# Web Search

Search the web and ingest results as wiki pages

- Repository: https://github.com/axoviq-ai/synthadoc (1725 stars)
- Category: Engineering
- License: AGPL-3.0-or-later
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add axoviq-ai/synthadoc --skill web_search -g -a claude-code -y`
Codex: `npx skills add axoviq-ai/synthadoc --skill web_search -g -a codex -y`
Cursor: `npx skills add axoviq-ai/synthadoc --skill web_search -g -a cursor -y`
Gemini CLI: `npx skills add axoviq-ai/synthadoc --skill web_search -g -a gemini-cli -y`

## Description

Search the web and ingest results as wiki pages

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Web Search Skill

Accepts a natural language query, calls the Tavily AI search API, and
returns the top matching URLs. Your agent receives those URLs and decides
what to do with them, fetch each one, display them, pass them to another
skill, etc.

## Setup

**1. Install the dependency:**
```bash
pip install tavily-python
```

**2. Set your Tavily API key** (free tier: 1,000 searches/month, sign up at
https://tavily.com, no credit card required):
```bash
# macOS / Linux
export TAVILY_API_KEY="tvly-your-key-here"

# Windows (Command Prompt)
set TAVILY_API_KEY=tvly-your-key-here

# Windows (PowerShell)
$env:TAVILY_API_KEY = "tvly-your-key-here"
```

**3. Optional, cap the number of results** (default: 20):
```bash
export SYNTHADOC_WEB_SEARCH_MAX_RESULTS=10
```

## Standalone usage

```python
import asyncio
from synthadoc.skills.web_search.scripts.main import WebSearchSkill

skill = WebSearchSkill()

async def main():
    result = await skill.extract("search for: transformer architecture papers")
    urls = result.metadata["child_sources"]   # list[str], top matching URLs
    query = result.metadata["query"]          # "transformer architecture papers"
    print(f"Found {len(urls)} URLs for '{query}':")
    for url in urls:
        print(" ", url)

asyncio.run(main())
```

`result.text` is always empty, the skill is a discovery step that returns
URLs, not page content. Pass the URLs to the `url` or `youtube` skill (or
your own HTTP client) to fetch content.

## Intent prefixes

The skill strips a leading intent phrase before sending the query to Tavily:

| Input | Query sent to Tavily |
|---|---|
| `search for: RAG evaluation` | `RAG evaluation` |
| `find on the web: LLM benchmarks` | `LLM benchmarks` |
| `look up quantum computing` | `quantum computing` |
| `youtube: Karpathy transformers` | `Karpathy transformers` (YouTube only) |
| `搜索: 深度学习架构` | `深度学习架构` |

The rest: https://github.com/axoviq-ai/synthadoc/blob/HEAD/synthadoc/skills/web_search/SKILL.md