[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698Y5R3JB357WQ0V8A55ZFC":3,"skill-same:01M698Y5R3JB357WQ0V8A55ZFC":136},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M698Y5R3JB357WQ0V8A55ZFC","adk-architecture",null,"Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface. Use when answering \"how does X work\" about ADK internals, tracing where an event or a piece of state comes from, deciding where a new capability belongs, reviewing a change to BaseNode, Workflow, Runner, Agent, Event or Context, working out why a node re-ran or stayed waiting after a resume, or judging whether a change breaks the public API. Don't use for assembling an agent from existing pieces (use adk-agent-builder), diagnosing one failing run or test (use adk-debug), or formatting and naming conventions (use adk-style).","google\u002Fadk-python","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698XZC2HCATT8VD5VAVZDTP",22178,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"adk","adk architecture","architecture","failing","when","re","public api","runner","builder","node","work","model","why","how","api","flow","tracing","run","change","workflow","2026-11-10 10:12:30",false,"---\nname: adk-architecture\ndescription: >-\n  Explains how the ADK runtime fits together: the node and graph execution\n  model, Context and Event flow, checkpoint and resume, tracing, and the rules\n  governing the public API surface. Use when answering \"how does X work\" about\n  ADK internals, tracing where an event or a piece of state comes from,\n  deciding where a new capability belongs, reviewing a change to BaseNode,\n  Workflow, Runner, Agent, Event or Context, working out why a node re-ran or\n  stayed waiting after a resume, or judging whether a change breaks the public\n  API. Don't use for assembling an agent from existing pieces (use\n  adk-agent-builder), diagnosing one failing run or test (use adk-debug), or\n  formatting and naming conventions (use adk-style).\n---\n\n# ADK Architecture\n\nThe runtime is a graph of nodes. `BaseNode` is the unit of execution.\n`Workflow` is a node that schedules other nodes along declared edges.\n`NodeRunner` executes exactly one node. `Runner` owns the invocation and the\nsession. Agents are nodes too — `BaseAgent` extends `BaseNode`.\n\nA node communicates with its parent through a per-execution `Context`, and\nwith the session through `Event`s it yields. Those are two separate channels:\n`ctx` carries the result upward, events carry persistence and streaming.\n\nRead the source before relying on any signature here. These notes drift; the\ncode does not. Paths below are relative to `src\u002Fgoogle\u002Fadk\u002F`.\n\n## Pick a reference\n\n| Question | Reference |\n|---|---|\n| What must a node implement? What may it yield? Which config fields exist? | [BaseNode](references\u002Finterface-base-node.md) |\n| How does the graph schedule nodes, dedup dynamic children, propagate interrupts? | [Workflow](references\u002Finterface-workflow.md) |\n| How does a caller start an invocation? | [Runner](references\u002Finterface-runner.md) |\n| What is `Agent`, and which methods do I call on it? | [Agent](references\u002Finterface-agent.md) |\n| I am subclassing an agent — what do I override? | [BaseAgent](references\u002Finterface-base-agent.md) |\n| What is on an `Event`, and what may I assume about its lifetime? | [Event](references\u002Finterface-event.md) |\n| What does a node read and write on `ctx`? | [Context](references\u002Farchitecture-context.md) |\n| Who creates the child Context, stamps events, retries, catches errors? | [NodeRunner](references\u002Farchitecture-node-runner.md) |\n| Why are Runner, NodeRunner and Workflow three separate things? | [Runner roles](references\u002Farchitecture-runner-roles.md) |\n| How does a human-in-the-loop pause and resume work for one node? | [Checkpoint and resume](references\u002Farchitecture-checkpoint-resume.md) |\n| How does a whole workflow survive a pause, and what does `is_resumable` change? | [Workflow resumability](references\u002Farchitecture-workflow-resumability.md) |\n| How are spans created, and what attributes do they carry? | [Observability](references\u002Farchitecture-observability.md) |\n| Why does the model not see the raw event log? | [LLM context orchestration](references\u002Farchitecture-llm-context-orchestration.md) |\n| Is this change a breaking change? Where does a new export belong? | [API