{
  "schemaVersion": "1.0",
  "item": {
    "slug": "dexter",
    "name": "dexter",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/igorhvr/dexter",
    "canonicalUrl": "https://clawhub.ai/igorhvr/dexter",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/dexter",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=dexter",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/dexter"
    },
    "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/dexter",
    "agentPageUrl": "https://openagent3.xyz/skills/dexter/agent",
    "manifestUrl": "https://openagent3.xyz/skills/dexter/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/dexter/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": "Dexter Skill (Clawdbot)",
        "body": "Dexter is an autonomous financial research agent that plans, executes, and synthesizes financial data analysis. Use it for any financial research question involving stocks, crypto, company fundamentals, or market data."
      },
      {
        "title": "When to Use Dexter",
        "body": "Use Dexter for:\n\nStock prices (current and historical)\nFinancial statements (income, balance sheet, cash flow)\nFinancial metrics (P/E, P/B, margins, market cap, etc.)\nSEC filings (10-K, 10-Q, 8-K)\nAnalyst estimates\nInsider trades\nCompany news\nCrypto prices\nComparative financial analysis\nRevenue trends and growth rates\n\nNote: Dexter's Financial Datasets API covers primarily US stocks. For international stocks (like European exchanges), it falls back to web search via Tavily."
      },
      {
        "title": "Installation",
        "body": "If Dexter is not installed, follow these steps:"
      },
      {
        "title": "1. Clone and Install",
        "body": "DEXTER_DIR=\"/root/clawd-workspace/dexter\"\n\n# Clone if not exists\nif [ ! -d \"$DEXTER_DIR\" ]; then\n  git clone https://github.com/virattt/dexter.git \"$DEXTER_DIR\"\nfi\n\ncd \"$DEXTER_DIR\"\n\n# Install dependencies\nbun install"
      },
      {
        "title": "2. Configure API Keys",
        "body": "Create .env file with required API keys:\n\ncat > \"$DEXTER_DIR/.env\" << 'EOF'\n# LLM API Keys (at least one required)\nANTHROPIC_API_KEY=your-anthropic-key\n\n# Stock Market API Key - Get from https://financialdatasets.ai\nFINANCIAL_DATASETS_API_KEY=your-financial-datasets-key\n\n# Web Search API Key - Get from https://tavily.com (optional but recommended)\nTAVILY_API_KEY=your-tavily-key\nEOF\n\nAPI Key Sources:\n\nAnthropic: https://console.anthropic.com/\nFinancial Datasets: https://financialdatasets.ai (free tier available)\nTavily: https://tavily.com (optional, for web search fallback)"
      },
      {
        "title": "3. Patch for Anthropic-Only Usage",
        "body": "Dexter's tool executor defaults to OpenAI's gpt-5-mini. If using Anthropic only, patch it:\n\n# Fix hardcoded OpenAI model in tool-executor.ts\nsed -i \"s/const SMALL_MODEL = 'gpt-5-mini';/const SMALL_MODEL = 'claude-3-5-haiku-latest';/\" \\\n  \"$DEXTER_DIR/src/agent/tool-executor.ts\""
      },
      {
        "title": "4. Configure Model Settings",
        "body": "Set Claude as the default model:\n\nmkdir -p \"$DEXTER_DIR/.dexter\"\ncat > \"$DEXTER_DIR/.dexter/settings.json\" << 'EOF'\n{\n  \"provider\": \"anthropic\",\n  \"modelId\": \"claude-sonnet-4-5\"\n}\nEOF"
      },
      {
        "title": "5. Create Non-Interactive Query Script",
