{ "schemaVersion": "1.0", "item": { "slug": "k3-blockchain-agent", "name": "K3 Blockhain Agent Skill", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/alexgrankinukr-hash/k3-blockchain-agent", "canonicalUrl": "https://clawhub.ai/alexgrankinukr-hash/k3-blockchain-agent", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/k3-blockchain-agent", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=k3-blockchain-agent", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "references/data-sources.md", "references/troubleshooting.md", "references/workflow-patterns.md", "references/node-types.md", "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/k3-blockchain-agent" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/k3-blockchain-agent", "agentPageUrl": "https://openagent3.xyz/skills/k3-blockchain-agent/agent", "manifestUrl": "https://openagent3.xyz/skills/k3-blockchain-agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/k3-blockchain-agent/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "K3 Blockchain Agent", "body": "Transform requests like \"Send me daily updates about the WETH/USDC pool on Uniswap\"\ninto fully deployed workflows that fetch data, run AI analysis, and deliver reports\nautomatically." }, { "title": "Setup", "body": "This skill requires the K3 Development MCP to be connected. The MCP provides\ntools like generateWorkflow, executeWorkflow, findAgentByFunctionality, and\nothers that let you create and manage blockchain workflows programmatically.\n\nIf the K3 MCP isn't connected yet, tell the user they need to add it before\nproceeding. Once connected, verify by calling listTeamMcpServerIntegrations() —\nthis confirms the connection and shows what data source integrations (TheGraph,\nCoinGecko, etc.) the user's team has wired up. Every team's integrations will be\ndifferent — discover what's available rather than assuming." }, { "title": "How Workflow Building Works", "body": "The K3 orchestrator is conversational. You describe what you want in plain\nlanguage, and the orchestrator asks clarifying questions, then builds and deploys\nthe workflow. Your job is to show up with the right information so the conversation\nis productive.\n\nThe loop:\n\nUNDERSTAND → what does the user actually want?\nFIND DATA → how do we get that information into the workflow?\nTEST → does the data actually come back correctly?\nBUILD → give the orchestrator everything it needs\nDEPLOY → launch it and verify it works\n\nSkipping \"test\" is the most common mistake — you end up with a deployed workflow\nthat returns empty data." }, { "title": "Step 1: Understand the Request", "body": "When a user asks for a workflow, figure out these parameters. Ask if anything is\nunclear — don't guess on addresses or emails.\n\nParameterWhat to find outExamplesData targetWhat blockchain data do they need?pool metrics, token price, wallet balance, NFT dataProtocolWhich DeFi protocol or chain feature?Uniswap, Aave, SushiSwap, native transfersChainWhich blockchain?Ethereum, Arbitrum, Polygon, Base, StellarScheduleHow often / what triggers it?daily, hourly, on-demand, on wallet activity, on contract event, Telegram chatbotAnalysisWhat kind of insights?performance summary, anomaly alerts, trend report, trade signalDeliveryHow should results arrive?email, Telegram, Slack, Google SheetsActionsShould the workflow do anything?execute a swap, transfer tokens, write to a contractSpecificsAny addresses or IDs?pool address, token contract, wallet address\n\nIf the user is new to DeFi, briefly explain relevant concepts as you go (what TVL\nmeans, what a liquidity pool is, etc.). Don't assume they know the jargon." }, { "title": "Step 2: Find the Right Data", "body": "This is the critical step. K3 has many ways to get data into a workflow, and you\nneed to figure out which approach works for the user's specific request." }, { "title": "K3 data functions", "body": "These are the built-in functions for getting data into a workflow. Read\nreferences/node-types.md for full details on each.