_edges;\n\u002F\u002F Node lookups from all sources\nlet user_nodes = Employees | project nodeId = username, label = name, nodeType = \"User\";\nlet host_nodes = AuthEvents | distinct hostname | project nodeId = hostname, label = hostname, nodeType = \"Host\";\nlet all_nodes = union user_nodes, host_nodes;\nall_edges\n| make-graph Source --> Target with all_nodes on nodeId\n```\n\n## Persistent Graphs\n\nFor large-scale, reusable graphs. Stored in database metadata. Support snapshots for historical comparison.\n\n> **Safety:** Creating or altering graph models and snapshots modifies the database. Always show the exact command and confirm with the user before executing `.create-or-alter graph_model` or `.make graph_snapshot`.\n\n### Step 1: Create a graph model\n\n```kql\n.create-or-alter graph_model SecurityGraph\n{\n  \"Schema\": {\n    \"Nodes\": {\n      \"User\": {\"name\": \"string\", \"role\": \"string\"},\n      \"Host\": {\"hostname\": \"string\"},\n      \"IP\":   {\"ip\": \"string\"}\n    },\n    \"Edges\": {\n      \"AuthenticatesTo\": {\"timestamp\": \"datetime\", \"result\": \"string\"},\n      \"ConnectsFrom\":    {\"timestamp\": \"datetime\"}\n    }\n  },\n  \"Definition\": {\n    \"Steps\": [\n      {\n        \"Kind\": \"AddNodes\",\n        \"Query\": \"Employees | project name, role\",\n        \"NodeIdColumn\": \"name\",\n        \"Labels\": [\"User\"]\n      },\n      {\n        \"Kind\": \"AddNodes\",\n        \"Query\": \"AuthenticationEvents | distinct hostname | project hostname\",\n        \"NodeIdColumn\": \"hostname\",\n        \"Labels\": [\"Host\"]\n      },\n      {\n        \"Kind\": \"AddEdges\",\n        \"Query\": \"AuthenticationEvents | project username, hostname, timestamp, result\",\n        \"SourceColumn\": \"username\",\n        \"TargetColumn\": \"hostname\",\n        \"Labels\": [\"AuthenticatesTo\"]\n      }\n    ]\n  }\n}\n```\n\n### Step 2: Create a snapshot\n\n```kql\n.make graph_snapshot SecurityGraph Snapshot_2025_07\n```\n\n### Step 3: Query the snapshot\n\n```kql\ngraph(\"SecurityGraph\")\n| graph-match (user)-[auth]->(host)\n    where user.role == \"Admin\" and auth.result == \"Failed Login\"\n    project User = user.name, Host = host.hostname, Time = auth.timestamp\n```\n\n### Management commands\n\n> **Safety:** All control commands below modify or delete database objects. Never execute `.drop`, `.create-or-alter graph_model`, or `.make graph_snapshot` automatically. Always show the exact command, cluster, database, and affected object, then require explicit user confirmation before execution.\n\n```kql\n.show graph_models                        \u002F\u002F list all models\n.show graph_model SecurityGraph           \u002F\u002F show model details\n.show graph_snapshots SecurityGraph       \u002F\u002F list snapshots\n.drop graph_snapshot SecurityGraph Snapshot_2025_07  \u002F\u002F delete a snapshot (CONFIRM FIRST)\n.drop graph_model SecurityGraph           \u002F\u002F delete model and all snapshots (CONFIRM FIRST)\n```\n\n## Transient vs Persistent: When to Use Which\n\n| Factor | Transient (`make-graph`) | Persistent (`graph()`) |\n|---|---|---|\n| Setup | None -- inline in query | Create model + snapshot |\n| Lifetime | Query execution only | Stored in database metadata |\n| Data freshness | Always current | Snapshot at creation time |\n| Scale | Limited by query memory | Enterprise-scale |\n| Reuse | Rebuilt every query | Shared across users\u002Fqueries |\n| Best for | Ad-hoc hunts, prototyping | Production workflows, dashboards |\n\n## Security & Threat Hunting Examples\n\n### Authentication graph: who logged into what from where\n\n```kql\nlet auth_edges = AuthenticationEvents\n    | summarize\n        logins = count(),\n        fails = countif(result == \"Failed Login\")\n      by src_ip, username, hostname;\nlet ip_nodes = auth_edges | distinct src_ip\n    | project nodeId = src_ip, label = src_ip, nodeType = \"IP\";\nlet user_nodes = auth_edges | distinct