{"skill":{"slug":"liang-tavily-research","displayName":"Tavily Research","summary":"Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis, d...","description":"---\nname: tavily-research\ndescription: Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports.\nhomepage: https://tavily.com\nmetadata: {\"openclaw\":{\"emoji\":\"📊\",\"requires\":{\"bins\":[\"node\"],\"env\":[\"TAVILY_API_KEY\"]},\"primaryEnv\":\"TAVILY_API_KEY\"}}\n---\n\n# Tavily Research\n\nConduct comprehensive research on any topic with automatic source gathering, analysis, and response generation with citations.\n\n## Authentication\n\nGet your API key at https://tavily.com and add to your OpenClaw config:\n\n```json\n{\n  \"skills\": {\n    \"entries\": {\n      \"tavily-research\": {\n        \"enabled\": true,\n        \"apiKey\": \"tvly-YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\nOr set the environment variable:\n```bash\nexport TAVILY_API_KEY=\"tvly-YOUR_API_KEY_HERE\"\n```\n\n## Quick Start\n\n### Using the Script\n\n```bash\nnode {baseDir}/scripts/research.mjs \"query\"\nnode {baseDir}/scripts/research.mjs \"query\" --pro\nnode {baseDir}/scripts/research.mjs \"query\" --output report.md\n```\n\n### Examples\n\n```bash\n# Quick overview\nnode {baseDir}/scripts/research.mjs \"What is retrieval augmented generation?\"\n\n# Comprehensive analysis\nnode {baseDir}/scripts/research.mjs \"LangGraph vs CrewAI for multi-agent systems\" --pro\n\n# Market research with output file\nnode {baseDir}/scripts/research.mjs \"Fintech startup landscape 2025\" --pro --output fintech-report.md\n\n# Technical comparison\nnode {baseDir}/scripts/research.mjs \"React vs Vue vs Svelte\" --pro\n```\n\n## Options\n\n| Option | Description | Default |\n|--------|-------------|---------|\n| `--model <model>` | Model: `mini`, `pro`, `auto` | `mini` |\n| `--output <file>` | Save report to file | - |\n| `--json` | Output raw JSON | false |\n\n## Model Selection\n\n**Rule of thumb**: \"what does X do?\" → mini. \"X vs Y vs Z\" or \"best way to...\" → pro.\n\n| Model | Use Case | Speed |\n|-------|----------|-------|\n| `mini` | Single topic, targeted research | ~30s |\n| `pro` | Comprehensive multi-angle analysis | ~60-120s |\n| `auto` | API chooses based on complexity | Varies |\n\n## Output Format\n\nThe research includes:\n- **AI-generated answer**: Comprehensive synthesis\n- **Sources**: Citations with titles, URLs, and relevance scores\n- **Metadata**: Query, response time, and statistics\n\n## Tips\n\n- Research can take 30-120 seconds depending on complexity\n- Use `--pro` for comparisons, market analysis, or detailed reports\n- Use `--output` to save reports for later reference\n- The `auto` model lets Tavily choose based on query complexity","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":980,"installsAllTime":2,"installsCurrent":2,"stars":1,"versions":1},"createdAt":1772418910612,"updatedAt":1778994387041},"latestVersion":{"version":"1.0.0","createdAt":1772418910612,"changelog":"tavily-research 1.0.0 – Initial release\n\n- Enables comprehensive web-based research with explicit citations.\n- Supports both quick overviews and detailed multi-source synthesis (comparisons, market analysis, current events).\n- Allows interactive queries via command line with options for output file, model selection, and JSON output.\n- Includes authentication via API key and clear instructions for setup.\n- Provides flexible model choices: mini, pro, and auto, to suit various research needs.","license":null},"metadata":{"setup":[{"key":"TAVILY_API_KEY","required":true}],"os":null,"systems":null},"owner":{"handle":"matthew77","userId":"s173wv4gdgnxtget34hxdg8efd8843ep","displayName":"Liang","image":"https://avatars.githubusercontent.com/u/156555?v=4"},"moderation":null}