[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MQRYAT7K6N0W24891SWHR6":3,"skill-same:01M6MQRYAT7K6N0W24891SWHR6":275},{"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":37,"publishedAt":58,"linkOnly":59,"markdownContent":60,"markdownBody":61,"frontMatter":62,"refName":67,"commitSha":68,"skillDirectory":69,"forksCount":14,"repositoryHtmlUrl":70,"repositoryHomepageUrl":6,"ownerHtmlUrl":71,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":72,"install":73,"resources":86},"01M6MQRYAT7K6N0W24891SWHR6","valyu-best-practices",null,"Complete Valyu API toolkit for AI agents. Use this skill when asked to perform real-time search across web, academic, medical, transportation, financial sources, content extraction from URLs, AI-powered answers with citations, or comprehensive deep research reports.","guiselig\u002FFigurinhas-Trader","guiselig","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F176198808?v=4","01M6MQAH18ADYX0YJWFY017FRM","Guilherme Selig","01M6MQAH59WPCRB2SS2V4E22GT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002FSKILL.md",[18,23,26,29,34],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":35,"categoryName":36,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000036","内容创作者",[38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"best practices","valyu best practices","use","for","sources","complete","medical","deep","across","time","reports","ai agents","access","api","real-time","Citations","network","deep research","search","valid","2026-11-10 10:12:30",false,"---\nname: valyu-best-practices\ndescription: Complete Valyu API toolkit for AI agents. Use this skill when asked to perform real-time search across web, academic, medical, transportation, financial sources, content extraction from URLs, AI-powered answers with citations, or comprehensive deep research reports.\nlicense: MIT\ncompatibility: Requires network access and valid Valyu API key\nmetadata:\n  author: valyu\n  version: \"1.0\"\n---\n\n# Valyu Best Practices\n\nThis skill provides instructions for using the Valyu API to perform search, content extraction, AI-powered answers, and deep research tasks.\n\n## Quick Reference: Choosing the Right API\n\nUse this decision tree to select the appropriate Valyu API:\n\n```\nWhat do you need?\n\n├─ Find information across multiple sources\n│  └─ Use Search API\n│\n├─ Extract content from specific URLs\n│  └─ Use Contents API\n│\n├─ Get an AI-synthesized answer with citations\n│  └─ Use Answer API\n│\n├─ Generate a comprehensive research report\n│  └─ Use DeepResearch API\n│\n└─ Discover available data sources\n   └─ Use Datasources API\n```\n\n---\n\n## ⚠️ MANDATORY: Use Official Valyu SDK Libraries\n\n**CRITICAL: When writing code that uses the Valyu API, you MUST use the official SDK libraries. NEVER make raw HTTP\u002Ffetch calls to the Valyu API endpoints.**\n\n### JavaScript\u002FTypeScript: `valyu-js`\n\n```bash\nnpm install valyu-js\n# or\npnpm add valyu-js\n```\n\n```typescript\nimport { Valyu } from 'valyu-js';\n\nconst valyu = new Valyu(process.env.VALYU_API_KEY);\n\n\u002F\u002F Now use valyu.search(), valyu.contents(), valyu.answer(), valyu.deepResearch\n```\n\n### Python: `valyu`\n\n```bash\npip install valyu\n# or\nuv add valyu\n```\n\n```python\nfrom valyu import Valyu\n\nvalyu = Valyu(api_key=os.environ.get(\"VALYU_API_KEY\"))\n\n# Now use valyu.search(), valyu.contents(), valyu.answer(), valyu.deep_research\n```\n\n### Why SDK Over Raw API Calls?\n\n1. **Type safety** - Full TypeScript\u002FPython type hints for all parameters and responses\n2. **Automatic retries** - Built-in retry logic for transient failures\n3. **Streaming support** - Proper async iterator support for streaming responses\n4. **Error handling** - Structured error types with helpful messages\n5. **Future compatibility** - SDK updates handle API changes automatically\n\n### ❌ NEVER Do This\n\n```typescript\n\u002F\u002F DON'T make raw fetch calls\nconst response = await fetch('https:\u002F\u002Fapi.valyu.ai\u002Fv1\u002Fsearch', {\n  method: 'POST',\n  headers: {\n    'x-api-key': apiKey,\n    'Content-Type': 'application\u002Fjson'\n  },\n  body: JSON.stringify({ query: '...' })\n});\n```\n\n### ✅ Always Do This\n\n```typescript\n\u002F\u002F DO use the SDK\nimport { Valyu } from 'valyu-js';\n\nconst valyu = new Valyu(process.env.VALYU_API_KEY);\nconst response = await valyu.search({ query: '...' });\n```\n\n---\n\n## 1. Search API\n\n**Purpose:** Find information across web, academic, medical, transportation, financial, news, and proprietary sources.\n\n### When to Use\n\n- Finding recent information on any topic\n- Academic research (arXiv, PubMed, bioRxiv, medRxiv)\n- Financial data (SEC filings, earnings reports, stock data)\n- News monitoring and current events\n- Healthcare data (clinical trials, drug labels)\n- Prediction markets (Polymarket, Kalshi)\n- Transportation (UK National Rail, Global Shipping)\n\n### Basic Usage\n\n```typescript\nconst response = await valyu.search({\n  query: \"transformer architecture attention mechanism 2024\",\n  searchType: \"all\",\n  maxNumResults: 10\n});\n```\n\n### Search Types\n\n| Type | Use For |\n|------|---------|\n| `all` | Everything - web, academic, financial, proprietary |\n| `web` | General internet content only |\n| `proprietary` | Licensed academic papers and research |\n| `news` | News articles and current events |\n\n### Key Parameters\n\n| Parameter (TS\u002FJS) | Parameter (Python) | Purpose | Example |\n|-------------------|-------------------|---------|---------|\n| `query` | `query` | Search query (under 400 chars) | `\"CRISPR gene editing 2024\"` |\n| `searchType` | `search_type` | Source scope | `\"all\"`, `\"web\"`, `\"proprietary\"`, `\"news\"` |\n| `maxNumResults` | `max_num_results` | Number of results (1-20) | `10` |\n| `includedSources` | `included_sources` | Limit to specific sources | `[\"valyu\u002Fvalyu-arxiv\", \"valyu\u002Fvalyu-pubmed\"]` |\n| `startDate` \u002F `endDate` | `start_date` \u002F `end_date` | Date filtering | `\"2024-01-01\"` |\n| `relevanceThreshold` | `relevance_threshold` | Minimum relevance (0-1) | `0.7` |\n\n### Domain-Specific Search Patterns\n\n**Academic Research:**\n```typescript\nawait valyu.search({\n  query: \"CRISPR therapeutic