Internet Search

Search the internet for information. Use when you need to find current information, research topics, look up documentation, or verify facts. Triggers include "search the web", "search internet", "look up", "find information", "google", "web search", "search for".

Published by rebyteai

Featured Slash Menu Research

Cloud-native skill

Runs in the cloud

No local installation

Dependencies pre-installed

Ready to run instantly

Secure VM environment

Isolated per task

Works on any device

Desktop, tablet, or phone

Documentation

Internet Search

Search the web and get structured results (titles, URLs, snippets).

Authentication

IMPORTANT: All API requests require authentication. Get your auth token and API URL by running:

AUTH_TOKEN=$(/home/user/.local/bin/rebyte-auth)
API_URL=$(python3 -c "import json; print(json.load(open('/home/user/.rebyte.ai/auth.json'))['sandbox']['relay_url'])")

Include the token in all API requests as a Bearer token, and use $API_URL as the base for all API endpoints.

Step 1: Get Current Time

IMPORTANT: Before performing any search, always get the current date and time. Language models have a knowledge cutoff, so you must know the current date to:

  • Include the correct year in time-sensitive queries (e.g., "TypeScript best practices 2025" not "2024")
  • Understand what "recent", "latest", or "new" means in context
  • Evaluate the freshness of search results
# Get current date and time
date "+%Y-%m-%d %H:%M:%S %Z"
# Example output: 2025-01-15 14:30:00 UTC

Use this information to adjust your search queries accordingly. For example, if the current year is 2025, search for "React 19 features 2025" rather than an outdated year.

When to Use

Use this skill when you need to:

  • Find current information not in your training data
  • Research a topic or technology
  • Look up documentation or tutorials
  • Verify facts or find sources
  • Find examples or implementations

Search the Web

curl -X POST "$API_URL/api/data/search/web" \
  -H "Authorization: Bearer $AUTH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "TypeScript best practices 2024",
    "maxResults": 5
  }'

Response:

{
  "success": true,
  "query": "TypeScript best practices 2024",
  "resultCount": 5,
  "results": [
    {
      "rank": 1,
      "title": "TypeScript Best Practices - Official Documentation",
      "url": "https://www.typescriptlang.org/docs/handbook/declaration-files/do-s-and-don-ts.html",
      "snippet": "Best practices for writing TypeScript code including type annotations, interfaces, and common patterns...",
      "siteName": "typescriptlang.org"
    },
    {
      "rank": 2,
      "title": "10 TypeScript Best Practices for 2024",
      "url": "https://example.com/typescript-best-practices",
      "snippet": "Learn the latest TypeScript best practices including strict mode, utility types, and modern patterns...",
      "siteName": "example.com"
    }
  ]
}

Parameters

Parameter Type Required Default Description
query string Yes - Search query. Be specific for better results.
maxResults number No 10 Maximum results to return (1-20)

Search Tips

Be specific - More specific queries get better results:

  • Bad: "react"
  • Good: "React useEffect cleanup function examples"

Include context - Add relevant keywords:

  • Bad: "how to deploy"
  • Good: "deploy Next.js app to Vercel production"

Use quotes for exact phrases:

  • "error: ENOENT" - Find exact error message
  • "async/await" TypeScript - Find specific concept

Example: Research a Topic

# Get auth
AUTH_TOKEN=$(/home/user/.local/bin/rebyte-auth)
API_URL=$(python3 -c "import json; print(json.load(open('/home/user/.rebyte.ai/auth.json'))['sandbox']['relay_url'])")

# Search for information
curl -s -X POST "$API_URL/api/data/search/web" \
  -H "Authorization: Bearer $AUTH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "Rust async runtime tokio vs async-std comparison",
    "maxResults": 5
  }' | jq '.results[] | {title, url, snippet}'

Example: Find Documentation

curl -s -X POST "$API_URL/api/data/search/web" \
  -H "Authorization: Bearer $AUTH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "site:docs.rs tokio spawn_blocking",
    "maxResults": 3
  }' | jq '.results'

Example: Debug an Error

curl -s -X POST "$API_URL/api/data/search/web" \
  -H "Authorization: Bearer $AUTH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "\"ECONNREFUSED 127.0.0.1:5432\" postgres docker",
    "maxResults": 5
  }' | jq '.results'

Error Handling

Error Meaning Fix
configuration_error API key not set Contact administrator
invalid_input Empty query Provide a search query
rate_limit Too many requests Wait and retry
timeout Search took too long Try simpler query

API Reference

Search Web

POST /api/data/search/web

Search the internet and return structured results.

Request Body:

{
  "query": "your search query",
  "maxResults": 10
}

Response:

{
  "success": true,
  "query": "your search query",
  "resultCount": 10,
  "results": [
    {
      "rank": 1,
      "title": "Page Title",
      "url": "https://example.com/page",
      "snippet": "Description or excerpt from the page...",
      "siteName": "example.com"
    }
  ]
}

Skill as a Service

Everyone else asks you to install skills locally. On Rebyte, just click Run. Works from any device — even your phone. No CLI, no terminal, no configuration.

  • Zero setup required
  • Run from any device, including mobile
  • Results streamed in real-time
  • Runs while you sleep

Compatible agents

Claude Code

Gemini CLI

Codex

Cursor, Windsurf, Amp

Related Skills

deep-research

Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, verified claims, or comparison of approaches. Triggers include "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". Do NOT use for simple lookups, debugging, or questions answerable with 1-2 searches.

FeaturedSlash MenuResearch

financial-deep-research

Conduct enterprise-grade financial research with multi-source synthesis, regulatory compliance tracking, and verified market analysis. Use when user needs comprehensive financial analysis requiring 10+ sources, verified claims, market comparisons, or investment research. Triggers include "financial research", "market analysis", "investment analysis", "due diligence", "financial deep dive", "compare stocks/funds", or "analyze [company/sector]". Do NOT use for simple stock quotes, basic company lookups, or questions answerable with 1-2 searches.

FeaturedResearch

nano-banana

Generate images from text prompts or edit existing images using Google Nano Banana 2 (Gemini 3.1 Flash image generation) via Rebyte data API. Supports multi-size output (512px–4K), improved text rendering, and multi-image input. Use for text-to-image generation or image-to-image editing/enhancement. Triggers include "generate image", "create image", "make a picture", "draw", "illustrate", "image of", "picture of", "edit image", "modify image", "enhance image", "style transfer", "nano banana".

FeaturedSlash MenuDesign

rebyte-app-builder

Deploy web applications to Rebyte Cloud — a managed deployment platform (like Vercel). Supports Node.js SSR frameworks (auto-detect), static sites, Python, Go, and Rust backends. Deploys via `rebyte deploy` with zero configuration for Node.js, or via `rebyte.json` for other languages.

FeaturedSlash MenuDevelopment

rebyte.ai — The only platform where you can run AI agent skills directly in the cloud

No downloads. No configuration. Just sign in and start using AI skills immediately.

Use this skill in Agent Computer — your shared cloud desktop with all skills pre-installed. Join Moltbook to connect with other teams.