[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MX8T6V2YATHE5X3QDJS1SD":3,"skill-same:01M6MX8T6V2YATHE5X3QDJS1SD":114},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6MX8T6V2YATHE5X3QDJS1SD","aws-agentcore-langgraph",null,"Deploy production LangGraph agents on AWS Bedrock AgentCore. Use for (1) multi-agent systems with orchestrator and specialist agent patterns, (2) building stateful agents with persistent cross-session memory, (3) connecting external tools via AgentCore Gateway (MCP, Lambda, APIs), (4) managing shared context across distributed agents, or (5) deploying complex agent ecosystems via CLI with production observability and scaling.","Kernel8901\u002Fai-agent-skills-classification","Kernel8901","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72647553?v=4","01M6KV388J2H5PNC8D8P940BJD","01M6KV38CS5B3AY63RKZB410YM",7,"MIT","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"aws agentcore langgraph","langgraph","aws","agentcore","patterns","stateful","bedrock","external tools","scaling","ecosystems","shared","across","session memory","MCP","langgraph agents","orchestrator","multi-agent","lambda","memory","cli","2026-11-10 10:12:30",false,"---\nname: aws-agentcore-langgraph\ndescription: Deploy production LangGraph agents on AWS Bedrock AgentCore. Use for (1) multi-agent systems with orchestrator and specialist agent patterns, (2) building stateful agents with persistent cross-session memory, (3) connecting external tools via AgentCore Gateway (MCP, Lambda, APIs), (4) managing shared context across distributed agents, or (5) deploying complex agent ecosystems via CLI with production observability and scaling.\n---\n\n# AWS AgentCore + LangGraph\n\nMulti-agent systems on AWS Bedrock AgentCore with LangGraph orchestration. Source: https:\u002F\u002Fgithub.com\u002Faws\u002Fbedrock-agentcore-starter-toolkit\n\n## Install\n```bash\npip install bedrock-agentcore bedrock-agentcore-starter-toolkit langgraph\nuv tool install bedrock-agentcore-starter-toolkit  # installs agentcore CLI\n```\n\n## Quick Start\n```python\nfrom langgraph.graph import StateGraph, START\nfrom langgraph.graph.message import add_messages\nfrom langgraph.prebuilt import ToolNode, tools_condition  # routing + tool execution\nfrom bedrock_agentcore.runtime import BedrockAgentCoreApp\nfrom typing import Annotated\nfrom typing_extensions import TypedDict\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]\n\nbuilder = StateGraph(State)\nbuilder.add_node(\"agent\", agent_node)\nbuilder.add_node(\"tools\", ToolNode(tools))  # prebuilt tool executor\nbuilder.add_conditional_edges(\"agent\", tools_condition)  # routes to tools or END\nbuilder.add_edge(START, \"agent\")\ngraph = builder.compile()\n\napp = BedrockAgentCoreApp()  # Wraps as HTTP service on port 8080 (\u002Finvocations, \u002Fping)\n@app.entrypoint\ndef invoke(payload, context):\n    result = graph.invoke({\"messages\": [(\"user\", payload.get(\"prompt\", \"\"))]})\n    return {\"result\": result[\"messages\"][-1].content}\napp.run()\n```\n\n## CLI Commands\n| Command | Purpose |\n|---------|---------|\n| `agentcore configure -e agent.py --region us-east-1` | Setup |\n| `agentcore configure -e agent.py --region us-east-1 --name my_agent --non-interactive` | Scripted setup |\n| `agentcore launch --deployment-type container` | Deploy (container mode) |\n| `agentcore launch --disable-memory` | Deploy without memory subsystem |\n| `agentcore dev` | Hot-reload local dev server |\n| `agentcore invoke '{\"prompt\": \"Hello\"}'` | Test |\n| `agentcore destroy` | Cleanup |\n\n## Core Patterns\n\n### Multi-Agent Orchestration\n- Orchestrator delegates to specialists (customer service, e-commerce, healthcare, financial, etc.)\n- Specialists: inline functions or separate deployed agents; all share `session_id` for context\n\n### Memory (STM\u002FLTM)\n```python\nfrom bedrock_agentcore.memory import MemoryClient\nmemory = MemoryClient()\nmemory.create_event(session_id, actor_id, event_type, payload)  # Store\nevents = memory.list_events(session_id)  # Retrieve (returns list)\n```\n- **STM**: Turn-by-turn within session | **LTM**: Facts\u002Fdecisions across sessions\u002Fagents\n- ~10s eventual consistency after writes\n\n### Gateway Tools\n```bash\npython -m bedrock_agentcore.gateway.deploy --stack-name my-agents --region us-east-1\n```\n```python\nfrom bedrock_agentcore.gateway import GatewayToolClient\ngateway = GatewayToolClient()\nresult = gateway.call(\"tool_name\", param1=value1, param2=value2)\n```\n- Transport: Fallback Mock (local), Local MCP servers, Production Gateway (Lambda\u002FREST\u002FMCP)\n- Auto-configures `BEDROCK_AGENTCORE_GATEWAY_URL` after deploy\n\n## Decision Tree\n```\nMultiple agents coordinating? → Orchestrator + specialists pattern\nPersistent cross-session memory? → AgentCore Memory (not LangGraph checkpoints)\nExternal APIs\u002FLambda? → AgentCore Gateway\nSingle agent, simple? → Quick Start above\nComplex multi-step logic? → StateGraph + tools_condition + ToolNode\n```\n\n## Key Concepts\n- **AgentCore Runtime**: HTTP service on port 8080 (handles `\u002Finvocations`, `\u002Fping`)\n- **AgentCore Memory**: Managed cross-session\u002Fcross-agent memory\n- **LangGraph Routing**: `tools_condition` for agent→tool routing, `ToolNode` for execution\n- **AgentCore Gateway**: Transforms APIs\u002FLambda into MCP tools with auth\n\n## Naming Rules\n- Start with letter, only letters\u002Fnumbers\u002Funderscores, 1-48 chars: `my_agent` not `my-agent`\n\n## Troubleshooting\n| Issue | Fix |\n|-------|-----|\n| `on-demand throughput isn't supported` | Use `us.anthropic.claude-*` inference profiles |\n| `Model use case details not submitted` | Fill Anthropic form in Bedrock Console |\n| `Invalid agent name` | Use underscores not hyphens |\n| Memory empty after write | Wait ~10s (eventual consistency) |\n| Container not reading .env | Set ENV in Dockerfile, not .env |\n| Memory not working after deploy | Check logs for \"Memory enabled\u002Fdisabled\" |\n| `list_events` returns empty | Check actor_id\u002Fsession_id match; `event['payload']` is a list |\n| Gateway \"Unknown tool\" | Lambda must strip `___` prefix from `bedrockAgentCoreToolName` |\n| Platform mismatch warning | Normal - CodeBuild handles ARM64 cross-platform builds |\n\n## References\n- [agentcore-cli.md](references\u002Fagentcore-cli.md) - CLI commands, deployment, lifecycle\n- [agentcore-runtime.md](references\u002Fagentcore-runtime.md) - Streaming, async, observability\n- [agentcore-memory.md](references\u002Fagentcore-memory.md) - STM\u002FLTM patterns, API reference\n- [agentcore-gateway.md](references\u002Fagentcore-gateway.md) - Tool integration, MCP, Lambda\n- [langgraph-patterns.md](references\u002Flanggraph-patterns.md) - StateGraph design, routing\n- [reference-architecture-advertising-agents-use-case.pdf](references\u002Freference-architecture-advertising-agents-use-case.pdf) - Example multi-agent architecture\n","# AWS AgentCore + LangGraph\n\nMulti-agent systems on AWS Bedrock AgentCore with LangGraph orchestration. Source: https:\u002F\u002Fgithub.com\u002Faws\u002Fbedrock-agentcore-starter-toolkit\n\n## Install\n```bash\npip install bedrock-agentcore bedrock-agentcore-starter-toolkit langgraph\nuv tool install bedrock-agentcore-starter-toolkit  # installs agentcore CLI\n```\n\n## Quick Start\n```python\nfrom langgraph.graph import StateGraph, START\nfrom langgraph.graph.message import add_messages\nfrom langgraph.prebuilt import ToolNode, tools_condition  # routing + tool execution\nfrom bedrock_agentcore.runtime import BedrockAgentCoreApp\nfrom typing import Annotated\nfrom typing_extensions import TypedDict\n\nclass State(TypedDict):\n    messages: Annotated[list, add_messages]\n\nbuilder = StateGraph(State)\nbuilder.add_node(\"agent\", agent_node)\nbuilder.add_node(\"tools\", ToolNode(tools))  # prebuilt tool executor\nbuilder.add_conditional_edges(\"agent\", tools_condition)  # routes to tools or END\nbuilder.add_edge(START, \"agent\")\ngraph = builder.compile()\n\napp = BedrockAgentCoreApp()  # Wraps as HTTP service on port 8080 (\u002Finvocations, \u002Fping)\n@app.entrypoint\ndef invoke(payload, context):\n    result = graph.invoke({\"messages\": [(\"user\", payload.get(\"prompt\", \"\"))]})\n    return {\"result\": result[\"messages\"][-1].content}\napp.run()\n```\n\n## CLI Commands\n| Command | Purpose |\n|---------|---------|\n| `agentcore configure -e agent.py --region us-east-1` | Setup |\n| `agentcore configure -e agent.py --region us-east-1 --name my_agent --non-interactive` | Scripted setup |\n| `agentcore launch --deployment-type container` | Deploy (container mode) |\n| `agentcore launch --disable-memory` | Deploy without memory subsystem |\n| `agentcore dev` | Hot-reload local dev server |\n| `agentcore invoke '{\"prompt\": \"Hello\"}'` | Test |\n| `agentcore destroy` | Cleanup |\n\n## Core Patterns\n\n### Multi-Agent Orchestration\n- Orchestrator delegates to specialists (customer service, e-commerce, healthcare, financial, etc.)