add tldr-prompt prompt

[jhauga]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• My contribution adds a new instruction, prompt, or chat mode file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, or chat mode with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.

---

Description

Generates a quasi-tldr for files in agents, collections, instructions, and prompts, plus general Copilot documentation queries, condensing and formatting the results as tldr command-line calls.

Tested on several prompt files. All output was good. Handles variations like if an agent file was passed.

Test Case

/tldr-prompt #file:typescript-mcp-server-generator.prompt.md

Results

I'll read the file typescript-mcp-server-generator.prompt.md and create a tldr summary. 

Read file:typescript-mcp-server-generator.prompt.md

# typescript-mcp-server-generator

> Generate a complete, production-ready Model Context Protocol (MCP) server in TypeScript with tools, resources, and proper configuration.
> Creates a full project structure with @modelcontextprotocol/sdk, zod validation, TypeScript ES modules, and either HTTP or stdio transport.
> More information: <typescript-mcp-server-generator.prompt.md>

- Generate a basic MCP server with stdio transport and one tool:

`/typescript-mcp-server-generator "Create an MCP server with stdio transport and a file reading tool"`

- Generate an HTTP-based MCP server with Express:

`/typescript-mcp-server-generator "Create an HTTP MCP server with port 3000 and database query tools"`

- Generate an MCP server with multiple tools and resource support:

`/typescript-mcp-server-generator "Create an MCP server with file operations, API integration tools, and resource templates"`

- Generate an MCP server with custom tool for data transformation:

`/typescript-mcp-server-generator "Create an MCP server with a JSON transformation tool using zod validation"`

- Generate an MCP server with sampling support for LLM-powered features:

`/typescript-mcp-server-generator "Create an MCP server with text summarization tool that uses sampling"`

- Generate a complete MCP server with prompts and resources:

`/typescript-mcp-server-generator "Create a full-featured MCP server with tools, preconfigured prompts, and dynamic resources"`

- Generate an MCP server with specific configuration options:

`/typescript-mcp-server-generator "Create an MCP server with environment-based config, CORS support, and error handling"`

## Key Components

**Project Setup**: Initializes TypeScript/Node.js project with `@modelcontextprotocol/sdk`, `zod@3`, ES modules (`"type": "module"`), and dev dependencies like `tsx`.

**Server Types**: 
- **stdio**: Uses `StdioServerTransport` for local/command-line MCP servers
- **HTTP**: Uses `StreamableHTTPServerTransport` with Express for network-accessible servers

**Tool Implementation**: Uses `registerTool()` with zod schemas for validation, returns both `content` and `structuredContent`, includes async support and error handling.

**Optional Features**: Supports `registerResource()` for dynamic resources with ResourceTemplate, `registerPrompt()` for preconfigured prompts, sampling for LLM integration, and notification debouncing.

**Testing**: Run with `npm start` or `npx tsx server.ts`, test with `npx @modelcontextprotocol/inspector`, HTTP servers connect at `http://localhost:PORT/mcp`.

And test regarding something relevant to VS Code Copilot

Test Case

/tldr-prompt "How do MCP servers work?" #fetch https://code.visualstudio.com/docs/copilot/customization/mcp-servers

Results

I'll fetch the MCP server documentation from https://code.visualstudio.com/docs/copilot/customization/mcp-servers and create a tldr summary of how MCP servers work. 

Using "Fetch Web Page"

Fetched https://code.visualstudio.com/docs/copilot/customization/mcp-servers

# MCP servers

> Model Context Protocol (MCP) is an open standard that connects AI models to external tools and services through a unified interface in VS Code.
> MCP servers provide tools, resources, and prompts to extend GitHub Copilot Chat capabilities for tasks like file operations, databases, and API interactions.
> More information: <https://code.visualstudio.com/docs/copilot/customization/mcp-servers>

- Install an MCP server from the GitHub registry via Extensions view:

`@mcp` in Extensions search or `MCP: Browse Servers`

- Add an MCP server to workspace using configuration file:

`MCP: Open Workspace Folder Configuration` → Edit `mcp.json`

- Use an MCP tool automatically with agents in chat:

Open tool picker → Select MCP tools → Ask question (tools invoked automatically)

- Reference an MCP tool explicitly in your prompt:

`#{{tool-name}}`

- Add an MCP resource as context in chat:

`Add Context > MCP Resources > {{resource-type}}`

- Invoke an MCP server's preconfigured prompt:

`/mcp.{{servername}}.{{promptname}}`

- Restart an MCP server after configuration changes:

`MCP: List Servers > {{server-name}} > Restart Server`

- View MCP server logs for troubleshooting:

`MCP: List Servers > {{server-name}} > Show Output`

## How MCP Servers Work

**Architecture**: MCP servers run as separate processes that communicate with VS Code through standard I/O (stdio), HTTP, or Server-Sent Events (SSE). They're configured in `mcp.json` files at user or workspace level.

**Configuration**: Servers are defined with connection details (command/args for stdio, URL for HTTP/SSE), optional environment variables, and input placeholders for sensitive data like API keys. VS Code discovers server capabilities (tools, resources, prompts) on first start and caches them.

**Transport Methods**:
- **stdio**: Most common for local servers (npx, node, python, docker commands)
- **HTTP/SSE**: For remote servers or network-accessible services  
- **Unix sockets/Named pipes**: Local servers listening on sockets (`unix:///path/to/server.sock`) or pipes

**Three Capabilities**:
- **Tools**: Functions that agents can invoke automatically or you can reference with `#tool-name`
- **Resources**: Direct access to data (files, database tables) you can add as context
- **Prompts**: Preconfigured prompts you invoke with `/mcp.servername.promptname`

**Trust & Security**: VS Code prompts for confirmation before starting any MCP server for the first time. Servers can run arbitrary code—only add from trusted sources. Reset trust with `MCP: Reset Trust`.

**Tool Usage**: Maximum 128 tools per chat request due to model constraints. Use tool picker to enable/disable specific tools or group related tools into tool sets for easier management.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New chat mode file.
• New collection file.
• Update to existing instruction, prompt, chat mode, or collection.
• Other (please specify):

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[Copilot]

Pull request overview

This PR adds a new prompt file tldr-prompt.prompt.md that generates concise tldr-style summaries for GitHub Copilot customization files (prompts, agents, instructions, collections), MCP server documentation, and general Copilot documentation. The prompt uses the claude-sonnet-4 model and integrates tools for fetching web content and searching the workspace, making it a versatile documentation summarization tool.

Key Changes

• Adds a comprehensive prompt that creates tldr-pages-style summaries with example-driven documentation
• Implements smart query resolution that searches workspace files first, then falls back to the awesome-copilot repository on GitHub
• Updates the README to include the new TLDR Prompt entry in alphabetical order

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
prompts/tldr-prompt.prompt.md	New prompt file that generates tldr summaries for Copilot files and documentation, with comprehensive workflow, template guidelines, and query resolution strategies
docs/README.prompts.md	Adds the TLDR Prompt entry to the prompts table in alphabetical order between "Test Planning" and "TUnit Best Practices"