applications clinical trials\",\n  searchType: \"proprietary\",\n  includedSources: [\"valyu\u002Fvalyu-arxiv\", \"valyu\u002Fvalyu-pubmed\", \"valyu\u002Fvalyu-biorxiv\"],\n  startDate: \"2024-01-01\"\n});\n```\n\n**Financial Analysis:**\n```typescript\nawait valyu.search({\n  query: \"Apple revenue Q4 2024 earnings\",\n  searchType: \"all\",\n  includedSources: [\"valyu\u002Fvalyu-sec-filings\", \"valyu\u002Fvalyu-earnings-US\"]\n});\n```\n\n**News Monitoring:**\n```typescript\nawait valyu.search({\n  query: \"AI regulation EU\",\n  searchType: \"news\",\n  startDate: \"2024-06-01\",\n  countryCode: \"EU\"\n});\n```\n\n### Search Recipes\n\nFor detailed patterns, see:\n- [Basic Search Patterns](references\u002Fsearch-recipes\u002Fbasic-search-all.md)\n- [Academic Search](references\u002Fsearch-recipes\u002Facademic-search.md)\n- [Finance Search](references\u002Fsearch-recipes\u002Ffinance-search.md)\n- [News Search](references\u002Fsearch-recipes\u002Fnews-search.md)\n- [Healthcare Search](references\u002Fsearch-recipes\u002Fhealthcare-and-bio-search.md)\n\n---\n\n## 2. Contents API\n\n**Purpose:** Extract clean, structured content from web pages optimized for LLM processing.\n\n### When to Use\n\n- Converting web pages to clean markdown\n- Extracting article text for summarization\n- Parsing documentation for RAG systems\n- Structured data extraction from product pages\n- Processing academic papers\n\n### Basic Usage\n\n```typescript\nconst response = await valyu.contents({\n  urls: [\"https:\u002F\u002Fexample.com\u002Farticle\"]\n});\n```\n\n### With Summarization\n\n```typescript\nconst response = await valyu.contents({\n  urls: [\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.12345\"],\n  summary: \"Extract key findings in 3 bullet points\"\n});\n```\n\n### Structured Extraction (JSON Schema)\n\n```typescript\nconst response = await valyu.contents({\n  urls: [\"https:\u002F\u002Fexample.com\u002Fproduct\"],\n  summary: {\n    type: \"object\",\n    properties: {\n      product_name: { type: \"string\" },\n      price: { type: \"number\" },\n      features: { type: \"array\", items: { type: \"string\" } }\n    },\n    required: [\"product_name\", \"price\"]\n  }\n});\n```\n\n### Key Parameters\n\n| Parameter (TS\u002FJS) | Parameter (Python) | Purpose | Example |\n|-------------------|-------------------|---------|---------|\n| `urls` | `urls` | URLs to process (1-10) | `[\"https:\u002F\u002Fexample.com\"]` |\n| `responseLength` | `response_length` | Content length | `\"short\"`, `\"medium\"`, `\"large\"`, `\"max\"` |\n| `extractEffort` | `extract_effort` | Extraction quality | `\"normal\"`, `\"high\"`, `\"auto\"` |\n| `summary` | `summary` | AI summarization | `true`, `\"instructions\"`, or JSON schema |\n| `screenshot` | `screenshot` | Capture screenshots | `true` |\n\n### Content Recipes\n\nFor detailed patterns, see:\n- [Basic Content Extraction](references\u002Fcontent-recipes\u002Fbasic-content-extraction-from-web.md)\n- [Extraction with Summary](references\u002Fcontent-recipes\u002Fbasic-content-extraction-from-web-with-summary.md)\n- [Structured Extraction](references\u002Fcontent-recipes\u002Fstructured-content-extraction-from-web.md)\n- [Research Paper Extraction](references\u002Fcontent-recipes\u002Fextract-content-from-research-paper.md)\n\n---\n\n## 3. Answer API\n\n**Purpose:** Get AI-powered answers grounded in real-time search results with citations.\n\n### When to Use\n\n- Questions requiring current information synthesis\n- Multi-source fact verification\n- Technical documentation questions\n- Research requiring cited sources\n- Structured data extraction from search results\n\n### Basic Usage\n\n```typescript\nconst response = await valyu.answer({\n  query: \"What are the latest developments in quantum computing?\"\n});\n```\n\n### With Fast Mode (Lower Latency)\n\n```typescript\nconst response = await valyu.answer({\n  query: \"Current Bitcoin price and 24h change\",\n  fastMode: true\n});\n```\n\n### With Custom Instructions\n\n```typescript\nconst response = await valyu.answer({\n  query: \"Compare React and Vue for enterprise applications\",\n  systemInstructions: \"Provide a balanced comparison with pros and cons. Format as a comparison table.\"\n});\n```\n\n### With Streaming\n\n```typescript\nconst stream = await valyu.answer({\n  query: \"Explain transformer architecture\",\n  streaming: true\n});\n\nfor await (const chunk of stream) {\n  \u002F\u002F Handle: search_results, content, metadata, done, error\n  console.log(chunk);\n}\n```\n\n### Structured Output\n\n```typescript\nconst response = await valyu.answer({\n  query: \"Apple Q4 2024 financial highlights\",\n  structuredOutput: {\n    type: \"object\",\n    properties: {\n      revenue: { type: \"string\" },\n      growthRate: { type: \"string\" },\n      keyHighlights: { type: \"array\", items: { type: \"string\" } }\n    }\n  }\n});\n```\n\n### Key Parameters\n\n| Parameter (TS\u002FJS) | Parameter (Python) | Purpose | Example |\n|-------------------|-------------------|---------|---------|\n| `query` | `query` | Question to answer | `\"What is quantum computing?\"` |\n| `fastMode` | `fast_mode` | Lower latency | `true` |\n| `systemInstructions` | `system_instructions` | AI directives | `\"Be concise\"` |\n| `structuredOutput` | `structured_output` | JSON schema | `{type: \"object\", ...}` |\n| `streaming` | `streaming` | Enable SSE streaming | `true` |\n| `dataMaxPrice` | `data_max_price` | Dollar limit | `1.0` |\n\n### Answer Recipes\n\nFor detailed patterns, see:\n- [Basic Answer](references\u002Fanswer-recipes\u002Fbasic-answer.md)\n- [Fast Mode](references\u002Fanswer-recipes\u002Fanswer-with-fast-mode.md)\n- [Streaming](references\u002Fanswer-recipes\u002Fanswer-with-streaming.md)\n- [Custom Instructions](references\u002Fanswer-recipes\u002Fanswer-with-custom-instructions.md)\n\n---\n\n## 4. DeepResearch API\n\n**Purpose:** Generate comprehensive research reports with detailed analysis and citations.