\n- Specialists: inline functions or separate deployed agents; all share `session_id` for context\n\n### Memory (STM\u002FLTM)\n```python\nfrom bedrock_agentcore.memory import MemoryClient\nmemory = MemoryClient()\nmemory.create_event(session_id, actor_id, event_type, payload)  # Store\nevents = memory.list_events(session_id)  # Retrieve (returns list)\n```\n- **STM**: Turn-by-turn within session | **LTM**: Facts\u002Fdecisions across sessions\u002Fagents\n- ~10s eventual consistency after writes\n\n### Gateway Tools\n```bash\npython -m bedrock_agentcore.gateway.deploy --stack-name my-agents --region us-east-1\n```\n```python\nfrom bedrock_agentcore.gateway import GatewayToolClient\ngateway = GatewayToolClient()\nresult = gateway.call(\"tool_name\", param1=value1, param2=value2)\n```\n- Transport: Fallback Mock (local), Local MCP servers, Production Gateway (Lambda\u002FREST\u002FMCP)\n- Auto-configures `BEDROCK_AGENTCORE_GATEWAY_URL` after deploy\n\n## Decision Tree\n```\nMultiple agents coordinating? → Orchestrator + specialists pattern\nPersistent cross-session memory? → AgentCore Memory (not LangGraph checkpoints)\nExternal APIs\u002FLambda? → AgentCore Gateway\nSingle agent, simple? → Quick Start above\nComplex multi-step logic? → StateGraph + tools_condition + ToolNode\n```\n\n## Key Concepts\n- **AgentCore Runtime**: HTTP service on port 8080 (handles `\u002Finvocations`, `\u002Fping`)\n- **AgentCore Memory**: Managed cross-session\u002Fcross-agent memory\n- **LangGraph Routing**: `tools_condition` for agent→tool routing, `ToolNode` for execution\n- **AgentCore Gateway**: Transforms APIs\u002FLambda into MCP tools with auth\n\n## Naming Rules\n- Start with letter, only letters\u002Fnumbers\u002Funderscores, 1-48 chars: `my_agent` not `my-agent`\n\n## Troubleshooting\n| Issue | Fix |\n|-------|-----|\n| `on-demand throughput isn't supported` | Use `us.anthropic.claude-*` inference profiles |\n| `Model use case details not submitted` | Fill Anthropic form in Bedrock Console |\n| `Invalid agent name` | Use underscores not hyphens |\n| Memory empty after write | Wait ~10s (eventual consistency) |\n| Container not reading .env | Set ENV in Dockerfile, not .env |\n| Memory not working after deploy | Check logs for \"Memory enabled\u002Fdisabled\" |\n| `list_events` returns empty | Check actor_id\u002Fsession_id match; `event['payload']` is a list |\n| Gateway \"Unknown tool\" | Lambda must strip `___` prefix from `bedrockAgentCoreToolName` |\n| Platform mismatch warning | Normal - CodeBuild handles ARM64 cross-platform builds |\n\n## References\n- [agentcore-cli.md](references\u002Fagentcore-cli.md) - CLI commands, deployment, lifecycle\n- [agentcore-runtime.md](references\u002Fagentcore-runtime.md) - Streaming, async, observability\n- [agentcore-memory.md](references\u002Fagentcore-memory.md) - STM\u002FLTM patterns, API reference\n- [agentcore-gateway.md](references\u002Fagentcore-gateway.md) - Tool integration, MCP, Lambda\n- [langgraph-patterns.md](references\u002Flanggraph-patterns.md) - StateGraph design, routing\n- [reference-architecture-advertising-agents-use-case.pdf](references\u002Freference-architecture-advertising-agents-use-case.pdf) - Example multi-agent architecture\n",{"name":5,"description":7},"main","f4cb2d49f7667e79ef7804f50396d5aaffdf1f56","人工智能与大型语言模型\u002Faws-agentcore-langgraph",1,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification","https:\u002F\u002Fgithub.com\u002FKernel8901","a little little little dobe in life but science geek","2026-04-05 16:43:56",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add Kernel8901\u002Fai-agent-skills-classification --skill aws-agentcore-langgraph",{"tool":62,"command":63},"bunx","bunx skills add Kernel8901\u002Fai-agent-skills-classification --skill aws-agentcore-langgraph",{"tool":65,"command":66},"pnpm","pnpm dlx skills add Kernel8901\u002Fai-agent-skills-classification --skill aws-agentcore-langgraph","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002FSKILL.md",true,[70,76,80,84,88,92,96,102,106,110],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"_meta.json","REFERENCE","参考文档",301,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002F_meta.json",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fagentcore-cli.md",2678,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Freferences\u002Fagentcore-cli.md",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fagentcore-gateway.md",3056,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Freferences\u002Fagentcore-gateway.md",{"path":85,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fagentcore-memory.md",2770,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Freferences\u002Fagentcore-memory.md",{"path":89,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fagentcore-runtime.md",2892,