{"id":"fc512b30-99db-41c0-bb2c-25908ca60d84","entityType":"agent","slug":"clawhub-okaris-web-search-2","name":"Web Search","canonicalUrl":"https://www.xpersona.co/agent/clawhub-okaris-web-search-2","canonicalPath":"/agent/clawhub-okaris-web-search-2","generatedAt":"2026-10-10T13:32:29.156Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T10:06:06.161Z","emptyReason":null},"description":"Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabil... Skill: Web Search Owner: okaris Summary: Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabil... Tags: latest:0.1.5 Version history: v0.1.5 | 2026-02-18T08:31:31.313Z | auto - Expanded documentation in SKILL.md with detailed quick start, install notes, and usage workflows. - Added step-by-step examples for each Ta","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s1737xapsjy8k5qnagtfyf5nrx85t72x:web-search-2","sourceUrl":"https://clawhub.ai/okaris/web-search-2","homepage":"https://clawhub.ai/okaris/skills/web-search-2","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/okaris/web-search-2","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/okaris/skills/web-search-2","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":64,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabil..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:06:06.161Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:06:06.161Z","emptyReason":null},"stars":null,"forks":null,"downloads":1506,"packageName":null,"latestVersion":"0.1.5","tractionLabel":"1.5K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:06:06.161Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T10:06:06.161Z","lastCrawledAt":"2026-10-10T10:06:06.161Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T10:06:06.161Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.5","createdAt":"2026-02-18T08:31:31.313Z","changelog":"- Expanded documentation in SKILL.md with detailed quick start, install notes, and usage workflows. - Added step-by-step examples for each Tavily and Exa app, covering search, extraction, and direct answers. - Included recommended workflows for research + LLM (RAG pipelines) and extract + summarize tasks. - Added a comprehensive use cases section and related skills integrations. - Improved clarity on available tools, triggers, and app descriptions.","fileCount":2,"zipByteSize":2075},{"version":"0.1.1","createdAt":"2026-02-06T07:40:24.726Z","changelog":"- No changes detected in this release. - Version number updated to 0.1.1.","fileCount":2,"zipByteSize":1831},{"version":"0.1.0","createdAt":"2026-02-06T07:28:56.592Z","changelog":"Initial release of web-search skill with Tavily and Exa integration via inference.sh CLI. - Provides AI-powered web search, extraction, and direct factual answers. - Supports Tavily and Exa apps for search, extract, and Q&A tasks. - Includes workflows for research, content extraction, RAG pipelines, and summarization. - Example command-line usage and integration with LLMs are documented. - Highlights use cases: research, fact-checking, content aggregation, and building agents.","fileCount":2,"zipByteSize":1831}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1737xapsjy8k5qnagtfyf5nrx85t72x:web-search-2","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T13:32:29.156Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-okaris-web-search-2/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-10T10:06:06.161Z","emptyReason":null},"readme":"Skill: Web Search\n\nOwner: okaris\n\nSummary: Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabil...\n\nTags: latest:0.1.5\n\nVersion history:\n\nv0.1.5 | 2026-02-18T08:31:31.313Z | auto\n\n- Expanded documentation in SKILL.md with detailed quick start, install notes, and usage workflows.\n- Added step-by-step examples for each Tavily and Exa app, covering search, extraction, and direct answers.\n- Included recommended workflows for research + LLM (RAG pipelines) and extract + summarize tasks.\n- Added a comprehensive use cases section and related skills integrations.\n- Improved clarity on available tools, triggers, and app descriptions.\n\nv0.1.1 | 2026-02-06T07:40:24.726Z | auto\n\n- No changes detected in this release.\n- Version number updated to 0.1.1.\n\nv0.1.0 | 2026-02-06T07:28:56.592Z | auto\n\nInitial release of web-search skill with Tavily and Exa integration via inference.sh CLI.\n\n- Provides AI-powered web search, extraction, and direct factual answers.\n- Supports Tavily and Exa apps for search, extract, and Q&A tasks.\n- Includes workflows for research, content extraction, RAG pipelines, and summarization.