Get the FREE Ultimate OpenClaw Setup Guide →

copilot-ask

npx machina-cli add skill dceoy/ai-coding-agent-skills/copilot-ask --openclaw
Files (1)
SKILL.md
2.5 KB

Copilot Ask Skill

Use GitHub Copilot CLI to answer questions about code without making modifications. This is a read-only analysis skill.

When to Use

  • User asks "how does X work?"
  • User wants to find where something is implemented
  • User needs to understand architecture or patterns
  • User is debugging and needs to understand code flow
  • User asks "what does this code do?"

Prerequisites

Verify GitHub Copilot CLI is available:

copilot --version

Note: Copilot will ask you to trust the files in the current folder before it can read them.

Basic Usage

Step 1: Parse the Question

Extract what the user wants to know and the scope (files, feature, component).

Step 2: Launch Copilot CLI

cd /path/to/project
copilot

Step 3: Ask the Question

Provide a clear prompt:

Explain how [FEATURE/COMPONENT] works in this codebase.

Please provide:
1. Direct answer to the question
2. Specific file paths and line numbers
3. Code examples from the actual codebase
4. Related concepts or dependencies

Do NOT make any changes - this is read-only analysis.

Step 4: Present the Answer

Format with:

  • Summary (1-2 sentences)
  • Details (explanation)
  • File references (paths + line numbers)
  • Code examples
  • Related info (dependencies, gotchas)

Tips

  • Use @path/to/file to include a specific file in the prompt.
  • Use /usage to view session usage details.
  • Use /model to pick another model if needed.
  • Use ? or copilot help to see available commands.

Use Custom Instructions

Copilot CLI automatically loads repository instructions if present:

  • .github/copilot-instructions.md
  • .github/copilot-instructions/**/*.instructions.md
  • AGENTS.md (agent instructions)

Error Handling

  • If Copilot is not found, ensure it is installed per the prerequisites in README.md and available in PATH.
  • If authentication fails, run /login and follow prompts.
  • If the answer is unclear, narrow the question and include file paths.

Related Skills

  • copilot-exec for code modifications
  • copilot-review for code reviews

Limitations

  • Read-only analysis
  • Interactive mode only
  • Limited by current codebase context

Source

git clone https://github.com/dceoy/ai-coding-agent-skills/blob/main/skills/copilot-ask/SKILL.mdView on GitHub

Overview

Copilot-Ask is a read-only analysis skill that uses GitHub Copilot CLI to explain how code works, where things are implemented, and which patterns are used. It helps you understand architecture, debugging flows, and code behavior without making any changes. Prerequisites include having Copilot CLI installed and accessible in PATH.

How This Skill Works

User's question is parsed to define scope (files, feature, component). The agent launches Copilot CLI in the project directory and submits a carefully crafted prompt. Copilot returns a structured answer with a direct explanation, file references, and code examples from the actual codebase, all in read-only mode.

When to Use It

  • User asks "how does X work?"
  • User wants to find where something is implemented
  • User needs to understand architecture or patterns
  • User is debugging and needs to understand code flow
  • User asks "what does this code do?"

Quick Start

  1. Step 1: Parse the user's question and define the scope (files, feature, component)
  2. Step 2: In your project directory, launch the Copilot CLI session (copilot)
  3. Step 3: Ask a clear prompt and review the read-only answer with summary, details, and file references

Best Practices

  • Keep prompts scoped to a specific feature or component to avoid broad, unfocused results
  • Include precise file paths and line numbers when relevant
  • Request a direct answer plus file references and code examples from the codebase
  • Ask for related concepts or dependencies to provide context
  • Do NOT request code changes; this is strictly read-only analysis

Example Use Cases

  • Explain how the user authentication flow works in the login module
  • Find where the payment success path is implemented in the checkout service
  • Describe the event-driven pattern used in the order processing pipeline
  • Trace the data flow during debugging of a null reference in utils
  • Describe what the helper function does and where it is used in the codebase

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers