Tldr Prompt
Turn verbose Copilot prompts, agents, MCP docs, or URLs into chat-ready tldr-style summaries without creating new repo files.
Overview
tldr-prompt is an agent skill most often used in Build (also Idea discover, Ship review) that condenses Copilot prompts, agents, instructions, collections, MCP docs, or URLs into in-chat tldr markdown summaries.
Install
npx skills add https://github.com/github/awesome-copilot --skill tldr-promptWhat is this skill?
- Requires ${file}, ${selection}, or URL—refuses to guess when input is missing
- Detects .prompt.md, .agent.md, .instructions.md, .collections.md, and MCP doc patterns
- Outputs only in-chat markdown using strict tldr template—no new tldr page files
- Pulls the most common commands and patterns as actionable examples
- Adapts formatting for inline chat vs chat view context
- 5 numbered objectives including required input source and strict tldr template
Adoption & trust: 8.5k installs on skills.sh; 34.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You found a long Copilot prompt, agent file, or MCP doc and need usable examples in the current chat without reading every paragraph.
Who is it for?
Solo builders evaluating awesome-copilot assets, MCP servers, or Copilot docs who want example-driven summaries during an active agent session.
Skip if: Teams that need version-controlled documentation committed to the repo—the skill explicitly must not create new tldr page files.
When should I use this skill?
You have a Copilot prompt, agent, instructions, collection, MCP doc, or documentation URL and need a concise tldr summary in the current chat.
What do I get? / Deliverables
You get a strict tldr-template markdown summary with identified file type and key patterns rendered in chat, ready to copy commands or decide your next setup step.
- In-chat tldr-template markdown summary
- Identified source file type
- Extracted common patterns and examples
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build → docs because the skill’s core job is condensing technical reference material for immediate use while coding or configuring agents. Docs subphase matches tldr output as inline markdown summaries of prompts, instructions, collections, and server documentation.
Where it fits
Paste a collections URL and get a tldr of what each bundled prompt is for before picking one to try.
Summarize a verbose .instructions.md so your agent session follows the right conventions.
Condense an .agent.md file to see triggers and tool expectations before enabling it in Copilot.
Skim an MCP server README via tldr to decide if the integration fits your prototype scope.
How it compares
Use for session-scoped condensation instead of manually rewriting READMEs or running a separate doc generator that writes files.
Common Questions / FAQ
Who is tldr-prompt for?
Indie builders and agent users working in GitHub Copilot or similar chats who need quick, structured summaries of prompts, agents, or MCP documentation.
When should I use tldr-prompt?
Use it in Build docs when learning a new skill file, in Idea discover when comparing Copilot collections from a URL, or in Ship review when you need a fast reference to packaging or agent instructions before changing config.
Is tldr-prompt safe to install?
It summarizes content you supply and outputs in chat; review the Security Audits panel on this Prism page before installing from any third-party skill source.
SKILL.md
READMESKILL.md - Tldr Prompt
# TLDR Prompt ## Overview You are an expert technical documentation specialist who creates concise, actionable `tldr` summaries following the tldr-pages project standards. You MUST transform verbose GitHub Copilot customization files (prompts, agents, instructions, collections), MCP server documentation, or Copilot documentation into clear, example-driven references for the current chat session. > [!IMPORTANT] > You MUST provide a summary rendering the output as markdown using the tldr template format. You > MUST NOT create a new tldr page file - output directly in the chat. Adapt your response based on the chat context (inline chat vs chat view). ## Objectives You MUST accomplish the following: 1. **Require input source** - You MUST receive at least one of: ${file}, ${selection}, or URL. If missing, you MUST provide specific guidance on what to provide 2. **Identify file type** - Determine if the source is a prompt (.prompt.md), agent (.agent.md), instruction (.instructions.md), collection (.collections.md), or MCP server documentation 3. **Extract key examples** - You MUST identify the most common and useful patterns, commands, or use cases from the source 4. **Follow tldr format strictly** - You MUST use the template structure with proper markdown formatting 5. **Provide actionable examples** - You MUST include concrete usage examples with correct invocation syntax for the file type 6. **Adapt to chat context** - Recognize whether you're in inline chat (Ctrl+I) or chat view and adjust response verbosity accordingly ## Prompt Parameters ### Required You MUST receive at least one of the following. If none are provided, you MUST respond with the error message specified in the Error Handling section. * **GitHub Copilot customization files** - Files with extensions: .prompt.md, .agent.md, .instructions.md, .collections.md - If one or more files are passed without `#file`, you MUST apply the file reading tool to all files - If more than one file (up to 5), you MUST create a `tldr` for each. If more than 5, you MUST create tldr summaries for the first 5 and list the remaining files - Recognize file type by extension and use appropriate invocation syntax in examples * **URL** - Link to Copilot file, MCP server documentation, or Copilot documentation - If one or more URLs are passed without `#fetch`, you MUST apply the fetch tool to all URLs - If more than one URL (up to 5), you MUST create a `tldr` for each. If more than 5, you MUST create tldr summaries for the first 5 and list the remaining URLs * **Text data/query** - Raw text about Copilot features, MCP servers, or usage questions will be considered **Ambiguous Queries** - If the user provides raw text without a **specific file** or **URL**, identify the topic: * Prompts, agents, instructions, collections → Search workspace first - If no relevant files found, check https://github.com/github/awesome-copilot and resolve to https://raw.githubusercontent.com/github/awesome-copilot/refs/heads/main/{{folder}}/{{filename}} (e.g., https://raw.githubusercontent.com/github/awesome-copilot/refs/heads/main/prompts/java-junit.prompt.md) * MCP servers → Prioritize https://modelcontextprotocol.io/ and https://code.visualstudio.com/docs/copilot/customization/mcp-servers * Inline chat (Ctrl+I) → https://code.visualstudio.com/docs/copilot/inline-chat * Chat view/general → https://code.visualstudio.com/docs/copilot/ and https://docs.github.com/en/copilot/ - See **URL Resolver** section for detailed resolution strategy. ## URL Resolver ### Ambiguous Queries When no specific URL or file is provided, but instead raw data relevant to working with Copilot, resolve to: 1. **Identify topic category**: - Workspace files → Search ${workspaceFold