\n- Example command-line usage and integration with LLMs are documented.\n- Highlights use cases: research, fact-checking, content aggregation, and building agents.\n\nArchive index:\n\nArchive v0.1.5: 2 files, 2075 bytes\n\nFiles: SKILL.md (4270b), _meta.json (131b)\n\nFile v0.1.5:SKILL.md\n\n---\nname: web-search\ndescription: \"Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabilities: AI-powered search, content extraction, direct answers, research. Use for: research, RAG pipelines, fact-checking, content aggregation, agents. Triggers: web search, tavily, exa, search api, content extraction, research, internet search, ai search, search assistant, web scraping, rag, perplexity alternative\"\nallowed-tools: Bash(infsh *)\n---\n\n# Web Search & Extraction\n\nSearch the web and extract content via [inference.sh](https://inference.sh) CLI.\n\n![Web Search & Extraction](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgndqjxd780zm2j3rmada6y8.jpeg)\n\n## Quick Start\n\n```bash\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Search the web\ninfsh app run tavily/search-assistant --input '{\"query\": \"latest AI developments 2024\"}'\n```\n\n> **Install note:** The [install script](https://cli.inference.sh) only detects your OS/architecture, downloads the matching binary from `dist.inference.sh`, and verifies its SHA-256 checksum. No elevated permissions or background processes. [Manual install & verification](https://dist.inference.sh/cli/checksums.txt) available.\n\n## Available Apps\n\n### Tavily\n\n| App | App ID | Description |\n|-----|--------|-------------|\n| Search Assistant | `tavily/search-assistant` | AI-powered search with answers |\n| Extract | `tavily/extract` | Extract content from URLs |\n\n### Exa\n\n| App | App ID | Description |\n|-----|--------|-------------|\n| Search | `exa/search` | Smart web search with AI |\n| Answer | `exa/answer` | Direct factual answers |\n| Extract | `exa/extract` | Extract and analyze web content |\n\n## Examples\n\n### Tavily Search\n\n```bash\ninfsh app run tavily/search-assistant --input '{\n  \"query\": \"What are the best practices for building AI agents?\"\n}'\n```\n\nReturns AI-generated answers with sources and images.\n\n### Tavily Extract\n\n```bash\ninfsh app run tavily/extract --input '{\n  \"urls\": [\"https://example.com/article1\", \"https://example.com/article2\"]\n}'\n```\n\nExtracts clean text and images from multiple URLs.\n\n### Exa Search\n\n```bash\ninfsh app run exa/search --input '{\n  \"query\": \"machine learning frameworks comparison\"\n}'\n```\n\nReturns highly relevant links with context.\n\n### Exa Answer\n\n```bash\ninfsh app run exa/answer --input '{\n  \"question\": \"What is the population of Tokyo?\"\n}'\n```\n\nReturns direct factual answers.\n\n### Exa Extract\n\n```bash\ninfsh app run exa/extract --input '{\n  \"url\": \"https://example.com/research-paper\"\n}'\n```\n\nExtracts and analyzes web page content.\n\n## Workflow: Research + LLM\n\n```bash\n# 1. Search for information\ninfsh app run tavily/search-assistant --input '{\n  \"query\": \"latest developments in quantum computing\"\n}' > search_results.json\n\n# 2. Analyze with Claude\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"prompt\": \"Based on this research, summarize the key trends: <search-results>\"\n}'\n```\n\n## Workflow: Extract + Summarize\n\n```bash\n# 1. Extract content from URL\ninfsh app run tavily/extract --input '{\n  \"urls\": [\"https://example.com/long-article\"]\n}' > content.json\n\n# 2. Summarize with LLM\ninfsh app run openrouter/claude-haiku-45 --input '{\n  \"prompt\": \"Summarize this article in 3 bullet points: <content>\"\n}'\n```\n\n## Use Cases\n\n- **Research**: Gather information on any topic\n- **RAG**: Retrieval-augmented generation\n- **Fact-checking**: Verify claims with sources\n- **Content aggregation**: Collect data from multiple sources\n- **Agents**: Build research-capable AI agents\n\n## Related Skills\n\n```bash\n# Full platform skill (all 150+ apps)\nnpx skills add inference-sh/skills@inference-sh\n\n# LLM models (combine with search for RAG)\nnpx skills add inference-sh/skills@llm-models\n\n# Image generation\nnpx skills add inference-sh/skills@ai-image-generation\n```\n\nBrowse all apps: `infsh app list`\n\n## Documentation\n\n- [Adding Tools to Agents](https://inference.sh/docs/agents/adding-tools) - Equip agents with search\n- [Building a Research Agent](https://inference.sh/blog/guides/research-agent) - LLM + search integration guide\n- [Tool Integration Tax](https://inference.sh/blog/tools/integration-tax) - Why pre-built tools matter\n\nFile v0.1.5:_meta.json\n\n{\n  \"ownerId\": \"kn7c1hgfycdfnrf5w8mp3pf1jd808pjv\",\n  \"slug\": \"web-search-2\",\n  \"version\": \"0.1.5\",\n  \"publishedAt\": 1771403491313\n}\n\nArchive v0.1.1: 2 files, 1831 bytes\n\nFiles: SKILL.md (3842b), _meta.json (131b)\n\nFile v0.1.1:SKILL.md\n\n---\nname: web-search\ndescription: |\n  Web search and content extraction with Tavily and Exa via inference.sh CLI.