\n\nFunctionWhat it doesRead APICall any REST/GraphQL API — the most flexible optionRead Smart ContractQuery any smart contract directly on-chainRead Market DataGet token prices, volumes, market metricsRead WalletWallet balances, transfers, transaction historyRead NFTNFT collections, floor prices, traits, holdersRead GraphQuery TheGraph subgraphs with custom GraphQLRead DeploymentPull output from your own deployed code on K3AI Web ScraperExtract structured data from any web pageAI Agent with toolsAI that dynamically decides what to fetch" }, { "title": "How to find the data you need", "body": "The goal is to figure out the best way to get the specific data the user wants.\nThink of it as problem-solving — there are multiple valid approaches and you\nshould explore them:\n\nCheck what the team already has — call listTeamMcpServerIntegrations() to\nsee what MCP data sources are connected. If they have TheGraph, CoinGecko, or\nother integrations set up, those are the easiest path.\n\n\nSearch for existing templates — call findAgentByFunctionality() with the\nuser's intent. If someone already built a similar workflow, use it as a starting\npoint.\n\n\nThink about which K3 function fits:\n\nNeed on-chain contract data? → Read Smart Contract can query it directly\nNeed token prices or market data? → Read Market Data has it built in\nNeed complex DeFi metrics (TVL, volume, fees)? → Read Graph with the right\nsubgraph, or Read API to a protocol's analytics endpoint\nNeed wallet info? → Read Wallet for balances and history\nNeed NFT data? → Read NFT for collections and metadata\nNeed data from any public API? → Read API can call anything\nNeed to scrape a website? → AI Web Scraper can extract and structure it\n\n\n\nSearch the web for the right endpoint. If you need a specific protocol's data,\nlook up {protocol name} API, {protocol name} subgraph, or {protocol name} GraphQL endpoint. Many protocols publish public APIs and subgraphs.\n\n\nAsk the user — they may know the API endpoint, have an API key, or know\nexactly which smart contract to read from.\n\nThe key insight: there's rarely just one way to get the data. A Uniswap pool's TVL\ncould come from Read Graph (subgraph query), Read API (calling an analytics endpoint),\nor even Read Smart Contract (reading the pool contract directly). Pick whichever is\nmost reliable and gives you the data format you need." }, { "title": "Test before you build", "body": "Before constructing the full workflow, verify the data source actually returns\nwhat you expect:\n\n1. Create a minimal test workflow with generateWorkflow()\n — just a trigger + one data fetch step, nothing else\n2. Deploy and run it with executeWorkflow()\n3. Check the output with getWorkflowRunById() (set includeWorkflowData: true)\n4. If the data looks right → proceed to full build\n5. If empty or wrong → try a different approach and test again\n\nThis saves a lot of debugging later. A deployed workflow with bad data is worse\nthan no workflow." }, { "title": "Step 3: Build the Workflow", "body": "Now give the K3 orchestrator everything it needs. Use generateWorkflow() with\na detailed prompt that includes:\n\nTrigger type and schedule (e.g., \"runs daily\" or \"triggers on wallet activity\")\nData source and how to query it (e.g., \"use Read Graph to query pool X\" or\n\"use Read Smart Contract to get the pair's reserves\")\nWhat the AI should analyze (e.g., \"highlight TVL changes over 5%\")\nAny actions to take (e.g., \"execute a swap on Uniswap if condition is met\")\nHow to deliver results (e.g., \"send Telegram alert\" or \"email the report\")\nAny MCP integration IDs the orchestrator needs (from team integrations)\n\nSet deployWorkflow: false on the first call so you can review before deploying.\n\nThe orchestrator will likely ask follow-up questions — answer them using\neditGeneratedWorkflow() with the same generatedWorkflowId. This back-and-forth\nis normal; expect 2-4 rounds.\n\nOnce the configuration looks correct, call editGeneratedWorkflow() one final time\nwith deployWorkflow: true.\n\nFor the full list of available functions, triggers, AI models, and output options,\nread references/node-types.md." }, { "title": "Step 4: Deploy and Verify", "body": "After deploying:\n\nRun it manually with executeWorkflow() to trigger an immediate test\nCheck the run with getWorkflowRuns() or getWorkflowRunById()\nVerify the full chain: Did data fetch? Did AI analyze? Did notification send?