username\n    | project nodeId = username, label = username, nodeType = \"User\";\nlet host_nodes = auth_edges | distinct hostname\n    | project nodeId = hostname, label = hostname, nodeType = \"Host\";\nlet all_nodes = union ip_nodes, user_nodes, host_nodes;\n\u002F\u002F IP -> User edges\nlet ip_user = auth_edges\n    | project Source = src_ip, Target = username, logins, fails;\n\u002F\u002F User -> Host edges\nlet user_host = auth_edges\n    | project Source = username, Target = hostname, logins, fails;\nunion ip_user, user_host\n| make-graph Source --> Target with all_nodes on nodeId\n| graph-match (ip)-[e1]->(user)-[e2]->(host)\n    where e2.fails > 20\n    project\n        IP = ip.label,\n        User = user.label,\n        Host = host.label,\n        Failures = e2.fails\n| order by Failures desc\n```\n\n### Lateral movement detection: users sharing compromised hosts\n\n```kql\n\u002F\u002F Pattern: (user1)-[auth1]->(host)\u003C-[auth2]-(user2)\n\u002F\u002F Two users both failing on the same host = possible credential spray\nlet edges = AuthenticationEvents\n    | summarize fails = countif(result == \"Failed Login\"), logins = count()\n      by username, hostname;\nlet nodes = union\n    (edges | distinct username | project nodeId = username, nodeType = \"User\"),\n    (edges | distinct hostname | project nodeId = hostname, nodeType = \"Host\");\nedges\n| make-graph username --> hostname with nodes on nodeId\n| graph-match (u1)-[e1]->(h)\u003C-[e2]-(u2)\n    where u1.nodeId != u2.nodeId and e1.fails > 10 and e2.fails > 10\n    project\n        User1 = u1.nodeId, User2 = u2.nodeId,\n        SharedHost = h.nodeId,\n        User1Fails = e1.fails, User2Fails = e2.fails\n| distinct User1, SharedHost, User2, User1Fails, User2Fails\n| order by User1Fails + User2Fails desc\n```\n\n### Shortest attack path\n\n```kql\nlet edges = SecurityEvents\n    | project Source = source_entity, Target = target_entity, action, timestamp;\nlet nodes = union\n    (edges | distinct Source | project nodeId = Source),\n    (edges | distinct Target | project nodeId = Target);\nedges\n| make-graph Source --> Target with nodes on nodeId\n| graph-shortest-paths (start)-[e*1..10]->(end)\n    where start.nodeId == \"ExternalIP_1.2.3.4\" and end.nodeId == \"DatabaseServer\"\n    project\n        PathLength = array_length(e),\n        Actions = e.action,\n        Hops = e.Target\n```\n\n### Connected components: find isolated clusters\n\n```kql\nlet edges = NetworkFlows\n    | project Source = src_ip, Target = dst_ip;\nlet nodes = union\n    (edges | distinct Source | project nodeId = Source),\n    (edges | distinct Target | project nodeId = Target);\nedges\n| make-graph Source --> Target with nodes on nodeId\n| graph-mark-components with_component_id = ComponentId\n| graph-to-table nodes\n| summarize Members = make_list(nodeId), Size = count() by ComponentId\n| order by Size desc\n```\n\n### Visualize in Kusto Explorer\n\nEnd a query at `make-graph` (without piping to `graph-match`) to trigger Kusto Explorer's interactive graph visualization window:\n\n```kql\nedges\n| make-graph Source --> Target with all_nodes on nodeId\n\u002F\u002F \u003C- stop here. Kusto Explorer renders the graph visually.\n```\n\nTo flatten back to a table for dashboards or export, pipe through `graph-match | project` or `graph-to-table`.\n\n## Using with IRQL\n\nWhen working with security data, consider using IRQL selectors (`Get_*`) from the `azure-kusto-irql` skill as the data source. IRQL gives you a unified schema without memorizing raw table names or column mappings. For rich visualization with icons and node folding, the `azure-kusto-irql-graph` skill's `Lift_To_Graph` is the faster path.