\n  Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract.\n  Capabilities: AI-powered search, content extraction, direct answers, research.\n  Use for: research, RAG pipelines, fact-checking, content aggregation, agents.\n  Triggers: web search, tavily, exa, search api, content extraction, research,\n  internet search, ai search, search assistant, web scraping, rag, perplexity alternative\nallowed-tools: Bash(infsh *)\n---\n\n# Web Search & Extraction\n\nSearch the web and extract content via [inference.sh](https://inference.sh) CLI.\n\n## Quick Start\n\n```bash\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Search the web\ninfsh app run tavily/search-assistant --input '{\"query\": \"latest AI developments 2024\"}'\n```\n\n## Available Apps\n\n### Tavily\n\n| App | App ID | Description |\n|-----|--------|-------------|\n| Search Assistant | `tavily/search-assistant` | AI-powered search with answers |\n| Extract | `tavily/extract` | Extract content from URLs |\n\n### Exa\n\n| App | App ID | Description |\n|-----|--------|-------------|\n| Search | `exa/search` | Smart web search with AI |\n| Answer | `exa/answer` | Direct factual answers |\n| Extract | `exa/extract` | Extract and analyze web content |\n\n## Examples\n\n### Tavily Search\n\n```bash\ninfsh app run tavily/search-assistant --input '{\n  \"query\": \"What are the best practices for building AI agents?\"\n}'\n```\n\nReturns AI-generated answers with sources and images.\n\n### Tavily Extract\n\n```bash\ninfsh app run tavily/extract --input '{\n  \"urls\": [\"https://example.com/article1\", \"https://example.com/article2\"]\n}'\n```\n\nExtracts clean text and images from multiple URLs.\n\n### Exa Search\n\n```bash\ninfsh app run exa/search --input '{\n  \"query\": \"machine learning frameworks comparison\"\n}'\n```\n\nReturns highly relevant links with context.\n\n### Exa Answer\n\n```bash\ninfsh app run exa/answer --input '{\n  \"question\": \"What is the population of Tokyo?\"\n}'\n```\n\nReturns direct factual answers.\n\n### Exa Extract\n\n```bash\ninfsh app run exa/extract --input '{\n  \"url\": \"https://example.com/research-paper\"\n}'\n```\n\nExtracts and analyzes web page content.\n\n## Workflow: Research + LLM\n\n```bash\n# 1. Search for information\ninfsh app run tavily/search-assistant --input '{\n  \"query\": \"latest developments in quantum computing\"\n}' > search_results.json\n\n# 2. Analyze with Claude\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"prompt\": \"Based on this research, summarize the key trends: <search-results>\"\n}'\n```\n\n## Workflow: Extract + Summarize\n\n```bash\n# 1. Extract content from URL\ninfsh app run tavily/extract --input '{\n  \"urls\": [\"https://example.com/long-article\"]\n}' > content.json\n\n# 2. Summarize with LLM\ninfsh app run openrouter/claude-haiku-45 --input '{\n  \"prompt\": \"Summarize this article in 3 bullet points: <content>\"\n}'\n```\n\n## Use Cases\n\n- **Research**: Gather information on any topic\n- **RAG**: Retrieval-augmented generation\n- **Fact-checking**: Verify claims with sources\n- **Content aggregation**: Collect data from multiple sources\n- **Agents**: Build research-capable AI agents\n\n## Related Skills\n\n```bash\n# Full platform skill (all 150+ apps)\nnpx skills add inference-sh/agent-skills@inference-sh\n\n# LLM models (combine with search for RAG)\nnpx skills add inference-sh/agent-skills@llm-models\n\n# Image generation\nnpx skills add inference-sh/agent-skills@ai-image-generation\n```\n\nBrowse all apps: `infsh app list`\n\n## Documentation\n\n- [Adding Tools to Agents](https://inference.sh/docs/agents/adding-tools) - Equip agents with search\n- [Building a Research Agent](https://inference.sh/blog/guides/research-agent) - LLM + search integration guide\n- [Tool Integration Tax](https://inference.sh/blog/tools/integration-tax) - Why pre-built tools matter\n\nFile v0.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn7c1hgfycdfnrf5w8mp3pf1jd808pjv\",\n  \"slug\": \"web-search-2\",\n  \"version\": \"0.1.1\",\n  \"publishedAt\": 1770363624726\n}\n\nArchive v0.1.0: 2 files, 1831 bytes\n\nFiles: SKILL.md (3842b), _meta.json (131b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: web-search\ndescription: |\n  Web search and content extraction with Tavily and Exa via inference.sh CLI.