\n\n### When to Use\n\n- Comprehensive market analysis\n- Literature reviews\n- Competitive intelligence\n- Technical deep dives\n- Topics requiring multi-source synthesis\n\n### Research Modes\n\n| Mode | Duration | Best For |\n|------|----------|----------|\n| `fast` | ~5 minutes | Quick lookups, simple questions |\n| `standard` | ~10-20 minutes | Balanced research (most common) |\n| `heavy` | ~90 minutes | Comprehensive analysis, complex topics |\n\n### Create Research Task\n\n```typescript\nconst task = await valyu.deepResearch.create({\n  query: \"AI chip market competitive landscape 2024\",\n  model: \"standard\"\n});\n\u002F\u002F Returns: { deepresearch_id: \"abc123\", status: \"queued\" }\n```\n\n### Poll for Completion\n\n```typescript\nconst status = await valyu.deepResearch.getStatus(task.deepresearch_id);\n\u002F\u002F status: \"queued\" | \"running\" | \"completed\" | \"failed\" | \"cancelled\"\n\nif (status.status === \"completed\") {\n  console.log(status.output);  \u002F\u002F Markdown report\n  console.log(status.sources); \u002F\u002F Cited sources\n  console.log(status.pdf_url); \u002F\u002F PDF download link\n}\n```\n\n### Key Parameters\n\n| Parameter (TS\u002FJS) | Parameter (Python) | Purpose | Example |\n|-------------------|-------------------|---------|---------|\n| `query` | `query` | Research question | `\"AI market trends 2024\"` |\n| `model` | `model` | Research depth | `\"fast\"`, `\"standard\"`, `\"heavy\"` |\n| `outputFormat` | `output_format` | Report format | `\"markdown\"`, `\"pdf\"` |\n| `includedSources` | `included_sources` | Source filtering | `[\"valyu\u002Fvalyu-arxiv\", \"techcrunch.com\"]` |\n| `startDate` \u002F `endDate` | `start_date` \u002F `end_date` | Date range | `\"2024-01-01\"` |\n\n### DeepResearch Recipes\n\nFor detailed patterns, see:\n- [Fast Research](references\u002Fdeepresearch-recipes\u002Fcreate-a-fast-research-task-and-await-completion.md)\n- [Standard Research](references\u002Fdeepresearch-recipes\u002Fcreate-a-standard-research-task-and-await-completion.md)\n- [Heavy Research](references\u002Fdeepresearch-recipes\u002Fcreate-a-heavy-research-task-and-await-completion.md)\n\n---\n\n## 5. Query Writing Best Practices\n\n### Core Principles\n\n1. **Be specific** - Use domain terminology\n2. **Be concise** - Keep queries under 400 characters\n3. **Be focused** - One topic per query\n4. **Add constraints** - Include timeframes, source types\n\n### Query Anatomy\n\n| Element | Description | Example |\n|---------|-------------|---------|\n| **Intent** | What you need | \"latest advancements\" vs \"overview\" |\n| **Domain** | Topic terminology | \"transformer architecture\" |\n| **Constraints** | Filters | \"2024\", \"peer-reviewed\" |\n| **Source type** | Where to look | academic papers, SEC filings |\n\n### Good vs Bad Queries\n\n```\nBAD:  \"I want to know about AI\"\nGOOD: \"transformer attention mechanism survey 2024\"\n\nBAD:  \"Apple financial information\"\nGOOD: \"Apple revenue growth Q4 2024 earnings SEC filing\"\n\nBAD:  \"gene editing research\"\nGOOD: \"CRISPR off-target effects therapeutic applications 2024\"\n```\n\n### Split Complex Requests\n\n```\n# Don't do this\n\"Tesla stock performance, new products, and Elon Musk statements\"\n\n# Do this instead\nQuery 1: \"Tesla stock performance Q4 2024\"\nQuery 2: \"Tesla Cybertruck production updates 2024\"\nQuery 3: \"Tesla FSD autonomous driving progress\"\n```\n\n### Source Filtering\n\nUse `includedSources` for domain authority:\n​\nFinancial Research Collection. Some sources to include:\n- `valyu\u002Fvalyu-sec-filings` - SEC regulatory filings\n- `valyu\u002Fvalyu-stocks` - Stock market data\n- `valyu\u002Fvalyu-earnings-US` - Earnings reports\n- `reuters.com` - Financial news\n- `bloomberg.com` - Market analysis\n​\nMedical Research Collection. Some sources to include:\n- `valyu\u002Fvalyu-pubmed` - Medical literature\n- `valyu\u002Fvalyu-clinical-trials` - Clinical trial data\n- `valyu\u002Fvalyu-drug-labels` - FDA drug information\n- `nejm.org` - New England Journal of Medicine\n- `thelancet.com` - The Lancet\n​\nTech Documentation Collection. Some sources to include:\n- `docs.aws.amazon.com` - AWS documentation\n- `cloud.google.com\u002Fdocs` - Google Cloud docs\n- `learn.microsoft.com` - Microsoft docs\n- `kubernetes.io\u002Fdocs` - Kubernetes docs\n- `developer.mozilla.org` - MDN Web Docs\n\n```javascript\n\u002F\u002F Academic\nincludedSources: [\"valyu\u002Fvalyu-arxiv\", \"valyu\u002Fvalyu-pubmed\", \"nature\"]\n\n\u002F\u002F Financial\nincludedSources: [\"valyu\u002Fvalyu-sec-filings\", \"bloomberg.com\", \"reuters.com\"]\n\n\u002F\u002F Tech news\nincludedSources: [\"techcrunch.com\", \"theverge.com\", \"arstechnica.com\"]\n```\n\nFor complete prompting guide, see [references\u002Fprompting.md](references\u002Fprompting.md).\n\n---\n\n## 6. Common Workflows\n\n### Research Workflow\n\n```typescript\n\u002F\u002F 1. Quick search to find sources\nconst searchResults = await valyu.search({\n  query: \"CRISPR therapeutic applications\",\n  searchType: \"proprietary\",\n  maxNumResults: 20\n});\n\n\u002F\u002F 2. Extract key content from top results\nconst contents = await valyu.contents({\n  urls: searchResults.results.slice(0, 3).map(r => r.url),\n  summary: \"Extract key findings\"\n});\n\n\u002F\u002F 3. Deep analysis for comprehensive report\nconst research = await valyu.deepResearch.create({\n  query: \"CRISPR therapeutic applications comprehensive review\",\n  model: \"heavy\"\n});\n```\n\n### Financial Analysis Workflow\n\n```typescript\n\u002F\u002F 1. Get SEC filings\nconst filings = await valyu.search({\n  query: \"Apple 10-K 2024\",\n  includedSources: [\"valyu\u002Fvalyu-sec-filings\"]\n});\n\n\u002F\u002F 2. Quick synthesis\nconst summary = await valyu.answer({\n  query: \"Apple Q4 2024 financial highlights\",\n  fastMode: true\n});\n\n\u002F\u002F 3. Structured extraction\nconst metrics = await valyu.answer({\n  query: \"Apple financial metrics 2024\",\n  structuredOutput: {\n    type: \"object\",\n    properties: {\n      revenue: { type: \"string\" },\n      netIncome: { type: \"string\" },\n      growthRate: { type: \"string\" }\n    }\n  }\n});\n```\n\n---\n\n## 7. Available Data Sources\n\nValyu provides access to 25+ specialized datasets:\n\n| Category | Examples |\n|----------|----------|\n| **Academic** | arXiv (2.5M+ papers), PubMed (37M+), bioRxiv, medRxiv |\n| **Financial** | SEC filings, earnings transcripts, stock data, crypto |\n| **Healthcare** | Clinical trials, DailyMed, PubChem, drug labels, ChEMBL, DrugBank, Open Target, WHO ICD |\n| **Economic** | FRED, BLS, World Bank, US Treasury, Destatis |\n| **Predictions** | Polymarket, Kalshi |\n| **Patents** | US patent database |\n| **Transportation** | UK Rail, Ship Tracking |\n\nFor complete datasource reference, see [references\u002Fdatasources.md](references\u002Fdatasources.md).