Awesome Copilot Agents
✨ A curated list of awesome GitHub instructions, prompt, skills, MCPs and agent markdown files for enhancing your GitHub Copilot AI experience.
What is Awesome Copilot Agents?
Awesome Copilot Agents is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ✨ a curated list of awesome github instructions, prompt, skills, mcps and agent markdown files for enhancing your github copilot ai experience.
✨ A curated list of awesome GitHub instructions, prompt, skills, MCPs and agent markdown files for enhancing your GitHub Copilot AI experience.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- ✨ A curated list of awesome GitHub instructions, prompt, ski
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx awesome-copilot-agentsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Awesome Copilot Agents
Awesome Copilot Agents is a curated repository of GitHub Copilot enhancement resources including custom instruction files, reusable prompt templates, specialized AI agent personas, portable skill definitions, and MCP server integrations. It helps developers configure GitHub Copilot for specific languages (Python, Go, Rust, TypeScript, etc.), frameworks (Express, Azure Functions, Terraform), and workflows (PR reviews, task generation, architecture planning) by providing ready-to-use markdown files that Copilot reads from the .github/ directory.
Prerequisites
- GitHub Copilot subscription with access to GitHub Copilot in your IDE (VS Code, JetBrains, or GitHub.com)
- Git installed to clone the repository
- VS Code or another Copilot-supported IDE to use the instruction and prompt files
- An MCP-compatible client if using the included MCP server configurations
Clone the repository
Clone the awesome-copilot-agents repository to your local machine so you can browse and copy the resource files.
git clone https://github.com/Code-and-Sorts/awesome-copilot-agents.git
cd awesome-copilot-agentsBrowse the available resources
Explore the repository structure to find instructions, prompts, agents, skills, and MCP configurations relevant to your stack. Resources are organized by category and technology.
ls -la
# Key directories:
# instructions/ - .instructions.md files by language/framework
# prompts/ - .prompt.md reusable task templates
# agents/ - .agent.md custom AI persona definitions
# skills/ - portable capability files
# mcps/ - MCP server configurationsCopy instruction files to your project
Copy the relevant .instructions.md files into your project's .github/ directory. GitHub Copilot automatically reads these files to understand project context and coding conventions.
mkdir -p .github
# Example: copy Python instructions
cp awesome-copilot-agents/instructions/python.instructions.md .github/
# Example: copy Terraform instructions
cp awesome-copilot-agents/instructions/terraform.instructions.md .github/Add prompt templates to your project
Copy reusable .prompt.md files into .github/ for tasks you perform regularly such as PR reviews, task generation, or architecture planning. These become available as Copilot prompt shortcuts.
cp awesome-copilot-agents/prompts/create-prd.prompt.md .github/
cp awesome-copilot-agents/prompts/code-review.prompt.md .github/Configure MCP servers from the collection
Browse the mcps/ directory for MCP server configurations. Copy the JSON snippets into your MCP client configuration to connect GitHub, Playwright, Azure, or other tools to your AI assistant.
Awesome Copilot Agents Examples
Client configuration
Sample MCP server configurations from the awesome-copilot-agents collection. The exact list of available MCPs is in the repository's mcps/ directory.
{
"mcpServers": {
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "your-token-here"
}
},
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/project"]
}
}
}Prompts to try
After copying the resource files into your project, use these prompts with GitHub Copilot Chat.
- "Review this pull request using the code-review prompt template."
- "Generate a PRD for the feature I just described using the create-prd template."
- "Help me write a Terraform module following the project's infrastructure conventions."
- "Use the architect agent persona to evaluate the system design I described."
- "List all the MCP servers available in the awesome-copilot-agents collection."Troubleshooting Awesome Copilot Agents
Copilot does not pick up the instruction files
Ensure the .instructions.md files are in the .github/ directory at the root of your repository and that your VS Code Copilot extension is up to date. Instructions files require VS Code Copilot Chat 0.22+ or newer to be automatically loaded.
Prompt files are not appearing as Copilot shortcuts
Prompt files must use the .prompt.md extension and include valid YAML front matter with at least a 'mode' field. Verify the files were copied to .github/ and restart VS Code.
MCP server configs from the collection fail to connect
Each MCP server in the collection has its own dependencies and credentials. Check the individual MCP server's documentation for required API keys. For GitHub MCP, you need a personal access token with appropriate repository scopes.
Frequently Asked Questions about Awesome Copilot Agents
What is Awesome Copilot Agents?
Awesome Copilot Agents is a Model Context Protocol (MCP) server that ✨ a curated list of awesome github instructions, prompt, skills, mcps and agent markdown files for enhancing your github copilot ai experience. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Awesome Copilot Agents?
Follow the installation instructions on the Awesome Copilot Agents GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Awesome Copilot Agents?
Awesome Copilot Agents works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Awesome Copilot Agents free to use?
Yes, Awesome Copilot Agents is open source and available under the CC0-1.0 license. You can use it freely in both personal and commercial projects.
Awesome Copilot Agents Alternatives — Similar Developer Tools Servers
Looking for alternatives to Awesome Copilot Agents? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Awesome Copilot Agents in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Awesome Copilot Agents?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.