\n\nIf something failed, use editGeneratedWorkflow() to fix it — you don't need to\nstart over. See references/troubleshooting.md for common issues.\n\nTell the user what happened: \"Your workflow is live and will run daily. I just ran\na test — here's what the first report looks like: [summary].\"" }, { "title": "K3 MCP Tool Reference", "body": "ToolWhat it doesgenerateWorkflowStart building a workflow from natural languageeditGeneratedWorkflowContinue the conversation with the orchestratorexecuteWorkflowRun a workflow manuallygetWorkflowByIdGet workflow details and configgetWorkflowRunsList execution historygetWorkflowRunByIdGet a specific run's details and outputupdateWorkflowPause/unpause a scheduled workflowfindAgentByFunctionalitySearch for existing workflow templateslistAgentTemplatesBrowse all available templatesgetAgentTemplateByIdGet details on a specific templatelistTeamMcpServerIntegrationsSee what data sources the team has connectedlistMcpServerIntegrationsBrowse all available MCP data sources" }, { "title": "Important Rules", "body": "Always test data sources before building the full workflow. A quick test\nfetch saves a lot of debugging time.\nThe orchestrator is conversational — expect multiple rounds of back-and-forth\nvia editGeneratedWorkflow. That's how it's designed to work.\nAsk the user for anything you can't look up — never guess email addresses,\nTelegram handles, or wallet addresses.\nDiscover team integrations — call listTeamMcpServerIntegrations() to see\nwhat's available. Every team is different.\nVerify workflows work before telling the user it's done. Run it, check the\noutput, confirm delivery.\nBe mindful of context — don't call many K3 MCP tools at once or dump large\nresponses. Fetch what you need, check it, move on.\nUse web search to find API endpoints, subgraph URLs, and smart contract\naddresses when you don't know them. The web is your research tool." }, { "title": "Going Deeper", "body": "references/node-types.md — All trigger types, data functions, AI functions,\nDeFi/trading actions, and notification options\nreferences/data-sources.md — How to discover and evaluate data sources for\ndifferent blockchain data needs\nreferences/workflow-patterns.md — Common workflow architectures and when to\nuse each one\nreferences/troubleshooting.md — Diagnosing and fixing common workflow issues" } ], "body": "K3 Blockchain Agent\n\nTransform requests like \"Send me daily updates about the WETH/USDC pool on Uniswap\" into fully deployed workflows that fetch data, run AI analysis, and deliver reports automatically.\n\nSetup\n\nThis skill requires the K3 Development MCP to be connected. The MCP provides tools like generateWorkflow, executeWorkflow, findAgentByFunctionality, and others that let you create and manage blockchain workflows programmatically.\n\nIf the K3 MCP isn't connected yet, tell the user they need to add it before proceeding. Once connected, verify by calling listTeamMcpServerIntegrations() — this confirms the connection and shows what data source integrations (TheGraph, CoinGecko, etc.) the user's team has wired up. Every team's integrations will be different — discover what's available rather than assuming.\n\nHow Workflow Building Works\n\nThe K3 orchestrator is conversational. You describe what you want in plain language, and the orchestrator asks clarifying questions, then builds and deploys the workflow. Your job is to show up with the right information so the conversation is productive.\n\nThe loop:\n\nUNDERSTAND → what does the user actually want?\nFIND DATA → how do we get that information into the workflow?\nTEST → does the data actually come back correctly?\nBUILD → give the orchestrator everything it needs\nDEPLOY → launch it and verify it works\n\n\nSkipping \"test\" is the most common mistake — you end up with a deployed workflow that returns empty data.\n\nStep 1: Understand the Request\n\nWhen a user asks for a workflow, figure out these parameters. Ask if anything is unclear — don't guess on addresses or emails.\n\nParameter\tWhat to find out\tExamples\nData target\tWhat blockchain data do they need?