\n\n---\n\n## 8. API Reference\n\nFor complete API documentation including all parameters, response structures, and error codes, see [references\u002Fapi-guide.md](references\u002Fapi-guide.md).\n\n---\n\n## 9. Integration Guides\n\nPlatform-specific integration documentation:\n\n- [Anthropic Claude](references\u002Fintegrations\u002Fanthropic.md)\n- [OpenAI](references\u002Fintegrations\u002Fopenai.md)\n- [Vercel AI SDK](references\u002Fintegrations\u002Fvercel-ai-sdk.md)\n- [LangChain](references\u002Fintegrations\u002Flangchain.md)\n- [LlamaIndex](references\u002Fintegrations\u002Fllamaindex.md)\n- [MCP Server](references\u002Fintegrations\u002Fmcp-server.md)\n\n---\n\n## Additional Resources\n\n- [All Recipes Index](references\u002Frecipes.md)\n- [Design Philosophy](references\u002Fdesign-philosophy.md)\n- [Prompting Guide](references\u002Fprompting.md)\n- [Full API Reference](references\u002Fapi-guide.md)\n","# Valyu Best Practices\n\nThis skill provides instructions for using the Valyu API to perform search, content extraction, AI-powered answers, and deep research tasks.\n\n## Quick Reference: Choosing the Right API\n\nUse this decision tree to select the appropriate Valyu API:\n\n```\nWhat do you need?\n\n├─ Find information across multiple sources\n│  └─ Use Search API\n│\n├─ Extract content from specific URLs\n│  └─ Use Contents API\n│\n├─ Get an AI-synthesized answer with citations\n│  └─ Use Answer API\n│\n├─ Generate a comprehensive research report\n│  └─ Use DeepResearch API\n│\n└─ Discover available data sources\n   └─ Use Datasources API\n```\n\n---\n\n## ⚠️ MANDATORY: Use Official Valyu SDK Libraries\n\n**CRITICAL: When writing code that uses the Valyu API, you MUST use the official SDK libraries. NEVER make raw HTTP\u002Ffetch calls to the Valyu API endpoints.**\n\n### JavaScript\u002FTypeScript: `valyu-js`\n\n```bash\nnpm install valyu-js\n# or\npnpm add valyu-js\n```\n\n```typescript\nimport { Valyu } from 'valyu-js';\n\nconst valyu = new Valyu(process.env.VALYU_API_KEY);\n\n\u002F\u002F Now use valyu.search(), valyu.contents(), valyu.answer(), valyu.deepResearch\n```\n\n### Python: `valyu`\n\n```bash\npip install valyu\n# or\nuv add valyu\n```\n\n```python\nfrom valyu import Valyu\n\nvalyu = Valyu(api_key=os.environ.get(\"VALYU_API_KEY\"))\n\n# Now use valyu.search(), valyu.contents(), valyu.answer(), valyu.deep_research\n```\n\n### Why SDK Over Raw API Calls?\n\n1. **Type safety** - Full TypeScript\u002FPython type hints for all parameters and responses\n2. **Automatic retries** - Built-in retry logic for transient failures\n3. **Streaming support** - Proper async iterator support for streaming responses\n4. **Error handling** - Structured error types with helpful messages\n5. **Future compatibility** - SDK updates handle API changes automatically\n\n### ❌ NEVER Do This\n\n```typescript\n\u002F\u002F DON'T make raw fetch calls\nconst response = await fetch('https:\u002F\u002Fapi.valyu.ai\u002Fv1\u002Fsearch', {\n  method: 'POST',\n  headers: {\n    'x-api-key': apiKey,\n    'Content-Type': 'application\u002Fjson'\n  },\n  body: JSON.stringify({ query: '...' })\n});\n```\n\n### ✅ Always Do This\n\n```typescript\n\u002F\u002F DO use the SDK\nimport { Valyu } from 'valyu-js';\n\nconst valyu = new Valyu(process.env.VALYU_API_KEY);\nconst response = await valyu.search({ query: '...' });\n```\n\n---\n\n## 1. Search API\n\n**Purpose:** Find information across web, academic, medical, transportation, financial, news, and proprietary sources.\n\n### When to Use\n\n- Finding recent information on any topic\n- Academic research (arXiv, PubMed, bioRxiv, medRxiv)\n- Financial data (SEC filings, earnings reports, stock data)\n- News monitoring and current events\n- Healthcare data (clinical trials, drug labels)\n- Prediction markets (Polymarket, Kalshi)\n- Transportation (UK National Rail, Global Shipping)\n\n### Basic Usage\n\n```typescript\nconst response = await valyu.search({\n  query: \"transformer architecture attention mechanism 2024\",\n  searchType: \"all\",\n  maxNumResults: 10\n});\n```\n\n### Search Types\n\n| Type | Use For |\n|------|---------|\n| `all` | Everything - web, academic, financial, proprietary |\n| `web` | General internet content only |\n| `proprietary` | Licensed academic papers and research |\n| `news` | News articles and current events |\n\n### Key Parameters\n\n| Parameter (TS\u002FJS) | Parameter (Python) | Purpose | Example |\n|-------------------|-------------------|---------|---------|\n| `query` | `query` | Search query (under 400 chars) | `\"CRISPR gene editing 2024\"` |\n| `searchType` | `search_type` | Source scope | `\"all\"`, `\"web\"`, `\"proprietary\"`, `\"news\"` |\n| `maxNumResults` | `max_num_results` | Number of results (1-20) | `10` |\n| `includedSources` | `included_sources` | Limit to specific sources | `[\"valyu\u002Fvalyu-arxiv\", \"valyu\u002Fvalyu-pubmed\"]` |\n| `startDate` \u002F `endDate` | `start_date` \u002F `end_date` | Date filtering | `\"2024-01-01\"` |\n| `relevanceThreshold` | `relevance_threshold` | Minimum relevance (0-1) | `0.7` |\n\n### Domain-Specific Search Patterns\n\n**Academic Research:**\n```typescript\nawait valyu.search({\n  query: \"CRISPR therapeutic applications clinical trials\",\n  searchType: \"proprietary\",\n  includedSources: [\"valyu\u002Fvalyu-arxiv\", \"valyu\u002Fvalyu-pubmed\", \"valyu\u002Fvalyu-biorxiv\"],\n  startDate: \"2024-01-01\"\n});\n```\n\n**Financial Analysis:**\n```typescript\nawait valyu.search({\n  query: \"Apple revenue Q4 2024 earnings\",\n  searchType: \"all\",\n  includedSources: [\"valyu\u002Fvalyu-sec-filings\", \"valyu\u002Fvalyu-earnings-US\"]\n});\n```\n\n**News Monitoring:**\n```typescript\nawait valyu.search({\n  query: \"AI regulation EU\",\n  searchType: \"news\",\n  startDate: \"2024-06-01\",\n  countryCode: \"EU\"\n});\n```\n\n### Search Recipes\n\nFor detailed patterns, see:\n- [Basic Search Patterns](references\u002Fsearch-recipes\u002Fbasic-search-all.md)\n- [Academic Search](references\u002Fsearch-recipes\u002Facademic-search.md)\n- [Finance Search](references\u002Fsearch-recipes\u002Ffinance-search.md)\n- [News Search](references\u002Fsearch-recipes\u002Fnews-search.md)\n- [Healthcare Search](references\u002Fsearch-recipes\u002Fhealthcare-and-bio-search.md)\n\n---\n\n## 2. Contents API\n\n**Purpose:** Extract clean, structured content from web pages optimized for LLM processing.