\n\n| Approach | Best For |\n|---|---|\n| Raw `make-graph` (this skill) | Full control, persistent models, shortest paths, connected components, custom schemas |\n| `Lift_To_Graph` (`azure-kusto-irql-graph`) | Quick icon-decorated visualization in Kusto Explorer, node folding |\n| IRQL `Get_*` -> `make-graph` | IRQL's unified schema as input, then raw graph operators for analysis |\n| IRQL `Get_*` -> `Lift_To_Graph` -> `Graph_Render_View` | Fastest path from question to visual graph |\n\n> **Note:** `Lift_To_Graph`, `Graph_Render_View`, and `Graph_Fold_By_Property` are stored functions, not built-in operators. They are pre-deployed on the kc7001 example cluster but may need deployment on other clusters. See `azure-kusto-irql-graph\u002Freferences\u002FDEPLOY_IRQL_FUNCTIONS.md` for function definitions and deployment instructions.\n\n### Example: IRQL selectors -> make-graph -> shortest path\n\nIRQL handles the data retrieval; `make-graph` handles the graph analysis. This finds the shortest path from an external IP to a mail server through auth events:\n\n```kql\n\u002F\u002F IRQL provides unified columns (ClientIp, Hostname, Username, Result)\nlet auth = Get_Event_Authentication_All\n    | where Result == \"Failed Login\";\nlet edges = auth\n    | summarize Failures = count() by ClientIp, Hostname;\nlet nodes = union\n    (edges | distinct ClientIp | project nodeId = ClientIp, nodeType = \"IP\"),\n    (edges | distinct Hostname | project nodeId = Hostname, nodeType = \"Host\");\nedges\n| make-graph ClientIp --> Hostname with nodes on nodeId\n| graph-shortest-paths (src)-[e*1..5]->(dest)\n    where src.nodeType == \"IP\" and dest.nodeId == \"MAIL-SERVER01\"\n    project\n        SourceIP = src.nodeId,\n        PathLength = array_length(e),\n        Hops = e.Hostname\n```\n\n### Example: IRQL selectors -> make-graph -> connected components\n\nFind clusters of IPs and domains that are interconnected -- potential C2 infrastructure:\n\n```kql\nlet dns = Get_Dns_All;\nlet edges = dns | project Source = ClientIp, Target = Domain;\nlet nodes = union\n    (edges | distinct Source | project nodeId = Source, nodeType = \"IP\"),\n    (edges | distinct Target | project nodeId = Target, nodeType = \"Domain\");\nedges\n| make-graph Source --> Target with nodes on nodeId\n| graph-mark-components with_component_id = ComponentId\n| graph-to-table nodes\n| summarize\n    IPs = make_set_if(nodeId, nodeType == \"IP\"),\n    Domains = make_set_if(nodeId, nodeType == \"Domain\"),\n    Size = count()\n  by ComponentId\n| where Size > 3\n| order by Size desc\n```\n\n### Example: IRQL + make-graph integration\n\nSee [references\u002FEXAMPLES.md](references\u002FEXAMPLES.md) for multi-source investigation graphs combining IRQL selectors with `make-graph`, and `Lift_To_Graph` visual graph examples.\n\n## Practical Usage Scenarios\n\nSee [references\u002FSCENARIOS.md](references\u002FSCENARIOS.md) for full worked examples including:\n- Reachability analysis (shortest paths to critical assets)\n- Network segmentation validation (connected components)\n- Blast radius of compromised accounts (variable-length path matching)\n- Persistent graph models for SOC teams (graph_model + snapshots)\n\n## MCP Tools Used\n\n| Tool | Purpose |\n|------|---------|\n| `kusto_query` | Execute KQL queries including `make-graph`, `graph-match`, and management commands |\n| `kusto_table_schema_get` | Discover table columns before building edge\u002Fnode projections |\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\n### Default: Output KQL in Chat\n\nAlways output the complete KQL 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 ending at make-graph>\n```\n\nThen immediately below, output an **ADX Web Explorer version** that appends `| graph-to-table nodes as N, edges as E` since ADX Web Explorer cannot render `make-graph` directly:\n\n```\n\u002F\u002F ADX Web Explorer version (tabular output):\n\u003CSAME_QUERY>\n| graph-to-table nodes as N, edges as E\n```\n\nThis ensures the output works in both Kusto Explorer (graph visualization) and ADX Web Explorer (tabular results) without the user having to modify anything.