Web Search

---
name: web_search
description: Search the web for information relevant to the current experiment
argument-hint: <search query>
---

# Web Search Skill

## Purpose
Search the web to find information, best practices, latest techniques, and solutions relevant to the current optimization experiment.

## When to Use
- During `/sva:research` to understand best practices and latest methods for the target domain
- During `/sva:optimize` when subagents need external knowledge to form better hypotheses
- When encountering unfamiliar error patterns or library behaviors
- When looking for state-of-the-art approaches to beat the current frontier

## How to Use
Run:

```bash
python -c "from sva.web_search import search; import json; print(json.dumps(search('{QUERY}', max_results=5), indent=2))"
```

Replace `{QUERY}` with your search query. Results include title, URL, and snippet.

If `TAVILY_API_KEY` is set, the skill uses Tavily. Otherwise it falls back to DuckDuckGo.

## Rules
- Keep queries specific and technical
- Use results to inform hypotheses, not to copy-paste code blindly
- Always cite sources in experiment annotations