Web Search

This one lets Claude search the web and pull results into wiki pages when you say things like "search for" or "look up." It's intent-driven, supports multilingual triggers including Chinese, and uses httpx plus BeautifulSoup for fetching and parsing. Worth noting this is explicitly a v1 stub with the extract() method not implemented yet, so you're really getting the architecture and trigger setup. The actual search and ingestion logic is marked for v2. If you need web search working today, look elsewhere. If you want to fork it or you're fine waiting for the real implementation, the scaffolding is solid and the intent system is already wired up.

GitHub stars: 452
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add axoviq-ai/synthadoc --skill web_search --agent claude-code

Installs into .claude/skills of the current project.

Files

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:

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):

# 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):

export SYNTHADOC_WEB_SEARCH_MAX_RESULTS=10

Standalone usage

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

skill = WebSearchSkill()

SKILL.md on GitHub

Details

Repository: github.com/axoviq-ai/synthadoc
Category: Documentation
License: AGPL-3.0
First seen: Jun 11, 2026

More from axoviq-ai/synthadoc

All 9