Coding standards, frameworks, refactoring, and code review (16.8K skills)
Review C#/.NET code for design patterns, separation of responsibilities, and common implementation issues. Receive actionable recommendations covering maintainability, testing, performance, and security without changing the code.
Turn a business use case into a Dataverse solution using Python. Get table and relationship designs, implementation code, usage instructions, and recommendations for error recovery, logging, monitoring, and performance based on the expected workload.
Build or modify content management systems such as WordPress and Shopify. Locate the right theme, extension, editor, or content layer, then make changes that respect platform conventions, media handling, previews, and publishing behavior.
Create a copilot-instructions.md file from an existing codebase. Identify technology versions, architecture, naming conventions, and testing practices, then turn observed patterns into project-specific guidance for GitHub Copilot without introducing unsupported assumptions.
Generate a customizable AI prompt for finding representative examples in an existing codebase. Configure analysis depth, categories, and snippets so GitHub Copilot can produce exemplars.md with real file references and explanations of coding conventions.
Turn a feature requirements document into a detailed Markdown implementation plan following Epoch’s monorepo structure. Cover frontend components, APIs, database design, security, performance, and deployment, with Mermaid diagrams showing system architecture and data relationships.
Generate commit messages from git diffs, staged changes, or written descriptions. Explain the reason and problem behind each change using Conventional Commits, a structured message format, and suggest separate messages for unrelated changes.
Create, debug, and maintain Windows batch scripts for file operations, backups, and scheduled tasks. Covers command arguments, variables, loops, and error handling, with starter templates for command-line tools and reusable functions.
Work through GitHub pull request feedback by classifying findings, fixing code, running repository checks, and posting replies. With suitable permissions, the skill repeats Copilot reviews until the latest code is reviewed and every thread has an agent response.
Create an Architectural Decision Record, a document explaining a system design choice. Organize context, rationale, alternatives, benefits, drawbacks, and implementation notes in consistent Markdown that people can read and AI tools can parse.
Turn a Python script into a beginner-friendly project by improving its structure and naming, adding comments that explain the reasoning, and creating a README.md tutorial covering setup, code logic, and example usage.
Create step-by-step code walkthroughs tailored to readers such as new contributors, reviewers, or bug fixers. Produce CodeTour .tour files linked to verified files and line numbers, with explanations of behavior, design choices, and pitfalls.
Turn application requirements into an Azure Cosmos DB NoSQL data model. Gather read and write patterns, workload volumes, and relationships, then document container structures, partition keys for distributing data, indexes, and design trade-offs in two Markdown files.
Create and check Git branch names using Conventional Branch rules. Choose a prefix for the task, normalize the description, detect the repository’s base branch, and create and switch to the new branch.
Build applications with GitHub Copilot SDK using Python, TypeScript, Go, or .NET. Add custom tools, display responses as they arrive, preserve conversations across restarts, and connect external tools through MCP, a protocol for connecting agents to tools.
Review Git changes and prepare consistent commit messages using Conventional Commits, a format that labels each change by type and scope. The workflow includes message validation, optional explanatory details, and committing changes through Copilot.
Create an AGENTS.md file that explains how coding agents should work in a project. Examine its structure and existing configuration, then document setup commands, development workflows, tests, coding conventions, builds, and contribution requirements.
Turn a product requirements document for a major development initiative into a technical architecture specification, including a Mermaid system diagram, major features, supporting technologies, technical value, and a rough size estimate.
Explore unfamiliar code with Codebase Memory to map architecture, trace function calls and dependencies, and assess change impact. Findings are checked against source files, with index freshness and coverage considered before drawing conclusions.
Map the code relevant to a task before implementation. Identify files to change, direct dependencies, related tests, and existing patterns, then organize the findings and potential risks into a structured document for review.
Improve code through repeated experiments against a measurable target, such as execution time or memory use. After defining scope and constraints, the agent tests changes, keeps improvements, reverts unsuccessful attempts, and logs results.
Plan and implement connections between Arduino devices and Azure IoT Hub, directly or through an IoT Edge gateway. Define sensor messages, device credentials, offline buffering, remote commands, and implementation tasks for firmware, gateways, and cloud services.
Analyze a codebase to document its technologies, architecture, dependencies, and implementation patterns. Produce a Markdown reference with optional diagrams, code examples, and guidance for adding features consistently with the existing design.
Build ASP.NET Minimal API endpoints with explicit request and response types, input validation, and standard error responses. Organize related endpoints and add OpenAPI documentation, a structured description of API operations, parameters, and schemas.