        "body": "cat > \"$DEXTER_DIR/query.ts\" << 'SCRIPT'\n#!/usr/bin/env bun\n/**\n * Non-interactive Dexter query runner\n * Usage: bun query.ts \"What is Apple's revenue growth?\"\n */\nimport { config } from 'dotenv';\nimport { Agent } from './src/agent/orchestrator.js';\nimport { getSetting } from './src/utils/config.js';\n\nconfig({ quiet: true });\n\nconst query = process.argv[2];\nif (!query) {\n  console.error('Usage: bun query.ts \"Your financial question here\"');\n  process.exit(1);\n}\n\nconst model = getSetting('modelId', 'claude-sonnet-4-5') as string;\n\nasync function runQuery() {\n  let answer = '';\n  \n  const agent = new Agent({\n    model,\n    callbacks: {\n      onPhaseStart: (phase) => {\n        if (process.env.DEXTER_VERBOSE) {\n          console.error(`[Phase: ${phase}]`);\n        }\n      },\n      onPlanCreated: (plan) => {\n        if (process.env.DEXTER_VERBOSE) {\n          console.error(`[Tasks: ${plan.tasks.map(t => t.description).join(', ')}]`);\n        }\n      },\n      onAnswerStream: async (stream) => {\n        for await (const chunk of stream) {\n          answer += chunk;\n          process.stdout.write(chunk);\n        }\n      },\n    },\n  });\n\n  try {\n    await agent.run(query);\n    if (!answer.endsWith('\\n')) {\n      console.log();\n    }\n  } catch (error) {\n    console.error('Error:', error);\n    process.exit(1);\n  }\n}\n\nrunQuery();\nSCRIPT"
      },
      {
        "title": "Full One-Shot Installation",
        "body": "Complete installation script (requires API keys as environment variables):\n\n#!/bin/bash\nset -e\n\nDEXTER_DIR=\"/root/clawd-workspace/dexter\"\n\n# Clone\n[ ! -d \"$DEXTER_DIR\" ] && git clone https://github.com/virattt/dexter.git \"$DEXTER_DIR\"\ncd \"$DEXTER_DIR\"\n\n# Install deps\nbun install\n\n# Create .env (set these variables before running)\ncat > .env << EOF\nANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-your-key-here}\nFINANCIAL_DATASETS_API_KEY=${FINANCIAL_DATASETS_API_KEY:-your-key-here}\nTAVILY_API_KEY=${TAVILY_API_KEY:-your-key-here}\nEOF\n\n# Patch for Anthropic\nsed -i \"s/const SMALL_MODEL = 'gpt-5-mini';/const SMALL_MODEL = 'claude-3-5-haiku-latest';/\" \\\n  src/agent/tool-executor.ts\n\n# Set model config\nmkdir -p .dexter\necho '{\"provider\":\"anthropic\",\"modelId\":\"claude-sonnet-4-5\"}' > .dexter/settings.json\n\necho \"Dexter installed successfully!\""
      },
      {
        "title": "Location",
        "body": "/root/clawd-workspace/dexter"
      },
      {
        "title": "Quick Query (Non-Interactive)",
        "body": "For quick financial questions, use the query script:\n\ncd /root/clawd-workspace/dexter && bun query.ts \"Your financial question here\"\n\nExamples:\n\nbun query.ts \"What is Apple's current P/E ratio?\"\nbun query.ts \"Compare Microsoft and Google revenue growth over the last 4 quarters\"\nbun query.ts \"What was Tesla's free cash flow in 2025?\"\nbun query.ts \"Show me insider trades for NVDA in the last 30 days\"\nbun query.ts \"What is Bitcoin's price trend over the last week?\"\n\nFor verbose output (shows planning steps):\n\nDEXTER_VERBOSE=1 bun query.ts \"Your question\""
      },
      {
        "title": "Interactive Mode (Complex Research)",
        "body": "For multi-turn research sessions or follow-up questions, use the interactive CLI via tmux:\n\nSOCKET_DIR=\"${CLAWDBOT_TMUX_SOCKET_DIR:-${TMPDIR:-/tmp}/clawdbot-tmux-sockets}\"\nSOCKET=\"$SOCKET_DIR/clawdbot.sock\"\nSESSION=dexter\n\n# Start Dexter (if not running)\ntmux -S \"$SOCKET\" kill-session -t \"$SESSION\" 2>/dev/null || true\ntmux -S \"$SOCKET\" new -d -s \"$SESSION\" -n shell -c /root/clawd-workspace/dexter\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- 'bun start' Enter\nsleep 3\n\n# Send a query\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -l -- 'Your question here'\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 Enter\n\n# Check output\ntmux -S \"$SOCKET\" capture-pane -p -J -t \"$SESSION\":0.0 -S -200"
