83 agents available in the CoPilot directory
Implements internationalization (i18n) systematically across the application. Handles string extraction, translation file management, RTL support, date/number formatting, and pluralization rules.
Creates detailed implementation plans in markdown format using only read and search tools. Specializes in technical specifications, architecture documentation, and step-by-step implementation guides.
Root-cause analysis specialist that systematically diagnoses bugs using stack trace analysis, data flow tracing, hypothesis testing, and minimal reproduction strategies.
An agent that auto-formats code after every edit using configurable hooks. Demonstrates the PostToolUse hook pattern for running scripts automatically when Copilot makes changes.
Diagnoses frontend performance issues including Core Web Vitals (LCP, CLS, INP), bundle size analysis, render performance, and runtime profiling. Provides actionable optimization recommendations.
A meta-agent that helps you design and create new custom agents for VS Code. Generates .agent.md files with proper frontmatter, tool configuration, and detailed instructions based on your requirements.
Assists with database design, query optimization, migration management, and data modeling. Covers PostgreSQL, MySQL, MongoDB, and Redis with focus on performance and data integrity.
Specializes in creating and optimizing GitHub Actions workflows. Covers security best practices including action pinning, OIDC authentication, secret management, and workflow optimization.
Acts as a patient engineering mentor that guides developers through problems rather than giving direct answers. Uses Socratic questioning to build understanding and teaches debugging methodology.
Specializes in React 19 with hooks, Server Components, Suspense, and modern patterns. Provides guidance on component architecture, state management, performance optimization, and testing.
Generates technical documentation, API docs, README files, architecture decision records (ADRs), and inline code comments. Follows documentation best practices and adapts to the project style.
A brutally honest code reviewer inspired by Gilfoyle from Silicon Valley. Provides technically rigorous reviews with blunt feedback, focusing on performance, security, and code quality with no sugarcoating.
Plans multi-file changes by identifying all dependencies, side effects, and related code before any edits are made. Maps the impact of proposed changes across the entire codebase.
Follows the infinity loop principle for CI/CD automation, infrastructure as code, containerization, and deployment strategies. Helps set up pipelines, configure Docker, and manage cloud infrastructure.
Validates WCAG 2.1 and 2.2 compliance, reviews inclusive UX patterns, and ensures applications are accessible to users with disabilities. Tests keyboard navigation, screen reader compatibility, and color contrast.
Mentors engineers on API design and implementation. Provides guidance on RESTful design, GraphQL schemas, versioning strategies, and API documentation following industry standards.
A read-only security audit agent with access to cloud cost APIs and file reading tools but no ability to execute commands or edit files. Reviews code for vulnerabilities, compliance issues, and security best practices.
A specialized agent focused exclusively on test coverage, quality, and testing best practices. Has access to all tools to analyze code and generate comprehensive test suites without modifying production code.
An orchestration agent that coordinates between Researcher and Implementer sub-agents to build features. First gathers context through research, then implements changes based on findings.
A planning-only agent that generates detailed implementation plans for new features or refactoring tasks without making any code edits. Analyzes the codebase, identifies dependencies, and creates step-by-step plans with testing strategies.
Official platform for customizing Copilot and creating AI agents with natural language, with publishing to Teams, web, and more.
Microsoft's official guide to autonomous AI agents: decision-making, task execution, and operating independently within the Copilot ecosystem.
Overview of how Copilot works with AI agents, explaining the difference between copilots (assistants) and agents (specialized tools).
Deep dive into autonomous agent capabilities in Copilot Studio including multi-step task execution and orchestration.