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Freferences\u002Fagentcore-runtime.md",{"path":93,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Flanggraph-patterns.md",2983,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Freferences\u002Flanggraph-patterns.md",{"path":97,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Fagent-details.sh","SCRIPT","脚本",713,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Fscripts\u002Fagent-details.sh",{"path":103,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Flist-all.sh",1708,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Fscripts\u002Flist-all.sh",{"path":107,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fmemory-details.sh",622,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Fscripts\u002Fmemory-details.sh",{"path":111,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Ftail-logs.sh",610,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F人工智能与大型语言模型\u002Faws-agentcore-langgraph\u002Fscripts\u002Ftail-logs.sh",[115,139,169,180,190,220],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":43},"01M6Q5R6WZ06RRB9RQTW54B34B","zyfai","Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit\u002Fwithdraw anytime.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzyfai-sdk\u002FSKILL.md",[],[117,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138],"safe","ethereum","defi","Optimization","user","use","Wallet","base","deposit","withdraw","yield","arbitrum","non-custodial","passive","defi yield","earn","yield optimization",{"skillNo":140,"name":141,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":153,"publishedAt":43},"01M6Q5R337B5JSNER4P4YS03TN","zerion-api","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api\u002FSKILL.md",[144,147,148],{"categoryNo":145,"categoryName":146,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":149,"categoryName":150,"taxonomyType":151,"taxonomyTypeDesc":152},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[154,155,156,36,157,158,159,124,160,128,161,162,163,164,165,34,166,167,168],"api","zerion api","zerion","mcp server","server","blockchain","transactions","crypto wallet","crypto","evm","solana","query","positions","token","prices",{"skillNo":170,"name":171,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":177,"publishedAt":43},"01M6Q5QZFYTDAZMZ27BN5VZXAR","zerion-api-skill","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-skill\u002FSKILL.md",[174,175,176],{"categoryNo":145,"categoryName":146,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":149,"categoryName":150,"taxonomyType":151,"taxonomyTypeDesc":152},[154,178,179,155,156,36,157,158,159,124,160,128,162,163,164,165,34,166,167,168],"api skill","zerion api skill",{"skillNo":181,"name":182,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":188,"publishedAt":43},"01M6Q5QW17QW98RA3FE45E4RD8","zerion-api-mcp","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-mcp\u002FSKILL.md",[185,186,187],{"categoryNo":145,"categoryName":146,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":149,"categoryName":150,"taxonomyType":151,"taxonomyTypeDesc":152},[36,154,189,155,156,157,158,124,160,128,161,162,163,164,165,34,166,167,168],"zerion api mcp",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":199,"publishedAt":43},"01M6Q5QQYZB7A501BDEQWKGSJT","yahoo-finance-forex","Fetches real-time FOREX news and market data from Yahoo Finance for major currency pairs (EUR\u002FUSD, GBP\u002FUSD, USD\u002FJPY, etc.). Analyzes sentiment and provides trading context.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-forex\u002FSKILL.md",[196],{"categoryNo":197,"categoryName":198,"taxonomyType":151,"taxonomyTypeDesc":152},"01JBSEEDCAT000000000000040","财务",[200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219],"finance","yahoo finance","forex","yahoo","yahoo finance forex","github","https","sentiment","real-time","python3","install","Market","usd","news","time","currency","gbp","pip","market data","for",{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":227,"publishedAt":43},"01M6Q5QM6VS84WZVM7BKXXPF32","yahoo-finance","This skill should be used when the user asks to \"get stock prices\", \"check stock quotes\", \"look up earnings\", \"get financial data\", \"find trending stocks\", or needs stock market data from Yahoo Finance.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-cli\u002FSKILL.md",[226],{"categoryNo":197,"categoryName":198,"taxonomyType":151,"taxonomyTypeDesc":152},[200,201,203,42,228,229,230,231,232,211,233,234,235,236,237,238,239,240,168,218],"homebrew","find","check","brew","up","local","get","stock","link","trending","sf","quotes","ln"]