\tpool metrics, token price, wallet balance, NFT data\nProtocol\tWhich DeFi protocol or chain feature?\tUniswap, Aave, SushiSwap, native transfers\nChain\tWhich blockchain?\tEthereum, Arbitrum, Polygon, Base, Stellar\nSchedule\tHow often / what triggers it?\tdaily, hourly, on-demand, on wallet activity, on contract event, Telegram chatbot\nAnalysis\tWhat kind of insights?\tperformance summary, anomaly alerts, trend report, trade signal\nDelivery\tHow should results arrive?\temail, Telegram, Slack, Google Sheets\nActions\tShould the workflow do anything?\texecute a swap, transfer tokens, write to a contract\nSpecifics\tAny addresses or IDs?\tpool address, token contract, wallet address\n\nIf the user is new to DeFi, briefly explain relevant concepts as you go (what TVL means, what a liquidity pool is, etc.). Don't assume they know the jargon.\n\nStep 2: Find the Right Data\n\nThis is the critical step. K3 has many ways to get data into a workflow, and you need to figure out which approach works for the user's specific request.\n\nK3 data functions\n\nThese are the built-in functions for getting data into a workflow. Read references/node-types.md for full details on each.\n\nFunction\tWhat it does\nRead API\tCall any REST/GraphQL API — the most flexible option\nRead Smart Contract\tQuery any smart contract directly on-chain\nRead Market Data\tGet token prices, volumes, market metrics\nRead Wallet\tWallet balances, transfers, transaction history\nRead NFT\tNFT collections, floor prices, traits, holders\nRead Graph\tQuery TheGraph subgraphs with custom GraphQL\nRead Deployment\tPull output from your own deployed code on K3\nAI Web Scraper\tExtract structured data from any web page\nAI Agent with tools\tAI that dynamically decides what to fetch\nHow to find the data you need\n\nThe goal is to figure out the best way to get the specific data the user wants. Think of it as problem-solving — there are multiple valid approaches and you should explore them:\n\nCheck what the team already has — call listTeamMcpServerIntegrations() to see what MCP data sources are connected. If they have TheGraph, CoinGecko, or other integrations set up, those are the easiest path.\n\nSearch for existing templates — call findAgentByFunctionality() with the user's intent. If someone already built a similar workflow, use it as a starting point.\n\nThink about which K3 function fits:\n\nNeed on-chain contract data? → Read Smart Contract can query it directly\nNeed token prices or market data? → Read Market Data has it built in\nNeed complex DeFi metrics (TVL, volume, fees)? → Read Graph with the right subgraph, or Read API to a protocol's analytics endpoint\nNeed wallet info? → Read Wallet for balances and history\nNeed NFT data? → Read NFT for collections and metadata\nNeed data from any public API? → Read API can call anything\nNeed to scrape a website? → AI Web Scraper can extract and structure it\n\nSearch the web for the right endpoint. If you need a specific protocol's data, look up {protocol name} API, {protocol name} subgraph, or {protocol name} GraphQL endpoint. Many protocols publish public APIs and subgraphs.\n\nAsk the user — they may know the API endpoint, have an API key, or know exactly which smart contract to read from.\n\nThe key insight: there's rarely just one way to get the data. A Uniswap pool's TVL could come from Read Graph (subgraph query), Read API (calling an analytics endpoint), or even Read Smart Contract (reading the pool contract directly). Pick whichever is most reliable and gives you the data format you need.\n\nTest before you build\n\nBefore constructing the full workflow, verify the data source actually returns what you expect:\n\n1. Create a minimal test workflow with generateWorkflow()\n — just a trigger + one data fetch step, nothing else\n2. Deploy and run it with executeWorkflow()\n3. Check the output with getWorkflowRunById() (set includeWorkflowData: true)\n4. If the data looks right → proceed to full build\n5. If empty or wrong → try a different approach and test again\n\n\nThis saves a lot of debugging later. A deployed workflow with bad data is worse than no workflow.