\n\n### When to Use\n\n- Converting web pages to clean markdown\n- Extracting article text for summarization\n- Parsing documentation for RAG systems\n- Structured data extraction from product pages\n- Processing academic papers\n\n### Basic Usage\n\n```typescript\nconst response = await valyu.contents({\n  urls: [\"https:\u002F\u002Fexample.com\u002Farticle\"]\n});\n```\n\n### With Summarization\n\n```typescript\nconst response = await valyu.contents({\n  urls: [\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.12345\"],\n  summary: \"Extract key findings in 3 bullet points\"\n});\n```\n\n### Structured Extraction (JSON Schema)\n\n```typescript\nconst response = await valyu.contents({\n  urls: [\"https:\u002F\u002Fexample.com\u002Fproduct\"],\n  summary: {\n    type: \"object\",\n    properties: {\n      product_name: { type: \"string\" },\n      price: { type: \"number\" },\n      features: { type: \"array\", items: { type: \"string\" } }\n    },\n    required: [\"product_name\", \"price\"]\n  }\n});\n```\n\n### Key Parameters\n\n| Parameter (TS\u002FJS) | Parameter (Python) | Purpose | Example |\n|-------------------|-------------------|---------|---------|\n| `urls` | `urls` | URLs to process (1-10) | `[\"https:\u002F\u002Fexample.com\"]` |\n| `responseLength` | `response_length` | Content length | `\"short\"`, `\"medium\"`, `\"large\"`, `\"max\"` |\n| `extractEffort` | `extract_effort` | Extraction quality | `\"normal\"`, `\"high\"`, `\"auto\"` |\n| `summary` | `summary` | AI summarization | `true`, `\"instructions\"`, or JSON schema |\n| `screenshot` | `screenshot` | Capture screenshots | `true` |\n\n### Content Recipes\n\nFor detailed patterns, see:\n- [Basic Content Extraction](references\u002Fcontent-recipes\u002Fbasic-content-extraction-from-web.md)\n- [Extraction with Summary](references\u002Fcontent-recipes\u002Fbasic-content-extraction-from-web-with-summary.md)\n- [Structured Extraction](references\u002Fcontent-recipes\u002Fstructured-content-extraction-from-web.md)\n- [Research Paper Extraction](references\u002Fcontent-recipes\u002Fextract-content-from-research-paper.md)\n\n---\n\n## 3. Answer API\n\n**Purpose:** Get AI-powered answers grounded in real-time search results with citations.\n\n### When to Use\n\n- Questions requiring current information synthesis\n- Multi-source fact verification\n- Technical documentation questions\n- Research requiring cited sources\n- Structured data extraction from search results\n\n### Basic Usage\n\n```typescript\nconst response = await valyu.answer({\n  query: \"What are the latest developments in quantum computing?\"\n});\n```\n\n### With Fast Mode (Lower Latency)\n\n```typescript\nconst response = await valyu.answer({\n  query: \"Current Bitcoin price and 24h change\",\n  fastMode: true\n});\n```\n\n### With Custom Instructions\n\n```typescript\nconst response = await valyu.answer({\n  query: \"Compare React and Vue for enterprise applications\",\n  systemInstructions: \"Provide a balanced comparison with pros and cons. Format as a comparison table.\"\n});\n```\n\n### With Streaming\n\n```typescript\nconst stream = await valyu.answer({\n  query: \"Explain transformer architecture\",\n  streaming: true\n});\n\nfor await (const chunk of stream) {\n  \u002F\u002F Handle: search_results, content, metadata, done, error\n  console.log(chunk);\n}\n```\n\n### Structured Output\n\n```typescript\nconst response = await valyu.answer({\n  query: \"Apple Q4 2024 financial highlights\",\n  structuredOutput: {\n    type: \"object\",\n    properties: {\n      revenue: { type: \"string\" },\n      growthRate: { type: \"string\" },\n      keyHighlights: { type: \"array\", items: { type: \"string\" } }\n    }\n  }\n});\n```\n\n### Key Parameters\n\n| Parameter (TS\u002FJS) | Parameter (Python) | Purpose | Example |\n|-------------------|-------------------|---------|---------|\n| `query` | `query` | Question to answer | `\"What is quantum computing?\"` |\n| `fastMode` | `fast_mode` | Lower latency | `true` |\n| `systemInstructions` | `system_instructions` | AI directives | `\"Be concise\"` |\n| `structuredOutput` | `structured_output` | JSON schema | `{type: \"object\", ...}` |\n| `streaming` | `streaming` | Enable SSE streaming | `true` |\n| `dataMaxPrice` | `data_max_price` | Dollar limit | `1.0` |\n\n### Answer Recipes\n\nFor detailed patterns, see:\n- [Basic Answer](references\u002Fanswer-recipes\u002Fbasic-answer.md)\n- [Fast Mode](references\u002Fanswer-recipes\u002Fanswer-with-fast-mode.md)\n- [Streaming](references\u002Fanswer-recipes\u002Fanswer-with-streaming.md)\n- [Custom Instructions](references\u002Fanswer-recipes\u002Fanswer-with-custom-instructions.md)\n\n---\n\n## 4. DeepResearch API\n\n**Purpose:** Generate comprehensive research reports with detailed analysis and citations.