{ "schemaVersion": "1.0", "item": { "slug": "pond3r-skill", "name": "Pond3r Skill - Query Onchain Data", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/fabriziogianni7/pond3r-skill", "canonicalUrl": "https://clawhub.ai/fabriziogianni7/pond3r-skill", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/pond3r-skill", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pond3r-skill", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "reference.md", "SKILL.md", "scripts/query.mjs", "scripts/client.mjs", "scripts/list-datasets.mjs", "scripts/package.json" ], "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/pond3r-skill" }, "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/pond3r-skill", "agentPageUrl": "https://openagent3.xyz/skills/pond3r-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/pond3r-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/pond3r-skill/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": "Pond3r Crypto Intelligence Skill", "body": "Use this skill when the agent needs to query crypto/DeFi data: yields, protocol metrics, token opportunities, market analysis, or blockchain analytics. Pond3r provides an MCP server with read-only SQL access to curated datasets." }, { "title": "Prerequisites", "body": "API key: Obtain at makeit.pond3r.xyz/api-keys\nMCP setup: Pond3r must be configured as an MCP server in the runtime (Claude Code, Cursor, Claude Desktop, etc.)" }, { "title": "Setup: Where Is the Agent Running?", "body": "The agent needs MCP tools (list_datasets, get_schema, query) to use Pond3r. Those tools come from the runtime that executes the agent — not from the skill or env vars alone.\n\nRuntimeHow to enable Pond3rCursorCursor Settings → MCP Servers → Add server (URL + Authorization header). See MCP Connection below.Claude DesktopAdd Pond3r to claude_desktop_config.json under mcpServers. Restart Claude.Claude CodeRun claude mcp add pond3r-data ... (see below).OpenClaw (Docker/Telegram)Use the CLI scripts below. They call Pond3r MCP via HTTP. Set POND3R_API_KEY in .env; the agent runs the scripts and parses JSON output.\n\nNo extra info for the agent — the skill is enough. For runtimes with native MCP, add the API key in the MCP server config. For OpenClaw, use the scripts and POND3R_API_KEY in env." }, { "title": "MCP Connection", "body": "SettingValueURLhttps://mcp.pond3r.xyz/mcpTransportStreamable HTTPAuthAuthorization: Bearer " }, { "title": "Cursor", "body": "Open Cursor → Settings (⌘+,) → MCP\nClick Add new MCP server\nConfigure:\n\nURL: https://mcp.pond3r.xyz/mcp\nHeaders: Authorization: Bearer \n\nReplace with your key from makeit.pond3r.xyz/api-keys\nSome clients support Authorization: Bearer ${POND3R_API_KEY} if that env var is set\n\n\n\n\nSave and restart Cursor so tools load\nVerify: start a new chat and ask for stablecoin yields — the agent should call list_datasets, get_schema, query" }, { "title": "Claude Code", "body": "claude mcp add pond3r-data \\\n --transport http \\\n https://mcp.pond3r.xyz/mcp \\\n --header \"Authorization: Bearer \"" }, { "title": "Claude Desktop (claude_desktop_config.json)", "body": "{\n \"mcpServers\": {\n \"pond3r\": {\n \"type\": \"http\",\n \"url\": \"https://mcp.pond3r.xyz/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer \"\n }\n }\n }\n}" }, { "title": "CLI Scripts (OpenClaw / Any Runtime)", "body": "When MCP tools are not available (e.g. OpenClaw/Telegram), use these scripts. They call Pond3r MCP over HTTP. Requires POND3R_API_KEY in env (e.g. in .env loaded by docker-compose).\n\nScripts live at /opt/pond3r-skill-scripts/ in the Docker image. When running locally, use ceo-agent/skills/pond3r-skill/scripts/ or the workspace-relative path." }, { "title": "1) List datasets", "body": "node /opt/pond3r-skill-scripts/list-datasets.mjs\n\nOutput: JSON with all datasets and tables." }, { "title": "2) Get schema for a dataset", "body": "node /opt/pond3r-skill-scripts/get-schema.mjs --dataset-id " }, { "title": "3) Run a SQL query", "body": "node /opt/pond3r-skill-scripts/query.mjs --dataset-id --sql \"SELECT * FROM stablecoin_yields LIMIT 10\"\n\nOr from file:\n\nnode /opt/pond3r-skill-scripts/query.mjs --sql-file /tmp/query.sql" }, { "title": "Script workflow", "body": "Run list-datasets.mjs to discover datasets and table names.\nRun get-schema.mjs --dataset-id to see columns and types.\nRun query.mjs --dataset-id --sql \"SELECT ...\" with valid SQL (SELECT only, bare table names, LIMIT where appropriate).