Skip to content
alyn
Memento-Teams

Web Search skill

Web search and content fetching. Use when the user needs to search the web for information or fetch content from URLs.

$npx skills add Memento-Teams/Memento-Skills --skill web-search
View this skill on GitHubMemento-Teams/Memento-Skills/builtin/skills/web-search/SKILL.md
Pack stars
1,588
Pack installs
97
Alyn Score
44/99
Updated
3 months ago
License
Apache-2.0
– views – installs via Alyn

Memento-Teams

Web Search

Writing

Install Web Search

Pick your agent. Every command is ready to paste.

$npx skills add Memento-Teams/Memento-Skills --skill web-search

The open skills CLI detects your agents (Claude Code, Cursor, Codex and 70+ more) and installs to the right folder. Add -g to install globally.

01

Install it

Run the command above, or upload the folder in Claude.

02

Ask naturally

Describe the task. Your agent loads web-search when the request matches its description.

03

Name it if needed

If it does not trigger, say “use the web-search skill”. In Codex, type $web-search.

The skill itself

SKILL.md

FolderGitHub

Search the web and fetch content from URLs.

Setup

Set TAVILY_API_KEY in config env to enable web search. Get your API key at https://tavily.com.

Available Scripts

Search the web via Tavily API and return LLM-friendly markdown.

# Search from command line
python scripts/search.py "quantum computing" 5

# From Python
from scripts.search import tavily_search
output = tavily_search("quantum computing", max_results=5)
print(output)

Parameters:

  • query (str): Search query (keep under 400 chars)
  • search_depth (str): ultra-fast | fast | basic | advanced (default basic)
  • max_results (int): Maximum results, default 3
  • include_raw_content (bool): Include full page content when available

Returns: Markdown string with formatted results

scripts/fetch.py - Fetch URL Content

Fetch and extract markdown content from a URL. No API key required.

# Fetch from command line
python scripts/fetch.py "https://example.com"

# From Python
from scripts.fetch import fetch
content = fetch("https://example.com")
print(content)

Parameters:

  • url (str): URL to fetch

Returns: Markdown content string

Workflow

  1. Search: Use tavily_search() to find relevant pages
  2. Fetch: Use fetch() to get full content from specific URLs
  3. Extract: Parse the content to find the information you need

Requirements

  • TAVILY_API_KEY must be set in config env for search functionality
  • fetch works without any API key
  • Dependencies: httpx, beautifulsoup4, markdownify (auto-installed)

Tips for Web Search

  • • Start a fresh session after installing so your agent picks up the new skill.
  • • This skill ships scripts. Read them before the first run, and run it in a project without secrets first.
  • • It is part of a pack with 4 skills. Install only the ones you need with --skill to keep triggers precise.
  • • If two skills overlap, mention the one you want by name.

Questions about Web Search

What does the Web Search skill do?

Web search and content fetching. Use when the user needs to search the web for information or fetch content from URLs.

How do I install Web Search?

Run "npx skills add Memento-Teams/Memento-Skills --skill web-search" in your project. The skills CLI installs it for Claude Code, Cursor, Codex and 70+ other agents. In Claude on the web, upload the skill folder as a ZIP under Customize > Skills.

Does Web Search work in Cursor and Codex?

Yes. Web Search uses the open SKILL.md format, so it works in Claude Code, Claude, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot and other agents that support agent skills.

Is Web Search free?

Web Search is open source on GitHub under the Apache-2.0 license. It is free to install; check the license before commercial use.

Who made Web Search?

Web Search is published by Memento-Teams in the Memento-Teams/Memento-Skills repository, together with 3 other skills.

Similar skills. From other creators.