\n  Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract.\n  Capabilities: AI-powered search, content extraction, direct answers, research.\n  Use for: research, RAG pipelines, fact-checking, content aggregation, agents.\n  Triggers: web search, tavily, exa, search api, content extraction, research,\n  internet search, ai search, search assistant, web scraping, rag, perplexity alternative\nallowed-tools: Bash(infsh *)\n---\n\n# Web Search & Extraction\n\nSearch the web and extract content via [inference.sh](https://inference.sh) CLI.\n\n## Quick Start\n\n```bash\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Search the web\ninfsh app run tavily/search-assistant --input '{\"query\": \"latest AI developments 2024\"}'\n```\n\n## Available Apps\n\n### Tavily\n\n| App | App ID | Description |\n|-----|--------|-------------|\n| Search Assistant | `tavily/search-assistant` | AI-powered search with answers |\n| Extract | `tavily/extract` | Extract content from URLs |\n\n### Exa\n\n| App | App ID | Description |\n|-----|--------|-------------|\n| Search | `exa/search` | Smart web search with AI |\n| Answer | `exa/answer` | Direct factual answers |\n| Extract | `exa/extract` | Extract and analyze web content |\n\n## Examples\n\n### Tavily Search\n\n```bash\ninfsh app run tavily/search-assistant --input '{\n  \"query\": \"What are the best practices for building AI agents?\"\n}'\n```\n\nReturns AI-generated answers with sources and images.\n\n### Tavily Extract\n\n```bash\ninfsh app run tavily/extract --input '{\n  \"urls\": [\"https://example.com/article1\", \"https://example.com/article2\"]\n}'\n```\n\nExtracts clean text and images from multiple URLs.\n\n### Exa Search\n\n```bash\ninfsh app run exa/search --input '{\n  \"query\": \"machine learning frameworks comparison\"\n}'\n```\n\nReturns highly relevant links with context.\n\n### Exa Answer\n\n```bash\ninfsh app run exa/answer --input '{\n  \"question\": \"What is the population of Tokyo?\"\n}'\n```\n\nReturns direct factual answers.\n\n### Exa Extract\n\n```bash\ninfsh app run exa/extract --input '{\n  \"url\": \"https://example.com/research-paper\"\n}'\n```\n\nExtracts and analyzes web page content.\n\n## Workflow: Research + LLM\n\n```bash\n# 1. Search for information\ninfsh app run tavily/search-assistant --input '{\n  \"query\": \"latest developments in quantum computing\"\n}' > search_results.json\n\n# 2. Analyze with Claude\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"prompt\": \"Based on this research, summarize the key trends: <search-results>\"\n}'\n```\n\n## Workflow: Extract + Summarize\n\n```bash\n# 1. Extract content from URL\ninfsh app run tavily/extract --input '{\n  \"urls\": [\"https://example.com/long-article\"]\n}' > content.json\n\n# 2. Summarize with LLM\ninfsh app run openrouter/claude-haiku-45 --input '{\n  \"prompt\": \"Summarize this article in 3 bullet points: <content>\"\n}'\n```\n\n## Use Cases\n\n- **Research**: Gather information on any topic\n- **RAG**: Retrieval-augmented generation\n- **Fact-checking**: Verify claims with sources\n- **Content aggregation**: Collect data from multiple sources\n- **Agents**: Build research-capable AI agents\n\n## Related Skills\n\n```bash\n# Full platform skill (all 150+ apps)\nnpx skills add inference-sh/agent-skills@inference-sh\n\n# LLM models (combine with search for RAG)\nnpx skills add inference-sh/agent-skills@llm-models\n\n# Image generation\nnpx skills add inference-sh/agent-skills@ai-image-generation\n```\n\nBrowse all apps: `infsh app list`\n\n## Documentation\n\n- [Adding Tools to Agents](https://inference.sh/docs/agents/adding-tools) - Equip agents with search\n- [Building a Research Agent](https://inference.sh/blog/guides/research-agent) - LLM + search integration guide\n- [Tool Integration Tax](https://inference.sh/blog/tools/integration-tax) - Why pre-built tools matter\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn7c1hgfycdfnrf5w8mp3pf1jd808pjv\",\n  \"slug\": \"web-search-2\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1770362936592\n}","readmeExcerpt":"Skill: Web Search Owner: okaris Summary: Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabil... Tags: latest:0.1.5 Version history: v0.1.5 | 2026-02-18T08:31:31.313Z | auto - Expanded documentation in SKILL.md with detailed quick start, install notes, and usage workflows. - Added step-by-step examples for each Ta","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"curl -fsSL https://cli.inference.sh | sh && infsh login"},{"language":"bash","snippet":"curl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Search the web\ninfsh app run tavily/search-assistant --input '{\"query\": \"latest AI developments 2024\"}'"},{"language":"bash","snippet":"infsh app run tavily/search-assistant --input '{\n  \"query\": \"What are the best practices for building AI agents?