\nParse the JSON output and summarize for the user." }, { "title": "Failure handling", "body": "Missing required env var: POND3R_API_KEY → Add POND3R_API_KEY to .env and ensure it is loaded (e.g. docker-compose env_file: .env).\nPond3r MCP HTTP 401 → Invalid or expired API key; rotate key at makeit.pond3r.xyz/api-keys.\nPond3r MCP error: ... → Check SQL syntax, table names, and row limits." }, { "title": "Available Tools (Native MCP)", "body": "ToolPurposelist_datasetsList all datasets and their tablesget_schemaGet column names, types, descriptions for a datasetqueryExecute read-only SQL against a dataset" }, { "title": "Query Rules", "body": "SELECT only — write operations are not allowed\nBare table names — use SELECT * FROM stablecoin_yields, not fully qualified paths\nResults capped at 10,000 rows — use LIMIT or WHERE filters for large datasets\nCost estimation — queries exceeding tier limits are rejected before running" }, { "title": "Use Cases", "body": "Protocol Intelligence\n\nTrack AI agent launches, token graduations, protocol metrics\nDaily yield farming reports across Aave, Compound, Convex\n\n\n\nMarket Opportunity Detection\n\nNew tokens on Uniswap with rising liquidity\nTokens with <$500K market cap and rising liquidity\nPolymarket trades with highest volume\n\n\n\nRisk-Adjusted Analysis\n\nMulti-dimensional risk scoring (volatility, liquidity, market structure)\nLiquidation risk monitoring for DeFi positions\nWhale activity tracking\n\n\n\nCross-Protocol & Cross-Chain\n\nCompare USDC yields across Aave and Compound on Arbitrum\nBridge volume analysis, ecosystem health comparison\nArbitrage opportunity detection\n\n\n\nStructured Data for Decisions\n\nStatistical analysis, trend identification\nVolume pattern analysis, unusual trading activity\nSentiment scoring (Farcaster, influencer activity)" }, { "title": "Example Queries (Natural Language → SQL)", "body": "Agent asks in natural language; MCP tools discover schema and execute SQL. Example prompts:\n\n\"What are the top 5 stablecoin yields on Ethereum right now?\"\n\"Show me Polymarket trades from the last 24 hours with the highest volume.\"\n\"Compare USDC yields across Aave and Compound on Arbitrum.\"" }, { "title": "Workflow", "body": "Discover available data: Call list_datasets to see datasets and tables\nUnderstand schema: Call get_schema for the dataset you need\nWrite and run: Use query with valid SQL (SELECT, bare table names, LIMIT where appropriate)\nInterpret results: Use returned data for analysis, proposals, or decisions" }, { "title": "Runtime Enforcement (Mandatory)", "body": "Before answering with Pond3r-backed data:\n\nPrefer scripts when MCP tools are unavailable:\n\nIf list_datasets, get_schema, query are not exposed by the runtime, use the CLI scripts instead.\nRun node /opt/pond3r-skill-scripts/list-datasets.mjs (or workspace path) with POND3R_API_KEY in env.\n\n\nIf neither MCP nor scripts work:\n\nStop and return: Pond3r unavailable: MCP tools missing and scripts failed (check POND3R_API_KEY in env).\n\n\nDo not assume fallback permission:\n\nDo not switch to web_search, web_fetch, or other sources unless the user explicitly approves fallback.\n\n\nReturn execution evidence:\n\nInclude the exact commands run and summarize returned dataset/query output.\nIf a call fails, include the exact error message and next remediation step." }, { "title": "Troubleshooting", "body": "SymptomFix\"Pond3r MCP not configured\"Add MCP server in your runtime (Cursor/Claude) with URL + Bearer header. Restart.Tools still missing after configRestart the app (Cursor/Claude). MCP loads at startup.Agent runs in OpenClaw/TelegramUse the CLI scripts with POND3R_API_KEY in .env. See CLI Scripts.Auth/401 errorsCheck API key is valid, not expired. Rotate if it was ever exposed." }, { "title": "Failure Handling", "body": "If MCP tools are unavailable, provide only:\n\nmissing tool names\nrequired server URL (https://mcp.pond3r.xyz/mcp)\nrequired auth header format (Authorization: Bearer )\n\n\nIf SQL is rejected (tier/cost/limits), rewrite with tighter WHERE/LIMIT and retry.