\n\n### When to Use\n\n- Comprehensive market analysis\n- Literature reviews\n- Competitive intelligence\n- Technical deep dives\n- Topics requiring multi-source synthesis\n\n### Research Modes\n\n| Mode | Duration | Best For |\n|------|----------|----------|\n| `fast` | ~5 minutes | Quick lookups, simple questions |\n| `standard` | ~10-20 minutes | Balanced research (most common) |\n| `heavy` | ~90 minutes | Comprehensive analysis, complex topics |\n\n### Create Research Task\n\n```typescript\nconst task = await valyu.deepResearch.create({\n  query: \"AI chip market competitive landscape 2024\",\n  model: \"standard\"\n});\n\u002F\u002F Returns: { deepresearch_id: \"abc123\", status: \"queued\" }\n```\n\n### Poll for Completion\n\n```typescript\nconst status = await valyu.deepResearch.getStatus(task.deepresearch_id);\n\u002F\u002F status: \"queued\" | \"running\" | \"completed\" | \"failed\" | \"cancelled\"\n\nif (status.status === \"completed\") {\n  console.log(status.output);  \u002F\u002F Markdown report\n  console.log(status.sources); \u002F\u002F Cited sources\n  console.log(status.pdf_url); \u002F\u002F PDF download link\n}\n```\n\n### Key Parameters\n\n| Parameter (TS\u002FJS) | Parameter (Python) | Purpose | Example |\n|-------------------|-------------------|---------|---------|\n| `query` | `query` | Research question | `\"AI market trends 2024\"` |\n| `model` | `model` | Research depth | `\"fast\"`, `\"standard\"`, `\"heavy\"` |\n| `outputFormat` | `output_format` | Report format | `\"markdown\"`, `\"pdf\"` |\n| `includedSources` | `included_sources` | Source filtering | `[\"valyu\u002Fvalyu-arxiv\", \"techcrunch.com\"]` |\n| `startDate` \u002F `endDate` | `start_date` \u002F `end_date` | Date range | `\"2024-01-01\"` |\n\n### DeepResearch Recipes\n\nFor detailed patterns, see:\n- [Fast Research](references\u002Fdeepresearch-recipes\u002Fcreate-a-fast-research-task-and-await-completion.md)\n- [Standard Research](references\u002Fdeepresearch-recipes\u002Fcreate-a-standard-research-task-and-await-completion.md)\n- [Heavy Research](references\u002Fdeepresearch-recipes\u002Fcreate-a-heavy-research-task-and-await-completion.md)\n\n---\n\n## 5. Query Writing Best Practices\n\n### Core Principles\n\n1. **Be specific** - Use domain terminology\n2. **Be concise** - Keep queries under 400 characters\n3. **Be focused** - One topic per query\n4. **Add constraints** - Include timeframes, source types\n\n### Query Anatomy\n\n| Element | Description | Example |\n|---------|-------------|---------|\n| **Intent** | What you need | \"latest advancements\" vs \"overview\" |\n| **Domain** | Topic terminology | \"transformer architecture\" |\n| **Constraints** | Filters | \"2024\", \"peer-reviewed\" |\n| **Source type** | Where to look | academic papers, SEC filings |\n\n### Good vs Bad Queries\n\n```\nBAD:  \"I want to know about AI\"\nGOOD: \"transformer attention mechanism survey 2024\"\n\nBAD:  \"Apple financial information\"\nGOOD: \"Apple revenue growth Q4 2024 earnings SEC filing\"\n\nBAD:  \"gene editing research\"\nGOOD: \"CRISPR off-target effects therapeutic applications 2024\"\n```\n\n### Split Complex Requests\n\n```\n# Don't do this\n\"Tesla stock performance, new products, and Elon Musk statements\"\n\n# Do this instead\nQuery 1: \"Tesla stock performance Q4 2024\"\nQuery 2: \"Tesla Cybertruck production updates 2024\"\nQuery 3: \"Tesla FSD autonomous driving progress\"\n```\n\n### Source Filtering\n\nUse `includedSources` for domain authority:\n​\nFinancial Research Collection. Some sources to include:\n- `valyu\u002Fvalyu-sec-filings` - SEC regulatory filings\n- `valyu\u002Fvalyu-stocks` - Stock market data\n- `valyu\u002Fvalyu-earnings-US` - Earnings reports\n- `reuters.com` - Financial news\n- `bloomberg.com` - Market analysis\n​\nMedical Research Collection. Some sources to include:\n- `valyu\u002Fvalyu-pubmed` - Medical literature\n- `valyu\u002Fvalyu-clinical-trials` - Clinical trial data\n- `valyu\u002Fvalyu-drug-labels` - FDA drug information\n- `nejm.org` - New England Journal of Medicine\n- `thelancet.com` - The Lancet\n​\nTech Documentation Collection. Some sources to include:\n- `docs.aws.amazon.com` - AWS documentation\n- `cloud.google.com\u002Fdocs` - Google Cloud docs\n- `learn.microsoft.com` - Microsoft docs\n- `kubernetes.io\u002Fdocs` - Kubernetes docs\n- `developer.mozilla.org` - MDN Web Docs\n\n```javascript\n\u002F\u002F Academic\nincludedSources: [\"valyu\u002Fvalyu-arxiv\", \"valyu\u002Fvalyu-pubmed\", \"nature\"]\n\n\u002F\u002F Financial\nincludedSources: [\"valyu\u002Fvalyu-sec-filings\", \"bloomberg.com\", \"reuters.com\"]\n\n\u002F\u002F Tech news\nincludedSources: [\"techcrunch.com\", \"theverge.com\", \"arstechnica.com\"]\n```\n\nFor complete prompting guide, see [references\u002Fprompting.md](references\u002Fprompting.md).\n\n---\n\n## 6. Common Workflows\n\n### Research Workflow\n\n```typescript\n\u002F\u002F 1. Quick search to find sources\nconst searchResults = await valyu.search({\n  query: \"CRISPR therapeutic applications\",\n  searchType: \"proprietary\",\n  maxNumResults: 20\n});\n\n\u002F\u002F 2. Extract key content from top results\nconst contents = await valyu.contents({\n  urls: searchResults.results.slice(0, 3).map(r => r.url),\n  summary: \"Extract key findings\"\n});\n\n\u002F\u002F 3. Deep analysis for comprehensive report\nconst research = await valyu.deepResearch.create({\n  query: \"CRISPR therapeutic applications comprehensive review\",\n  model: \"heavy\"\n});\n```\n\n### Financial Analysis Workflow\n\n```typescript\n\u002F\u002F 1. Get SEC filings\nconst filings = await valyu.search({\n  query: \"Apple 10-K 2024\",\n  includedSources: [\"valyu\u002Fvalyu-sec-filings\"]\n});\n\n\u002F\u002F 2. Quick synthesis\nconst summary = await valyu.answer({\n  query: \"Apple Q4 2024 financial highlights\",\n  fastMode: true\n});\n\n\u002F\u002F 3. Structured extraction\nconst metrics = await valyu.answer({\n  query: \"Apple financial metrics 2024\",\n  structuredOutput: {\n    type: \"object\",\n    properties: {\n      revenue: { type: \"string\" },\n      netIncome: { type: \"string\" },\n      growthRate: { type: \"string\" }\n    }\n  }\n});\n```\n\n---\n\n## 7. Available Data Sources\n\nValyu provides access to 25+ specialized datasets:\n\n| Category | Examples |\n|----------|----------|\n| **Academic** | arXiv (2.5M+ papers), PubMed (37M+), bioRxiv, medRxiv |\n| **Financial** | SEC filings, earnings transcripts, stock data, crypto |\n| **Healthcare** | Clinical trials, DailyMed, PubChem, drug labels, ChEMBL, DrugBank, Open Target, WHO ICD |\n| **Economic** | FRED, BLS, World Bank, US Treasury, Destatis |\n| **Predictions** | Polymarket, Kalshi |\n| **Patents** | US patent database |\n| **Transportation** | UK Rail, Ship Tracking |\n\nFor complete datasource reference, see [references\u002Fdatasources.md](references\u002Fdatasources.md).\n\n---\n\n## 8. API Reference\n\nFor complete API documentation including all parameters, response structures, and error codes, see [references\u002Fapi-guide.md](references\u002Fapi-guide.md).