[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75KPKEXX1RCEB9ABAT5020P":3,"skill-same:01M75KPKEXX1RCEB9ABAT5020P":47},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M75KPKEXX1RCEB9ABAT5020P","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.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fkillerapp\u002Faws-agentcore-langgraph\u002FSKILL.md",[],[],"2026-11-12 13:55:43",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","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fkillerapp\u002Faws-agentcore-langgraph",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill aws-agentcore-langgraph",{"tool":39,"command":40},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill aws-agentcore-langgraph",{"tool":42,"command":43},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill aws-agentcore-langgraph","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fkillerapp\u002Faws-agentcore-langgraph\u002FSKILL.md",true,[],[48,56,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":55},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":55},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":55},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":55},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":55},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":55},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]