\nIf access/auth fails, report authorization/configuration failure and request key/server verification." }, { "title": "Report API (Alternative to MCP)", "body": "For scheduled reports and structured JSON delivery, use the REST API:\n\nCreate report: POST https://api.pond3r.xyz/v1/api/reports with description, schedule, delivery_format\nGet latest: GET https://api.pond3r.xyz/v1/api/reports/{reportId}/latest\nHeaders: x-api-key: \n\nReport format includes executiveSummary, analysis, opportunities. For full API details and response structure, see reference.md." }, { "title": "Security", "body": "Never expose API keys in client-side code or public repositories\nUse environment variables for API keys\nMCP tools are read-only; no writes to Pond3r datasets\nNever print secret values in logs, chat, or command output (only report presence/absence)\nIf a secret is accidentally exposed, instruct immediate key rotation before continuing" } ], "body": "Pond3r Crypto Intelligence Skill\n\nUse this skill when the agent needs to query crypto/DeFi data: yields, protocol metrics, token opportunities, market analysis, or blockchain analytics. Pond3r provides an MCP server with read-only SQL access to curated datasets.\n\nPrerequisites\nAPI key: Obtain at makeit.pond3r.xyz/api-keys\nMCP setup: Pond3r must be configured as an MCP server in the runtime (Claude Code, Cursor, Claude Desktop, etc.)\nSetup: Where Is the Agent Running?\n\nThe agent needs MCP tools (list_datasets, get_schema, query) to use Pond3r. Those tools come from the runtime that executes the agent — not from the skill or env vars alone.\n\nRuntime\tHow to enable Pond3r\nCursor\tCursor Settings → MCP Servers → Add server (URL + Authorization header). See MCP Connection below.\nClaude Desktop\tAdd Pond3r to claude_desktop_config.json under mcpServers. Restart Claude.\nClaude Code\tRun claude mcp add pond3r-data ... (see below).\nOpenClaw (Docker/Telegram)\tUse the CLI scripts below. They call Pond3r MCP via HTTP. Set POND3R_API_KEY in .env; the agent runs the scripts and parses JSON output.\n\nNo extra info for the agent — the skill is enough. For runtimes with native MCP, add the API key in the MCP server config. For OpenClaw, use the scripts and POND3R_API_KEY in env.\n\nMCP Connection\nSetting\tValue\nURL\thttps://mcp.pond3r.xyz/mcp\nTransport\tStreamable HTTP\nAuth\tAuthorization: Bearer \nCursor\nOpen Cursor → Settings (⌘+,) → MCP\nClick Add new MCP server\nConfigure:\nURL: https://mcp.pond3r.xyz/mcp\nHeaders: Authorization: Bearer \nReplace with your key from makeit.pond3r.xyz/api-keys\nSome clients support Authorization: Bearer ${POND3R_API_KEY} if that env var is set\nSave and restart Cursor so tools load\nVerify: start a new chat and ask for stablecoin yields — the agent should call list_datasets, get_schema, query\nClaude Code\nclaude mcp add pond3r-data \\\n --transport http \\\n https://mcp.pond3r.xyz/mcp \\\n --header \"Authorization: Bearer \"\n\nClaude Desktop (claude_desktop_config.json)\n{\n \"mcpServers\": {\n \"pond3r\": {\n \"type\": \"http\",\n \"url\": \"https://mcp.pond3r.xyz/mcp\",\n \"headers\": {\n \"Authorization\": \"Bearer \"\n }\n }\n }\n}\n\nCLI Scripts (OpenClaw / Any Runtime)\n\nWhen MCP tools are not available (e.g. OpenClaw/Telegram), use these scripts. They call Pond3r MCP over HTTP. Requires POND3R_API_KEY in env (e.g. in .env loaded by docker-compose).\n\nScripts live at /opt/pond3r-skill-scripts/ in the Docker image. When running locally, use ceo-agent/skills/pond3r-skill/scripts/ or the workspace-relative path.\n\n1) List datasets\nnode /opt/pond3r-skill-scripts/list-datasets.mjs\n\n\nOutput: JSON with all datasets and tables.\n\n2) Get schema for a dataset\nnode /opt/pond3r-skill-scripts/get-schema.mjs --dataset-id \n\n3) Run a SQL query\nnode /opt/pond3r-skill-scripts/query.mjs --dataset-id --sql \"SELECT * FROM stablecoin_yields LIMIT 10\"\n\n\nOr from file:\n\nnode /opt/pond3r-skill-scripts/query.mjs --sql-file /tmp/query.sql\n\nScript workflow\nRun list-datasets.mjs to discover datasets and table names.\nRun get-schema.mjs --dataset-id to see columns and types.\nRun query.mjs --dataset-id --sql \"SELECT ...\" with valid SQL (SELECT only, bare table names, LIMIT where appropriate).\nParse the JSON output and summarize for the user.\nFailure handling\nMissing required env var: POND3R_API_KEY → Add POND3R_API_KEY to .env and ensure it is loaded (e.g. docker-compose env_file: .env).\nPond3r MCP HTTP 401 → Invalid or expired API key; rotate key at makeit.pond3r.xyz/api-keys.\nPond3r MCP error: ... → Check SQL syntax, table names, and row limits.