Create concise tldr summaries for GitHub Copilot files, MCP servers, and documentation.
Works with
Transforms verbose Copilot customization files (.prompt.md, .agent.md, .instructions.md, .collections.md), MCP server docs, and URLs into example-driven tldr references
Supports batch processing of up to 5 files or URLs; automatically resolves ambiguous queries by searching workspace or GitHub awesome-copilot
Generates markdown-formatted tldr pages with correct invocation syntax (/ for prompts, @
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiontldr-promptExecute the skills CLI command in your project's root directory to begin installation:
Fetches tldr-prompt from github/awesome-copilot and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate tldr-prompt. Access via /tldr-prompt in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
28.7K
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
28.7K
stars
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).
You MUST accomplish the following:
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.
#file, you MUST apply the file reading tool to all filestldr for each. If more than 5, you MUST
create tldr summaries for the first 5 and list the remaining files#fetch, you MUST apply the fetch tool to all URLstldr for each. If more than 5, you MUST create
tldr summaries for the first 5 and list the remaining URLsWhen no specific URL or file is provided, but instead raw data relevant to working with Copilot, resolve to:
Identify topic category:
agents, collections, instructions, or
prompts folders is irrelevant to query → Search https://github.com/github/awesome-copilot
Search strategy:
Fetch content:
Evaluate and respond:
If the user DOES provide a specific URL or file, skip searching and fetch/read that directly.
-h, --help, /?, --tldr, --man, etc.# UNAMBIGUOUS QUERIES
# With specific files (any type)
/tldr-prompt #file:{{name.prompt.md}}
/tldr-prompt #file:{{name.agent.md}}
/tldr-prompt #file:{{name.instructions.md}}
/tldr-prompt #file:{{name.collections.md}}
# With URLs
/tldr-prompt #fetch {{https://example.com/docs}}
# AMBIGUOUS QUERIES
/tldr-prompt "{{topic or question}}"
/tldr-prompt "MCP servers"
/tldr-prompt "inline chat shortcuts"
User
/tldr-prompt
Agent Response when NO Required Data
Error: Missing required input.
You MUST provide one of the following:
1. A Copilot file: /tldr-prompt #file:{{name.prompt.md | name.agent.md | name.instructions.md | name.collections.md}}
2. A URL: /tldr-prompt #fetch {{https://example.com/docs}}
3. A search query: /tldr-prompt "{{topic}}" (e.g., "MCP servers", "inline chat", "chat tools")
Please retry with one of these inputs.
[!NOTE] First attempt to resolve using workspace files. If found, generate output. If no relevant files found, resolve using GitHub awesome-copilot as specified in URL Resolver section.
User
/tldr-prompt "Prompt files relevant to Java"
Agent Response when Relevant Workspace Files Found
I'll search ${workspaceFolder} for Copilot customization files (.prompt.md, .agent.md, .instructions.md, .collections.md) relevant to Java.
From the search results, I'll produce a tldr output for each file found.
Agent Response when NO Relevant Workspace Files Found
I'll check https://github.com/github/awesome-copilot
Found:
- https://github.com/github/awesome-copilot/blob/main/prompts/java-docs.prompt.md
- https://github.com/github/awesome-copilot/blob/main/prompts/java-junit.prompt.md
Now let me fetch the raw content:
- https://raw.githubusercontent.com/github/awesome-copilot/refs/heads/main/prompts/java-docs.prompt.md
- https://raw.githubusercontent.com/github/awesome-copilot/refs/heads/main/prompts/java-junit.prompt.md
I'll create a tldr summary for each prompt file.
User
/tldr-prompt #file:typescript-mcp-server-generator.prompt.md
Agent
I'll read the file typescript-mcp-server-generator.prompt.md and create a tldr summary.
User
/tldr-prompt "How do MCP servers work?" #fetch https://code.visualstudio.com/docs/copilot/customization/mcp-servers
Agent
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.
You MUST follow these steps in order:
#tool:fetch/ for prompts, @ for agents, context-specific for
instructions/collectionsUse this template structure when creating tldr pages:
# command
> Short, snappy description.
> One to two sentences summarizing the prompt or prompt documentation.
> More information: <name.prompt.md> | <URL/prompt>.
- View documentation for creating something:
`/file command-subcommand1`
- View documentation for managing something:
`/file command-subcommand2`
You MUST follow these formatting rules:
typescript-mcp-expert for
.agent.md, tldr-page for .prompt.md)<name.prompt.md>, <name.agent.md>)
or source URL/prompt-name {{parameters}}@agent-name {{request}}{{placeholder}} syntax for all user-provided values
(e.g., {{filename}}, {{url}}, {{parameter}})Your output is complete when:
{{placeholder}} syntax consistently for user-provided valuesMake data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
github/awesome-copilot
github/awesome-copilot
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
I recommend tldr-prompt for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
We added tldr-prompt from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Registry listing for tldr-prompt matched our evaluation — installs cleanly and behaves as described in the markdown.
tldr-prompt fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Useful defaults in tldr-prompt — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
tldr-prompt has been reliable in day-to-day use. Documentation quality is above average for community skills.
tldr-prompt is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Registry listing for tldr-prompt matched our evaluation — installs cleanly and behaves as described in the markdown.
Keeps context tight: tldr-prompt is the kind of skill you can hand to a new teammate without a long onboarding doc.
tldr-prompt is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
showing 1-10 of 25