      },
      {
        "title": "Available Tools (Under the Hood)",
        "body": "Dexter automatically selects and uses these tools based on your query:"
      },
      {
        "title": "Financial Statements",
        "body": "get_income_statements - Revenue, expenses, net income\nget_balance_sheets - Assets, liabilities, equity\nget_cash_flow_statements - Operating, investing, financing cash flows\nget_all_financial_statements - All three in one call"
      },
      {
        "title": "Prices",
        "body": "get_price_snapshot - Current stock price\nget_prices - Historical price data"
      },
      {
        "title": "Crypto",
        "body": "get_crypto_price_snapshot - Current crypto price (e.g., BTC-USD)\nget_crypto_prices - Historical crypto prices\nget_available_crypto_tickers - List available crypto tickers"
      },
      {
        "title": "Metrics",
        "body": "get_financial_metrics_snapshot - Current metrics (P/E, market cap, etc.)\nget_financial_metrics - Historical metrics"
      },
      {
        "title": "SEC Filings",
        "body": "get_10k_filing_items - Annual report sections\nget_10q_filing_items - Quarterly report sections\nget_8k_filing_items - Current report items\nget_filings - List of all filings"
      },
      {
        "title": "Other Data",
        "body": "get_analyst_estimates - Earnings/revenue estimates\nget_segmented_revenues - Revenue by segment\nget_insider_trades - Insider buying/selling\nget_news - Company news\nsearch_web - Web search (via Tavily) for general info"
      },
      {
        "title": "Agent Architecture",
        "body": "Dexter uses a multi-phase approach:\n\nUnderstand: Extract intent, tickers, and time periods from query\nPlan: Create task list with dependencies\nExecute: Run tasks in parallel where possible\nReflect: Evaluate if more data is needed (iterates up to 5x)\nAnswer: Synthesize comprehensive response with sources"
      },
      {
        "title": "Example Queries",
        "body": "Stock Analysis:\n\n\"What is AAPL's revenue growth over the last 4 quarters?\"\n\"Compare MSFT and GOOG operating margins for 2025\"\n\"What was AMZN's debt-to-equity ratio last quarter?\"\n\nFinancial Health:\n\n\"Is NVDA's cash flow positive? Show me the trend\"\n\"What are Tesla's profit margins compared to Ford?\"\n\nSEC Filings:\n\n\"Summarize Apple's most recent 10-K risk factors\"\n\"What did Meta disclose in their latest 8-K?\"\n\nCrypto:\n\n\"What is Ethereum's price today?\"\n\"Show Bitcoin's price movement over the last month\"\n\nMarket Research:\n\n\"What are analyst estimates for Amazon's next quarter earnings?\"\n\"Show me recent insider trades for Microsoft\""
      },
      {
        "title": "\"Missing credentials... OPENAI_API_KEY\"",
        "body": "Run the Anthropic patch (step 3 in installation) - Dexter's tool executor defaults to OpenAI."
      },
      {
        "title": "API errors for non-US stocks",
        "body": "Financial Datasets API primarily covers US stocks. Dexter will fall back to Tavily web search for international stocks if TAVILY_API_KEY is configured."
      },
      {
        "title": "Slow responses",
        "body": "Complex queries may take 30-60 seconds. Dexter plans, executes multiple API calls, reflects on results, and synthesizes answers."