\nAvailable Tools (Native MCP)\nTool\tPurpose\nlist_datasets\tList all datasets and their tables\nget_schema\tGet column names, types, descriptions for a dataset\nquery\tExecute read-only SQL against a dataset\nQuery Rules\nSELECT only — write operations are not allowed\nBare table names — use SELECT * FROM stablecoin_yields, not fully qualified paths\nResults capped at 10,000 rows — use LIMIT or WHERE filters for large datasets\nCost estimation — queries exceeding tier limits are rejected before running\nUse Cases\n\nProtocol Intelligence\n\nTrack AI agent launches, token graduations, protocol metrics\nDaily yield farming reports across Aave, Compound, Convex\n\nMarket Opportunity Detection\n\nNew tokens on Uniswap with rising liquidity\nTokens with <$500K market cap and rising liquidity\nPolymarket trades with highest volume\n\nRisk-Adjusted Analysis\n\nMulti-dimensional risk scoring (volatility, liquidity, market structure)\nLiquidation risk monitoring for DeFi positions\nWhale activity tracking\n\nCross-Protocol & Cross-Chain\n\nCompare USDC yields across Aave and Compound on Arbitrum\nBridge volume analysis, ecosystem health comparison\nArbitrage opportunity detection\n\nStructured Data for Decisions\n\nStatistical analysis, trend identification\nVolume pattern analysis, unusual trading activity\nSentiment scoring (Farcaster, influencer activity)\nExample Queries (Natural Language → SQL)\n\nAgent asks in natural language; MCP tools discover schema and execute SQL. Example prompts:\n\n\"What are the top 5 stablecoin yields on Ethereum right now?\"\n\"Show me Polymarket trades from the last 24 hours with the highest volume.\"\n\"Compare USDC yields across Aave and Compound on Arbitrum.\"\nWorkflow\nDiscover available data: Call list_datasets to see datasets and tables\nUnderstand schema: Call get_schema for the dataset you need\nWrite and run: Use query with valid SQL (SELECT, bare table names, LIMIT where appropriate)\nInterpret results: Use returned data for analysis, proposals, or decisions\nRuntime Enforcement (Mandatory)\n\nBefore answering with Pond3r-backed data:\n\nPrefer scripts when MCP tools are unavailable:\nIf list_datasets, get_schema, query are not exposed by the runtime, use the CLI scripts instead.\nRun node /opt/pond3r-skill-scripts/list-datasets.mjs (or workspace path) with POND3R_API_KEY in env.\nIf neither MCP nor scripts work:\nStop and return: Pond3r unavailable: MCP tools missing and scripts failed (check POND3R_API_KEY in env).\nDo not assume fallback permission:\nDo not switch to web_search, web_fetch, or other sources unless the user explicitly approves fallback.\nReturn execution evidence:\nInclude the exact commands run and summarize returned dataset/query output.\nIf a call fails, include the exact error message and next remediation step.\nTroubleshooting\nSymptom\tFix\n\"Pond3r MCP not configured\"\tAdd MCP server in your runtime (Cursor/Claude) with URL + Bearer header. Restart.\nTools still missing after config\tRestart the app (Cursor/Claude). MCP loads at startup.\nAgent runs in OpenClaw/Telegram\tUse the CLI scripts with POND3R_API_KEY in .env. See CLI Scripts.\nAuth/401 errors\tCheck API key is valid, not expired. Rotate if it was ever exposed.\nFailure Handling\nIf MCP tools are unavailable, provide only:\nmissing tool names\nrequired server URL (https://mcp.pond3r.xyz/mcp)\nrequired auth header format (Authorization: Bearer )\nIf SQL is rejected (tier/cost/limits), rewrite with tighter WHERE/LIMIT and retry.\nIf access/auth fails, report authorization/configuration failure and request key/server verification.\nReport API (Alternative to MCP)\n\nFor scheduled reports and structured JSON delivery, use the REST API:\n\nCreate report: POST https://api.pond3r.xyz/v1/api/reports with description, schedule, delivery_format\nGet latest: GET https://api.pond3r.xyz/v1/api/reports/{reportId}/latest\nHeaders: x-api-key: \n\nReport format includes executiveSummary, analysis, opportunities. For full API details and response structure, see reference.md.\n\nSecurity\nNever expose API keys in client-side code or public repositories\nUse environment variables for API keys\nMCP tools are read-only; no writes to Pond3r datasets\nNever print secret values in logs, chat, or command output (only report presence/absence)\nIf a secret is accidentally exposed, instruct immediate key rotation before continuing" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/fabriziogianni7/pond3r-skill", "publisherUrl": "https://clawhub.ai/fabriziogianni7/pond3r-skill", "owner": "fabriziogianni7", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/pond3r-skill", "downloadUrl": "https://openagent3.xyz/downloads/pond3r-skill", "agentUrl": "https://openagent3.xyz/skills/pond3r-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/pond3r-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/pond3r-skill/agent.md" } }