\n\nStep 3: Build the Workflow\n\nNow give the K3 orchestrator everything it needs. Use generateWorkflow() with a detailed prompt that includes:\n\nTrigger type and schedule (e.g., \"runs daily\" or \"triggers on wallet activity\")\nData source and how to query it (e.g., \"use Read Graph to query pool X\" or \"use Read Smart Contract to get the pair's reserves\")\nWhat the AI should analyze (e.g., \"highlight TVL changes over 5%\")\nAny actions to take (e.g., \"execute a swap on Uniswap if condition is met\")\nHow to deliver results (e.g., \"send Telegram alert\" or \"email the report\")\nAny MCP integration IDs the orchestrator needs (from team integrations)\n\nSet deployWorkflow: false on the first call so you can review before deploying.\n\nThe orchestrator will likely ask follow-up questions — answer them using editGeneratedWorkflow() with the same generatedWorkflowId. This back-and-forth is normal; expect 2-4 rounds.\n\nOnce the configuration looks correct, call editGeneratedWorkflow() one final time with deployWorkflow: true.\n\nFor the full list of available functions, triggers, AI models, and output options, read references/node-types.md.\n\nStep 4: Deploy and Verify\n\nAfter deploying:\n\nRun it manually with executeWorkflow() to trigger an immediate test\nCheck the run with getWorkflowRuns() or getWorkflowRunById()\nVerify the full chain: Did data fetch? Did AI analyze? Did notification send?\n\nIf something failed, use editGeneratedWorkflow() to fix it — you don't need to start over. See references/troubleshooting.md for common issues.\n\nTell the user what happened: \"Your workflow is live and will run daily. I just ran a test — here's what the first report looks like: [summary].\"\n\nK3 MCP Tool Reference\nTool\tWhat it does\ngenerateWorkflow\tStart building a workflow from natural language\neditGeneratedWorkflow\tContinue the conversation with the orchestrator\nexecuteWorkflow\tRun a workflow manually\ngetWorkflowById\tGet workflow details and config\ngetWorkflowRuns\tList execution history\ngetWorkflowRunById\tGet a specific run's details and output\nupdateWorkflow\tPause/unpause a scheduled workflow\nfindAgentByFunctionality\tSearch for existing workflow templates\nlistAgentTemplates\tBrowse all available templates\ngetAgentTemplateById\tGet details on a specific template\nlistTeamMcpServerIntegrations\tSee what data sources the team has connected\nlistMcpServerIntegrations\tBrowse all available MCP data sources\nImportant Rules\nAlways test data sources before building the full workflow. A quick test fetch saves a lot of debugging time.\nThe orchestrator is conversational — expect multiple rounds of back-and-forth via editGeneratedWorkflow. That's how it's designed to work.\nAsk the user for anything you can't look up — never guess email addresses, Telegram handles, or wallet addresses.\nDiscover team integrations — call listTeamMcpServerIntegrations() to see what's available. Every team is different.\nVerify workflows work before telling the user it's done. Run it, check the output, confirm delivery.\nBe mindful of context — don't call many K3 MCP tools at once or dump large responses. Fetch what you need, check it, move on.\nUse web search to find API endpoints, subgraph URLs, and smart contract addresses when you don't know them. The web is your research tool.\nGoing Deeper\nreferences/node-types.md — All trigger types, data functions, AI functions, DeFi/trading actions, and notification options\nreferences/data-sources.md — How to discover and evaluate data sources for different blockchain data needs\nreferences/workflow-patterns.md — Common workflow architectures and when to use each one\nreferences/troubleshooting.md — Diagnosing and fixing common workflow issues" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/alexgrankinukr-hash/k3-blockchain-agent", "publisherUrl": "https://clawhub.ai/alexgrankinukr-hash/k3-blockchain-agent", "owner": "alexgrankinukr-hash", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/k3-blockchain-agent", "downloadUrl": "https://openagent3.xyz/downloads/k3-blockchain-agent", "agentUrl": "https://openagent3.xyz/skills/k3-blockchain-agent/agent", "manifestUrl": "https://openagent3.xyz/skills/k3-blockchain-agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/k3-blockchain-agent/agent.md" } }