      },
      {
        "title": "Tips",
        "body": "Be specific: Include ticker symbols and time periods when known\nUS stocks work best: The Financial Datasets API has comprehensive US coverage\nInternational stocks: Dexter falls back to web search for non-US stocks\nCrypto format: Use BTC-USD, ETH-USD format for crypto tickers\nTimeout: Complex queries may take 30-60 seconds as Dexter plans and executes multiple tasks"
      }
    ],
    "body": "Dexter Skill (Clawdbot)\n\nDexter is an autonomous financial research agent that plans, executes, and synthesizes financial data analysis. Use it for any financial research question involving stocks, crypto, company fundamentals, or market data.\n\nWhen to Use Dexter\n\nUse Dexter for:\n\nStock prices (current and historical)\nFinancial statements (income, balance sheet, cash flow)\nFinancial metrics (P/E, P/B, margins, market cap, etc.)\nSEC filings (10-K, 10-Q, 8-K)\nAnalyst estimates\nInsider trades\nCompany news\nCrypto prices\nComparative financial analysis\nRevenue trends and growth rates\n\nNote: Dexter's Financial Datasets API covers primarily US stocks. For international stocks (like European exchanges), it falls back to web search via Tavily.\n\nInstallation\n\nIf Dexter is not installed, follow these steps:\n\n1. Clone and Install\nDEXTER_DIR=\"/root/clawd-workspace/dexter\"\n\n# Clone if not exists\nif [ ! -d \"$DEXTER_DIR\" ]; then\n  git clone https://github.com/virattt/dexter.git \"$DEXTER_DIR\"\nfi\n\ncd \"$DEXTER_DIR\"\n\n# Install dependencies\nbun install\n\n2. Configure API Keys\n\nCreate .env file with required API keys:\n\ncat > \"$DEXTER_DIR/.env\" << 'EOF'\n# LLM API Keys (at least one required)\nANTHROPIC_API_KEY=your-anthropic-key\n\n# Stock Market API Key - Get from https://financialdatasets.ai\nFINANCIAL_DATASETS_API_KEY=your-financial-datasets-key\n\n# Web Search API Key - Get from https://tavily.com (optional but recommended)\nTAVILY_API_KEY=your-tavily-key\nEOF\n\n\nAPI Key Sources:\n\nAnthropic: https://console.anthropic.com/\nFinancial Datasets: https://financialdatasets.ai (free tier available)\nTavily: https://tavily.com (optional, for web search fallback)\n3. Patch for Anthropic-Only Usage\n\nDexter's tool executor defaults to OpenAI's gpt-5-mini. If using Anthropic only, patch it:\n\n# Fix hardcoded OpenAI model in tool-executor.ts\nsed -i \"s/const SMALL_MODEL = 'gpt-5-mini';/const SMALL_MODEL = 'claude-3-5-haiku-latest';/\" \\\n  \"$DEXTER_DIR/src/agent/tool-executor.ts\"\n\n4. Configure Model Settings\n\nSet Claude as the default model:\n\nmkdir -p \"$DEXTER_DIR/.dexter\"\ncat > \"$DEXTER_DIR/.dexter/settings.json\" << 'EOF'\n{\n  \"provider\": \"anthropic\",\n  \"modelId\": \"claude-sonnet-4-5\"\n}\nEOF\n\n5. Create Non-Interactive Query Script\ncat > \"$DEXTER_DIR/query.ts\" << 'SCRIPT'\n#!/usr/bin/env bun\n/**\n * Non-interactive Dexter query runner\n * Usage: bun query.ts \"What is Apple's revenue growth?