Skip to main content

Copilot customization cheat sheet

Compare the different customization options for GitHub Copilot.

GitHub Copilot offers several customization features that let you tailor its behavior to your workflow, your team's standards, and your project's needs. Use the tables below to find the right one for your use case.

Feature overview

This table shows what each customization feature is and where it lives.

FeatureWhat it isFilename and location
Custom instructionsAlways-on context that automatically applies to every interaction within its defined scope.github/copilot-instructions.md (repo-wide), .github/instructions/*.instructions.md (path-specific), AGENTS.md (third-party agents), or personal/org settings via UI on GitHub
Prompt filesReusable, standalone prompt template with input variables.github/prompts/*.prompt.md
Agentes personalizadosSpecialist persona with its own instructions, tool restrictions, and context.github/agents/AGENT-NAME.md (repo), agents/AGENT-NAME.md in .github-private repo (org/enterprise), or user profile
SubagentesSeparate agent spawned by the main agent to handle delegated work in an isolated contextN/A (runtime process, not a user-configured file)
Agent skillsFolder of instructions, scripts, and resources that Copilot loads when relevant to a task.github/skills/<skill-name>/SKILL.md (project) or ~/.copilot/skills/<skill-name>/SKILL.md (personal)
MCP serversConnection to external systems, APIs, and databasesmcp.json (path varies by IDE), repo settings on GitHub (agente de programación), or mcp-servers property in agente personalizado configurations

Usage comparison

This table helps you decide which customization feature to use.

FeatureHow to triggerBest forExample use cases
Custom instructionsAutomaticStandards, guidelines, or expectations that apply broadly across a contextEnforce coding standards, accessibility rules, review checklists
Prompt filesManual: reference directly in chat or use the prompt file pickerFocused single tasks you run once with different inputs each timeGenerate unit tests, run a code review checklist
Agentes personalizadosManual: select from the agent dropdown in your IDE, on GitHub, or in CLI de CopilotProjects or processes with distinct stages that need specialized capabilities or strict handoffsReact reviewer agent, read-only auditing agent
SubagentesAutomatic, or reference a subagente directly in your promptComplex subtasks that should run in isolation from the main agentCodebase research, running test suites
Agent skillsAutomatic: chosen by Copilot when relevant to your promptMulti-step workflows with bundled assets that should be loaded as neededGitHub Actions failure debugging, deployment procedures, release note drafting
MCP serversAutomatic, or ask for a specific tool by nameTasks that require access to external tools or real-time dataManage issues and PRs (GitHub MCP server), automate browser testing (Playwright MCP server)

IDE and surface support

This table shows which customization features are supported in each IDE and surface. For the full Copilot feature matrix, see Matriz de características de Copilot.

GitHub recommends using the latest stable IDE, CLI de Copilot, and Copilot extension versions to get the best Copilot experience.

Key:

  • ✓ = supported
  • ✗ = not supported
  • P = under preview
FeatureVS CodeVisual StudioJetBrains IDEsEclipseXcodeGitHub.comCLI de Copilot
Custom instructionsPPP
Prompt filesPP
Agentes personalizadosPPP
SubagentesPPP
Agent skillsP
MCP servers

For a detailed breakdown of which types of custom instructions are supported in each IDE and surface, see Compatibilidad con diferentes tipos de instrucciones personalizadas.

Further reading