principles](references\u002Fapi-principles.md) |\n\n## Where the code lives\n\n| Concept | Module |\n|---|---|\n| `BaseNode`, `START` | `workflow\u002F_base_node.py` |\n| `Workflow`, `_LoopState` | `workflow\u002F_workflow.py` |\n| `Graph`, edge compilation | `workflow\u002F_graph.py` |\n| `NodeRunner` | `workflow\u002F_node_runner.py` |\n| `DynamicNodeScheduler`, `DynamicNodeState`, `DynamicNodeRun` | `workflow\u002F_dynamic_node_scheduler.py` |\n| `ReplayManager` (resume scan) | `workflow\u002Futils\u002F_replay_manager.py` |\n| `check_interception` (replay fast-forward) | `workflow\u002Futils\u002F_replay_interceptor.py` |\n| `NodeInterruptedError`, `NodeTimeoutError` | `workflow\u002F_errors.py` |\n| `Context`, `ctx.run_node()` | `agents\u002Fcontext.py` |\n| `ReadonlyContext` | `agents\u002Freadonly_context.py` |\n| `InvocationContext` | `agents\u002Finvocation_context.py` |\n| `BaseAgent`, `LlmAgent` (aliased `Agent`) | `agents\u002Fbase_agent.py`, `agents\u002Fllm_agent.py` |\n| `BaseLlmFlow`, `SingleFlow`, `AutoFlow`, `flows\u002Fllm_flows\u002F` subpackages (`context\u002F`, `prompt\u002F`, `tools\u002F`, `extensions\u002F`, `core\u002F`) | `flows\u002Fllm_flows\u002F` |\n| `Event`, `NodeInfo` | `events\u002Fevent.py` |\n| `EventActions` | `events\u002Fevent_actions.py` |\n| Branch paths (`parent.child@1`) | `events\u002F_branch_path.py` |\n| Node paths (`wf@1\u002Fchild@2`) | `events\u002F_node_path_builder.py` |\n| `Runner`, `InMemoryRunner` | `runners.py` |\n| `LiveRequestQueue`, `LiveRequest` | `live\u002Flive_request_queue.py` |\n| Node spans, `TelemetryContext` | `telemetry\u002Fnode_tracing.py` |\n| `ResumabilityConfig` | `apps\u002F_configs.py` |\n\nEverything under `workflow\u002F` is a leading-underscore module. Treat those names\nas internal — they can change without a major version bump, so a change there\nis not automatically a breaking change.\n","# ADK Architecture\n\nThe runtime is a graph of nodes. `BaseNode` is the unit of execution.\n`Workflow` is a node that schedules other nodes along declared edges.\n`NodeRunner` executes exactly one node. `Runner` owns the invocation and the\nsession. Agents are nodes too — `BaseAgent` extends `BaseNode`.\n\nA node communicates with its parent through a per-execution `Context`, and\nwith the session through `Event`s it yields. Those are two separate channels:\n`ctx` carries the result upward, events carry persistence and streaming.\n\nRead the source before relying on any signature here. These notes drift; the\ncode does not. Paths below are relative to `src\u002Fgoogle\u002Fadk\u002F`.\n\n## Pick a reference\n\n| Question | Reference |\n|---|---|\n| What must a node implement? What may it yield? Which config fields exist? | [BaseNode](references\u002Finterface-base-node.md) |\n| How does the graph schedule nodes, dedup dynamic children, propagate interrupts? | [Workflow](references\u002Finterface-workflow.md) |\n| How does a caller start an invocation? | [Runner](references\u002Finterface-runner.md) |\n| What is `Agent`, and which methods do I call on it? | [Agent](references\u002Finterface-agent.md) |\n| I am subclassing an agent — what do I override? | [BaseAgent](references\u002Finterface-base-agent.md) |\n| What is on an `Event`, and what may I assume about its lifetime? | [Event](references\u002Finterface-event.md) |\n| What does a node read and write on `ctx`? | [Context](references\u002Farchitecture-context.md) |\n| Who creates the child Context, stamps events, retries, catches errors? | [NodeRunner](references\u002Farchitecture-node-runner.md) |\n| Why are Runner, NodeRunner and Workflow three separate things? | [Runner roles](references\u002Farchitecture-runner-roles.md) |\n| How does a human-in-the-loop pause and resume work for one node? | [Checkpoint and resume](references\u002Farchitecture-checkpoint-resume.md) |\n| How does a whole workflow survive a pause, and what does `is_resumable` change? | [Workflow resumability](references\u002Farchitecture-workflow-resumability.md) |\n| How are spans created, and what attributes do they carry? | [Observability](references\u002Farchitecture-observability.md) |\n| Why does the model not see the raw event log? | [LLM context orchestration](references\u002Farchitecture-llm-context-orchestration.md) |\n| Is this change a breaking change? Where does a new export belong? | [API principles](references\u002Fapi-principles.md) |\n\n## Where the code lives\n\n| Concept | Module |\n|---|---|\n| `BaseNode`, `START` | `workflow\u002F_base_node.py` |\n| `Workflow`, `_LoopState` | `workflow\u002F_workflow.py` |\n| `Graph`, edge compilation | `workflow\u002F_graph.py` |\n| `NodeRunner` | `workflow\u002F_node_runner.py` |\n| `DynamicNodeScheduler`, `DynamicNodeState`, `DynamicNodeRun` | `workflow\u002F_dynamic_node_scheduler.py` |\n| `ReplayManager` (resume scan) | `workflow\u002Futils\u002F_replay_manager.py` |\n| `check_interception` (replay fast-forward) | `workflow\u002Futils\u002F_replay_interceptor.py` |\n| `NodeInterruptedError`, `NodeTimeoutError` | `workflow\u002F_errors.py` |\n| `Context`, `ctx.run_node()` | `agents\u002Fcontext.py` |\n| `ReadonlyContext` | `agents\u002Freadonly_context.py` |\n| `InvocationContext` | `agents\u002Finvocation_context.py` |\n| `BaseAgent`, `LlmAgent` (aliased `Agent`) | `agents\u002Fbase_agent.py`, `agents\u002Fllm_agent.py` |\n| `BaseLlmFlow`, `SingleFlow`, `AutoFlow`, `flows\u002Fllm_flows\u002F` subpackages (`context\u002F`, `prompt\u002F`, `tools\u002F`, `extensions\u002F`, `core\u002F`) | `flows\u002Fllm_flows\u002F` |\n| `Event`, `NodeInfo` | `events\u002Fevent.py` |\n| `EventActions` | `events\u002Fevent_actions.py` |\n| Branch paths (`parent.child@1`) | `events\u002F_branch_path.py` |\n| Node paths (`wf@1\u002Fchild@2`) | `events\u002F_node_path_builder.py` |\n| `Runner`, `InMemoryRunner` | `runners.py` |\n| `LiveRequestQueue`, `LiveRequest` | `live\u002Flive_request_queue.py` |\n| Node spans, `TelemetryContext` | `telemetry\u002Fnode_tracing.py` |\n| `ResumabilityConfig` | `apps\u002F_configs.py` |\n\nEverything under `workflow\u002F` is a leading-underscore module. Treat those names\nas internal — they can change without a major version bump, so a change there\nis not automatically a breaking change.\n",{"name":5,"description":7},"main","8cd3b12c8a5d658c5e0d3ea0731d8be34a092a4a",".agents\u002Fskills\u002Fadk-architecture",4334,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python","https:\u002F\u002Fgoogle.github.io\u002Fadk-docs\u002F","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-11 08:39:57",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add google\u002Fadk-python --skill adk-architecture",{"tool":70,"command":71},"bunx","bunx skills add google\u002Fadk-python --skill adk-architecture",{"tool":73,"command":74},"pnpm","pnpm dlx skills add google\u002Fadk-python --skill adk-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002FSKILL.md",true,[78,84,88,92,96,100,104,108,112,116,120,124,128,132],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fapi-principles.md","REFERENCE","参考文档",2766,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Fapi-principles.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Farchitecture-checkpoint-resume.md",2650,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Farchitecture-checkpoint-resume.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Farchitecture-context.md",4280,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Farchitecture-context.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Farchitecture-llm-context-orchestration.md",1956,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Farchitecture-llm-context-orchestration.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Farchitecture-node-runner.md",6118,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Farchitecture-node-runner.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Farchitecture-observability.md",4065,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Farchitecture-observability.md",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Farchitecture-runner-roles.md",452,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Farchitecture-runner-roles.md",{"path":109,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Farchitecture-workflow-resumability.md",7920,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Farchitecture-workflow-resumability.md",{"path":113,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Finterface-agent.md",2024,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Finterface-agent.md",{"path":117,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Finterface-base-agent.md",2087,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Finterface-base-agent.md",{"path":121,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Finterface-base-node.md",5009,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Finterface-base-node.md",{"path":125,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Finterface-event.md",3314,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Finterface-event.md",{"path":129,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Finterface-runner.md",3059,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Finterface-runner.md",{"path":133,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Finterface-workflow.md",21605,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fadk-architecture\u002Freferences\u002Finterface-workflow.md",[137,165,192,218,234,242],{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":147,"publishedAt":49},"01M698ZJNXJCE7T81AK0Y5R01D","bigquery-graph","Skill for Graph Query Language (GQL) or SQL\u002FPGQ queries against a property graph.\nIncludes path finding, multi-hop traversal, topological connection, shortest path,\nnode reachability, edge connectivity, and semantic graph queries.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fadk\u002Fintegrations\u002Fbigquery\u002Fskills\u002Fbigquery-graph\u002FSKILL.md",[143,144],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":145,"categoryName":146,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师",[148,149,150,9,151,29,152,153,154,155,38,156,157,158,159,160,161,162,163,164],"graph","bigquery","bigquery graph","for","sql","edge","graph query","hop","queries","language","query","connectivity","gql","semantic","multi","connection","path",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":172,"publishedAt":49},"01M698ZEVMRDDFX2MH3GHQGSNW","bigquery-ai-ml","Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, measure the causal effect of an intervention, compute correlations between columns, detect change points or structural breaks, extract trend or seasonality components, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002Fsrc\u002Fgoogle\u002Fadk\u002Fintegrations\u002Fbigquery\u002Fskills\u002Fbigquery-ai-ml\u002FSKILL.md",[171],{"categoryNo":145,"categoryName":146,"taxonomyType":26,"taxonomyTypeDesc":27},[173,149,174,175,176,33,177,178,179,180,181,182,183,184,185,9,186,187,29,188,189,190,191],"ai ml","ml","bigquery ai ml","vector","generative","you","advanced","dataset","leverage","structural","time","effect","search","summarize","genai","generative ai","translate","components","capabilities",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":203,"publishedAt":49},"01M698ZCN6SZ9SJ8E9970M47FQ","code-review-skill","Reviews code with feedback tailored to the developer's profile in session state.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002Fcontributing\u002Fsamples\u002Fenvironment_and_skills\u002Fskills_inject_state\u002Fskills\u002Fcode-review-skill\u002FSKILL.md",[198,201,202],{"categoryNo":199,"categoryName":200,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[204,205,206,207,208,209,210,211,212,213,214,215,216,217],"review skill","code","code review skill","review","code review","session","state","developer","feedback","profile","with","session state","reviews","true",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":225,"publishedAt":49},"01M698ZAMH02NSGXMR533ETWYW","weather-skill","A skill that provides weather information based on reference data.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002Fcontributing\u002Fsamples\u002Fenvironment_and_skills\u002Fskills_agent\u002Fskills\u002Fweather-skill\u002FSKILL.md",[224],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[226,227,228,229,230,231,232,233],"weather skill","weather","data","reference","speed","get","wind","information",{"skillNo":235,"name":220,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":237,"categories":238,"keywords":240,"publishedAt":49},"01M698Z8QFDZ713E03589BHEG5","A skill that provides weather information based on reference data and scripts.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002Fcontributing\u002Fsamples\u002Fenvironment_and_skills\u002Fskills\u002Fskills\u002Fweather-skill\u002FSKILL.md",[239],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[227,226,233,232,241,231,230,229,228],"scripts",{"skillNo":243,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":244,"categories":245,"keywords":247,"publishedAt":49},"01M698Z6P1NZFW6A6V342AWZPR","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-python\u002Fblob\u002Fmain\u002Fcontributing\u002Fsamples\u002Fenvironment_and_skills\u002Flocal_environment_skill\u002Fskills\u002Fweather-skill\u002FSKILL.md",[246],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[226,227,229,233,228]]