\"\n */\nimport { config } from 'dotenv';\nimport { Agent } from './src/agent/orchestrator.js';\nimport { getSetting } from './src/utils/config.js';\n\nconfig({ quiet: true });\n\nconst query = process.argv[2];\nif (!query) {\n  console.error('Usage: bun query.ts \"Your financial question here\"');\n  process.exit(1);\n}\n\nconst model = getSetting('modelId', 'claude-sonnet-4-5') as string;\n\nasync function runQuery() {\n  let answer = '';\n  \n  const agent = new Agent({\n    model,\n    callbacks: {\n      onPhaseStart: (phase) => {\n        if (process.env.DEXTER_VERBOSE) {\n          console.error(`[Phase: ${phase}]`);\n        }\n      },\n      onPlanCreated: (plan) => {\n        if (process.env.DEXTER_VERBOSE) {\n          console.error(`[Tasks: ${plan.tasks.map(t => t.description).join(', ')}]`);\n        }\n      },\n      onAnswerStream: async (stream) => {\n        for await (const chunk of stream) {\n          answer += chunk;\n          process.stdout.write(chunk);\n        }\n      },\n    },\n  });\n\n  try {\n    await agent.run(query);\n    if (!answer.endsWith('\\n')) {\n      console.log();\n    }\n  } catch (error) {\n    console.error('Error:', error);\n    process.exit(1);\n  }\n}\n\nrunQuery();\nSCRIPT\n\nFull One-Shot Installation\n\nComplete installation script (requires API keys as environment variables):\n\n#!/bin/bash\nset -e\n\nDEXTER_DIR=\"/root/clawd-workspace/dexter\"\n\n# Clone\n[ ! -d \"$DEXTER_DIR\" ] && git clone https://github.com/virattt/dexter.git \"$DEXTER_DIR\"\ncd \"$DEXTER_DIR\"\n\n# Install deps\nbun install\n\n# Create .env (set these variables before running)\ncat > .env << EOF\nANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-your-key-here}\nFINANCIAL_DATASETS_API_KEY=${FINANCIAL_DATASETS_API_KEY:-your-key-here}\nTAVILY_API_KEY=${TAVILY_API_KEY:-your-key-here}\nEOF\n\n# Patch for Anthropic\nsed -i \"s/const SMALL_MODEL = 'gpt-5-mini';/const SMALL_MODEL = 'claude-3-5-haiku-latest';/\" \\\n  src/agent/tool-executor.ts\n\n# Set model config\nmkdir -p .dexter\necho '{\"provider\":\"anthropic\",\"modelId\":\"claude-sonnet-4-5\"}' > .dexter/settings.json\n\necho \"Dexter installed successfully!\"\n\nLocation\n/root/clawd-workspace/dexter\n\nQuick Query (Non-Interactive)\n\nFor quick financial questions, use the query script:\n\ncd /root/clawd-workspace/dexter && bun query.ts \"Your financial question here\"\n\n\nExamples:\n\nbun query.ts \"What is Apple's current P/E ratio?\"\nbun query.ts \"Compare Microsoft and Google revenue growth over the last 4 quarters\"\nbun query.ts \"What was Tesla's free cash flow in 2025?\"\nbun query.ts \"Show me insider trades for NVDA in the last 30 days\"\nbun query.ts \"What is Bitcoin's price trend over the last week?\"\n\n\nFor verbose output (shows planning steps):\n\nDEXTER_VERBOSE=1 bun query.ts \"Your question\"\n\nInteractive Mode (Complex Research)\n\nFor multi-turn research sessions or follow-up questions, use the interactive CLI via tmux:\n\nSOCKET_DIR=\"${CLAWDBOT_TMUX_SOCKET_DIR:-${TMPDIR:-/tmp}/clawdbot-tmux-sockets}\"\nSOCKET=\"$SOCKET_DIR/clawdbot.sock\"\nSESSION=dexter\n\n# Start Dexter (if not running)\ntmux -S \"$SOCKET\" kill-session -t \"$SESSION\" 2>/dev/null || true\ntmux -S \"$SOCKET\" new -d -s \"$SESSION\" -n shell -c /root/clawd-workspace/dexter\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- 'bun start' Enter\nsleep 3\n\n# Send a query\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -l -- 'Your question here'\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 Enter\n\n# Check output\ntmux -S \"$SOCKET\" capture-pane -p -J -t \"$SESSION\":0.0 -S -200\n\nAvailable Tools (Under the Hood)\n\nDexter automatically selects and uses these tools based on your query:\n\nFinancial Statements\nget_income_statements - Revenue, expenses, net