\n\n### Optional: Save and Launch\n\nIf the user asks to save or open the query in Kusto Explorer, follow the procedure in [references\u002FKUSTO_EXPLORER_LAUNCH.md](references\u002FKUSTO_EXPLORER_LAUNCH.md). Key rules:\n\n- **Always** use `ask_user` to confirm before writing files or launching executables\n- **Always** display the 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\nFor `make-graph` visualization (the graph window), the query must **end at `make-graph`** — do not pipe to `graph-match`. Kusto Explorer only opens the graph visualization window when the output is a graph object, not a table.\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-graph",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-graph",{"tool":67,"command":68},"bunx","bunx skills add microsoft\u002Fskills --skill azure-kusto-graph",{"tool":70,"command":71},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill azure-kusto-graph","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-graph\u002FSKILL.md",true,[75,81,85],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002FEXAMPLES.md","REFERENCE","参考文档",2975,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-kusto-graph-skills\u002Fskills\u002Fazure-kusto-graph\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-graph\u002Freferences\u002FKUSTO_EXPLORER_LAUNCH.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002FSCENARIOS.md",3853,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-kusto-graph-skills\u002Fskills\u002Fazure-kusto-graph\u002Freferences\u002FSCENARIOS.md",[90,98,122,159,186,206],{"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":96,"publishedAt":97},"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"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",[104],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[106,107,108,109,9,26,110,111,112,113,114,115,116,117,118,29,119,120,121],"skill creator","creator","ai coding agents","coding agents","foundry","microsoft foundry","coding","guide","for","use","Existing","services","new","sdks","with","ai coding",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":138,"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",[128,131,134,137],{"categoryNo":129,"categoryName":130,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":135,"categoryName":136,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[139,140,141,142,26,143,144,145,146,147,148,40,149,150,151,29,152,153,154,155,156,157,158],"podcast generation","generation","podcast","frontend","azure openai","realtime","react","python","Audio","creation","fastapi backend","python fastapi","fastapi","api","streaming","text","narrative","stack","generate","features",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"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",[165],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[167,9,168,169,170,171,172,26,173,174,175,176,177,178,179,180,114,181,64,182,115,183,184,185],"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":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":193,"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",[192],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[194,173,195,196,197,9,146,198,199,40,200,29,39,201,202,113,203,204,114,205,115,120],"mcp builder","builder","llms","sdk","typescript","model context protocol","building mcp servers","integrate","Tools","context","fastmcp","mcp sdk",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":224,"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",[212,215,216,221],{"categoryNo":213,"categoryName":214,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":217,"categoryName":218,"taxonomyType":219,"taxonomyTypeDesc":220},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":222,"categoryName":223,"taxonomyType":219,"taxonomyTypeDesc":220},"01JBSEEDCAT000000000000036","内容创作者",[208,26,174,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,114,241,242,243],"analytics","memory","summarize","exploration","parse","project","time","vector","join","log","pipe","datetime","discipline","time series","regex","anomaly","section","tool","geo"]