\n\n---\n\n## 9. Integration Guides\n\nPlatform-specific integration documentation:\n\n- [Anthropic Claude](references\u002Fintegrations\u002Fanthropic.md)\n- [OpenAI](references\u002Fintegrations\u002Fopenai.md)\n- [Vercel AI SDK](references\u002Fintegrations\u002Fvercel-ai-sdk.md)\n- [LangChain](references\u002Fintegrations\u002Flangchain.md)\n- [LlamaIndex](references\u002Fintegrations\u002Fllamaindex.md)\n- [MCP Server](references\u002Fintegrations\u002Fmcp-server.md)\n\n---\n\n## Additional Resources\n\n- [All Recipes Index](references\u002Frecipes.md)\n- [Design Philosophy](references\u002Fdesign-philosophy.md)\n- [Prompting Guide](references\u002Fprompting.md)\n- [Full API Reference](references\u002Fapi-guide.md)\n",{"name":5,"license":15,"metadata":63,"description":7,"compatibility":66},{"author":64,"version":65},"valyu","1.0","Requires network access and valid Valyu API key","main","ecd092ff2b21891b3d4601f3ac589d81f6e0f8ac",".claude\u002Fskills\u002Fvalyu-best-practices","https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader","https:\u002F\u002Fgithub.com\u002Fguiselig","2026-04-18 23:09:30",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add guiselig\u002FFigurinhas-Trader --skill valyu-best-practices",{"tool":79,"command":80},"bunx","bunx skills add guiselig\u002FFigurinhas-Trader --skill valyu-best-practices",{"tool":82,"command":83},"pnpm","pnpm dlx skills add guiselig\u002FFigurinhas-Trader --skill valyu-best-practices","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002FSKILL.md",true,[87,93,97,101,105,109,113,117,121,125,129,133,137,141,145,149,153,157,161,165,169,173,177,181,185,189,193,197,201,205,209,213,217,221,225,229,233,237,241,245,249,253,257,261,265,271],{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fanswer-recipes\u002Fanswer-with-custom-instructions.md","REFERENCE","参考文档",946,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fanswer-recipes\u002Fanswer-with-custom-instructions.md",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fanswer-recipes\u002Fanswer-with-streaming.md",1084,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fanswer-recipes\u002Fanswer-with-streaming.md",{"path":98,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fanswer-recipes\u002Fbasic-answer.md",671,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fanswer-recipes\u002Fbasic-answer.md",{"path":102,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fapi-guide.md",12291,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fapi-guide.md",{"path":106,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fcontent-recipes\u002Fbasic-content-extraction-from-web-with-summary.md",1215,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fcontent-recipes\u002Fbasic-content-extraction-from-web-with-summary.md",{"path":110,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fcontent-recipes\u002Fbasic-content-extraction-from-web.md",1001,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fcontent-recipes\u002Fbasic-content-extraction-from-web.md",{"path":114,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Fcontent-recipes\u002Fextract-content-from-research-paper.md",1272,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fcontent-recipes\u002Fextract-content-from-research-paper.md",{"path":118,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Fcontent-recipes\u002Fextract-product-data-from-online-product-info.md",1386,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fcontent-recipes\u002Fextract-product-data-from-online-product-info.md",{"path":122,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":123,"sourceHtmlUrl":124},"references\u002Fcontent-recipes\u002Fnews-aggregator-from-content-extraction.md",1648,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fcontent-recipes\u002Fnews-aggregator-from-content-extraction.md",{"path":126,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":127,"sourceHtmlUrl":128},"references\u002Fcontent-recipes\u002Fstructured-content-extraction-from-web.md",1643,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fcontent-recipes\u002Fstructured-content-extraction-from-web.md",{"path":130,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":131,"sourceHtmlUrl":132},"references\u002Fdatasources.md",8678,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fdatasources.md",{"path":134,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":135,"sourceHtmlUrl":136},"references\u002Fdeepresearch-recipes\u002Fcreate-a-fast-research-task-and-await-completion.md",1637,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fdeepresearch-recipes\u002Fcreate-a-fast-research-task-and-await-completion.md",{"path":138,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":139,"sourceHtmlUrl":140},"references\u002Fdeepresearch-recipes\u002Fcreate-a-heavy-research-task-and-await-completion.md",1774,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fdeepresearch-recipes\u002Fcreate-a-heavy-research-task-and-await-completion.md",{"path":142,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":143,"sourceHtmlUrl":144},"references\u002Fdeepresearch-recipes\u002Fcreate-a-standard-research-task-and-await-completion.md",1679,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fdeepresearch-recipes\u002Fcreate-a-standard-research-task-and-await-completion.md",{"path":146,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":147,"sourceHtmlUrl":148},"references\u002Fdesign-philosophy.md",2285,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fdesign-philosophy.md",{"path":150,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":151,"sourceHtmlUrl":152},"references\u002Fintegrations\u002Fanthropic.md",7391,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fanthropic.md",{"path":154,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":155,"sourceHtmlUrl":156},"references\u002Fintegrations\u002Faws-agentcore.md",5187,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Faws-agentcore.md",{"path":158,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":159,"sourceHtmlUrl":160},"references\u002Fintegrations\u002Fclaude-agent-sdk.md",6689,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fclaude-agent-sdk.md",{"path":162,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":163,"sourceHtmlUrl":164},"references\u002Fintegrations\u002Fclaude-code-plugin