income\nget_balance_sheets - Assets, liabilities, equity\nget_cash_flow_statements - Operating, investing, financing cash flows\nget_all_financial_statements - All three in one call\nPrices\nget_price_snapshot - Current stock price\nget_prices - Historical price data\nCrypto\nget_crypto_price_snapshot - Current crypto price (e.g., BTC-USD)\nget_crypto_prices - Historical crypto prices\nget_available_crypto_tickers - List available crypto tickers\nMetrics\nget_financial_metrics_snapshot - Current metrics (P/E, market cap, etc.)\nget_financial_metrics - Historical metrics\nSEC Filings\nget_10k_filing_items - Annual report sections\nget_10q_filing_items - Quarterly report sections\nget_8k_filing_items - Current report items\nget_filings - List of all filings\nOther Data\nget_analyst_estimates - Earnings/revenue estimates\nget_segmented_revenues - Revenue by segment\nget_insider_trades - Insider buying/selling\nget_news - Company news\nsearch_web - Web search (via Tavily) for general info\nAgent Architecture\n\nDexter uses a multi-phase approach:\n\nUnderstand: Extract intent, tickers, and time periods from query\nPlan: Create task list with dependencies\nExecute: Run tasks in parallel where possible\nReflect: Evaluate if more data is needed (iterates up to 5x)\nAnswer: Synthesize comprehensive response with sources\nExample Queries\n\nStock Analysis:\n\n\"What is AAPL's revenue growth over the last 4 quarters?\"\n\"Compare MSFT and GOOG operating margins for 2025\"\n\"What was AMZN's debt-to-equity ratio last quarter?\"\n\nFinancial Health:\n\n\"Is NVDA's cash flow positive? Show me the trend\"\n\"What are Tesla's profit margins compared to Ford?\"\n\nSEC Filings:\n\n\"Summarize Apple's most recent 10-K risk factors\"\n\"What did Meta disclose in their latest 8-K?\"\n\nCrypto:\n\n\"What is Ethereum's price today?\"\n\"Show Bitcoin's price movement over the last month\"\n\nMarket Research:\n\n\"What are analyst estimates for Amazon's next quarter earnings?\"\n\"Show me recent insider trades for Microsoft\"\nTroubleshooting\n\"Missing credentials... OPENAI_API_KEY\"\n\nRun the Anthropic patch (step 3 in installation) - Dexter's tool executor defaults to OpenAI.\n\nAPI errors for non-US stocks\n\nFinancial Datasets API primarily covers US stocks. Dexter will fall back to Tavily web search for international stocks if TAVILY_API_KEY is configured.\n\nSlow responses\n\nComplex queries may take 30-60 seconds. Dexter plans, executes multiple API calls, reflects on results, and synthesizes answers.\n\nTips\nBe specific: Include ticker symbols and time periods when known\nUS stocks work best: The Financial Datasets API has comprehensive US coverage\nInternational stocks: Dexter falls back to web search for non-US stocks\nCrypto format: Use BTC-USD, ETH-USD format for crypto tickers\nTimeout: Complex queries may take 30-60 seconds as Dexter plans and executes multiple tasks"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/igorhvr/dexter",
    "publisherUrl": "https://clawhub.ai/igorhvr/dexter",
    "owner": "igorhvr",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/dexter",
    "downloadUrl": "https://openagent3.xyz/downloads/dexter",
    "agentUrl": "https://openagent3.xyz/skills/dexter/agent",
    "manifestUrl": "https://openagent3.xyz/skills/dexter/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/dexter/agent.md"
  }
}