SI

simple-fetch

A demonstration skill showing the CLI-to-MCP call pattern by fetching URL content.

Install

mkdir -p .claude/skills/simple-fetch && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/71" && unzip -o skill.zip -d .claude/skills/simple-fetch && rm skill.zip

Installs to .claude/skills/simple-fetch

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Basic MCP skill demonstrating CLI-based execution pattern for fetching URL content
82 charsno explicit “when” trigger
Beginner

Key capabilities

  • Accept CLI arguments for URL targeting
  • Execute MCP fetch tool calls
  • Return fetched content and byte count

How it works

The script acts as a CLI wrapper that passes a URL argument to an MCP fetch tool, returning the retrieved content to the user.

Inputs & outputs

You give it
URL string via CLI argument
You get back
Fetched webpage content and success status

When to use simple-fetch

  • Testing MCP skill patterns
  • Fetching webpage content for analysis
  • Learning how to structure a custom CLI skill
  • Debugging MCP tool execution

About this skill

Simple Fetch Skill

When to Use This Skill

Use this Skill to:

  • Learn the basic skill pattern
  • Fetch content from a URL
  • Use as a template for creating custom skills

This is a demonstration skill showing the minimal CLI-based pattern.

What This Skill Does

Demonstrates the core skill pattern:

  1. Accept CLI arguments (--url)
  2. Call an MCP tool (fetch__fetch)
  3. Return result

Instructions

When you need to fetch content from a URL, execute:

cd /home/khitomer/Projects/mcp-code-execution-enhanced

uv run python -m runtime.harness scripts/simple_fetch.py \
    --url "https://example.com"

Parameters

  • --url: The URL to fetch (required)

Example Usage

# Fetch a webpage
uv run python -m runtime.harness scripts/simple_fetch.py \
    --url "https://docs.example.com/api"

# Fetch documentation
uv run python -m runtime.harness scripts/simple_fetch.py \
    --url "https://github.com/owner/repo/README.md"

Expected Output

The skill returns the fetched content and prints:

  • Success message with byte count
  • Or error message if fetch fails

MCP Servers Required

Configure a fetch-capable MCP server in mcp_config.json:

{
  "mcpServers": {
    "fetch": {
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    }
  }
}

Technical Notes

  • Pattern: CLI args → MCP call → Result
  • Token cost: ~110 tokens (discover + read + execute)
  • Time: <10 seconds
  • Immutable: Parameters via CLI, no file editing needed

This skill demonstrates the foundation for creating more complex MCP workflows.

When not to use it

  • When complex authentication or session management is required

Prerequisites

uvmcp-server-fetch

Limitations

  • Limited to simple GET requests
  • Requires pre-configured MCP server

How it compares

This provides a standardized CLI pattern for MCP interaction rather than writing custom fetch logic for every new tool.

Compared to similar skills

simple-fetch side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
simple-fetch (this skill)118moReviewBeginner
dev-browser534moReviewIntermediate
agent-browser303moReviewIntermediate
browser-tools69moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

dev-browser

SawyerHood

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

53176

agent-browser

vercel-labs

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

3075

browser-tools

Whamp

Lightweight Chrome automation toolkit with shared configuration, JSON-first output, and six focused scripts for starting, navigating, inspecting, capturing, evaluating, and cleaning up browser sessions.

694

browser

cexll

This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP server required.

346

agent-browser-skill

MGdaasLab

基于 agent-browser CLI 的浏览器自动化工具。提供快照获取、元素交互、截图等功能。推荐用于需要页面快照分析、通过 ref 引用交互元素的场景。

439

browserwing-executor

browserwing

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.

27

Search skills

Search the agent skills registry