.md",2733,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fclaude-code-plugin.md",{"path":166,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":167,"sourceHtmlUrl":168},"references\u002Fintegrations\u002Fgoogle.md",8821,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fgoogle.md",{"path":170,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":171,"sourceHtmlUrl":172},"references\u002Fintegrations\u002Flangchain.md",5372,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Flangchain.md",{"path":174,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":175,"sourceHtmlUrl":176},"references\u002Fintegrations\u002Fllamaindex.md",6327,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fllamaindex.md",{"path":178,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":179,"sourceHtmlUrl":180},"references\u002Fintegrations\u002Flmstudio.md",1663,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Flmstudio.md",{"path":182,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":183,"sourceHtmlUrl":184},"references\u002Fintegrations\u002Fmcp-desktop.md",2608,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fmcp-desktop.md",{"path":186,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":187,"sourceHtmlUrl":188},"references\u002Fintegrations\u002Fmcp-server.md",3179,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fmcp-server.md",{"path":190,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":191,"sourceHtmlUrl":192},"references\u002Fintegrations\u002Fn8n.md",2205,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fn8n.md",{"path":194,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":195,"sourceHtmlUrl":196},"references\u002Fintegrations\u002Fopenai.md",8273,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fopenai.md",{"path":198,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":199,"sourceHtmlUrl":200},"references\u002Fintegrations\u002Fvercel-ai-sdk.md",5317,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fintegrations\u002Fvercel-ai-sdk.md",{"path":202,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":203,"sourceHtmlUrl":204},"references\u002Fprompting.md",5516,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fprompting.md",{"path":206,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":207,"sourceHtmlUrl":208},"references\u002Frecipes.md",6433,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Frecipes.md",{"path":210,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":211,"sourceHtmlUrl":212},"references\u002Fsearch-recipes\u002Facademic-search.md",1747,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Facademic-search.md",{"path":214,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":215,"sourceHtmlUrl":216},"references\u002Fsearch-recipes\u002Fbasic-search-all.md",1154,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fbasic-search-all.md",{"path":218,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":219,"sourceHtmlUrl":220},"references\u002Fsearch-recipes\u002Fbasic-search-proprietary.md",1095,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fbasic-search-proprietary.md",{"path":222,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":223,"sourceHtmlUrl":224},"references\u002Fsearch-recipes\u002Fbasic-search-web.md",1056,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fbasic-search-web.md",{"path":226,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":227,"sourceHtmlUrl":228},"references\u002Fsearch-recipes\u002Ffinance-search.md",2274,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Ffinance-search.md",{"path":230,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":231,"sourceHtmlUrl":232},"references\u002Fsearch-recipes\u002Fhealthcare-and-bio-search.md",1996,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fhealthcare-and-bio-search.md",{"path":234,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":235,"sourceHtmlUrl":236},"references\u002Fsearch-recipes\u002Fmonitor-for-breaking-news.md",1534,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fmonitor-for-breaking-news.md",{"path":238,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":239,"sourceHtmlUrl":240},"references\u002Fsearch-recipes\u002Fmulti-step-search-workflow.md",2331,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fmulti-step-search-workflow.md",{"path":242,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":243,"sourceHtmlUrl":244},"references\u002Fsearch-recipes\u002Fmulti-topic-news-monitoring.md",2298,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fmulti-topic-news-monitoring.md",{"path":246,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":247,"sourceHtmlUrl":248},"references\u002Fsearch-recipes\u002Fnews-search.md",1438,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fnews-search.md",{"path":250,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":251,"sourceHtmlUrl":252},"references\u002Fsearch-recipes\u002Fprediction-markets-search.md",2151,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fprediction-markets-search.md",{"path":254,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":255,"sourceHtmlUrl":256},"references\u002Fsearch-recipes\u002Ftool-call.md",977,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Ftool-call.md",{"path":258,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":259,"sourceHtmlUrl":260},"references\u002Fsearch-recipes\u002Ftrack-news-for-brands.md",2234,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Ftrack-news-for-brands.md",{"path":262,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":263,"sourceHtmlUrl":264},"references\u002Fsearch-recipes\u002Fusing-collections-to-search.md",1293,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Freferences\u002Fsearch-recipes\u002Fusing-collections-to-search.md",{"path":266,"resourceType":267,"resourceTypeDesc":268,"sizeBytes":269,"sourceHtmlUrl":270},"scripts\u002Fvalyu","SCRIPT","脚本",419,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Fscripts\u002Fvalyu",{"path":272,"resourceType":267,"resourceTypeDesc":268,"sizeBytes":273,"sourceHtmlUrl":274},"scripts\u002Fvalyu.mjs",13195,"https:\u002F\u002Fgithub.com\u002Fguiselig\u002FFigurinhas-Trader\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvalyu-best-practices\u002Fscripts\u002Fvalyu.mjs",[]]