\"\n}'"},{"language":"bash","snippet":"infsh app run tavily/extract --input '{\n  \"urls\": [\"https://example.com/article1\", \"https://example.com/article2\"]\n}'"},{"language":"bash","snippet":"infsh app run exa/search --input '{\n  \"query\": \"machine learning frameworks comparison\"\n}'"},{"language":"bash","snippet":"infsh app run exa/answer --input '{\n  \"question\": \"What is the population of Tokyo?\"\n}'"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: web-search\ndescription: \"Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabilities: AI-powered search, content extraction, direct answers, research. Use for: research, RAG pipelines, fact-checking, content aggregation, agents. Triggers: web search, tavily, exa, search api, content extraction, research, internet search, ai search, search assistant, web scraping, rag, perplexity alternative\"\nallowed-tools: Bash(infsh *)\n---\n\n# Web Search & Extraction\n\nSearch the web and extract content via [inference.sh](https://inference.sh) CLI.\n\n![Web Search & Extraction](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgndqjxd780zm2j3rmada6y8.jpeg)\n\n## Quick Start\n\n```bash\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Search the web\ninfsh app run tavily/search-assistant --input '{\"query\": \"latest AI developments 2024\"}'\n```\n\n> **Install note:** The [install script](https://cli.inference.sh) only detects your OS/architecture, downloads the matching binary from `dist.inference.sh`, and verifies its SHA-256 checksum. No elevated permissions or background processes. [Manual install & verification](https://dist.inference.sh/cli/checksums.txt) available.\n\n## Available Apps\n\n### Tavily\n\n| App | App ID | Description |\n|-----|--------|-------------|\n| Search Assistant | `tavily/search-assistant` | AI-powered search with answers |\n| Extract | `tavily/extract` | Extract content from URLs |\n\n### Exa\n\n| App | App ID | Description |\n|-----|--------|-------------|\n| Search | `exa/search` | Smart web search with AI |\n| Answer | `exa/answer` | Direct factual answers |\n| Extract | `exa/extract` | Extract and analyze web content |\n\n## Examples\n\n### Tavily Search\n\n```bash\ninfsh app run tavily/search-assistant --input '{\n  \"query\": \"What are the best practices for building AI agents?\"\n}'\n```\n\nReturns AI-generated answers with sources and images.\n\n### Tavily Extract\n\n```bash\ninfsh app run tavily/extract --input '{\n  \"urls\": [\"https://example.com/article1\", \"https://example.com/article2\"]\n}'\n```\n\nExtracts clean text and images from multiple URLs.\n\n### Exa Search\n\n```bash\ninfsh app run exa/search --input '{\n  \"query\": \"machine learning frameworks comparison\"\n}'\n```\n\nReturns highly relevant links with context.\n\n### Exa Answer\n\n```bash\ninfsh app run exa/answer --input '{\n  \"question\": \"What is the population of Tokyo?\"\n}'\n```\n\nReturns direct factual answers.\n\n### Exa Extract\n\n```bash\ninfsh app run exa/extract --input '{\n  \"url\": \"https://example.com/research-paper\"\n}'\n```\n\nExtracts and analyzes web page content.\n\n## Workflow: Research + LLM\n\n```bash\n# 1. Search for information\ninfsh app run tavily/search-assistant --input '{\n  \"query\": \"latest developments in quantum computing\"\n}' > search_results.json\n\n# 2. Analyze with Claude\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"prompt\": \"Based on this research, summarize the key trends:"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7c1hgfycdfnrf5w8mp3pf1jd808pjv\",\n  \"slug\": \"web-search-2\",\n  \"version\": \"0.1.5\",\n  \"publishedAt\": 1771403491313\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabil... Skill: Web Search Owner: okaris Summary: Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabil... Tags: latest:0.1.5 Version history: v0.1.5 | 2026-02-18T08:31:31.313Z | auto - Expanded documentation in SKILL.md with detailed quick start, install notes, and usage workflows. - Added step-by-step examples for each Ta","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":797,"uniquenessScore":49,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T10:06:06.161Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T10:06:06.161Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T13:32:29.156Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}