Latest Agent Skills

Generates a comprehensive, well-structured README.md file for a project by analyzing the workspace and following best practices.

Retrieves real-time Azure retail pricing from the public Azure Retail Prices API and estimates Copilot Studio agent credit consumption.

Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and audio narration from video files, reconstructs the step-by-step workflow, and proposes automation at multiple complexity levels using tools already installed on the user machine.

Manage Arize datasets and examples using the ax CLI: create, list, get, export, and append datasets for evaluation and experimentation.

Generate XML configuration files and execute SSMA Console commands for Oracle to SQL Server database migration, including schema conversion and data migration.

Runs AI-powered exploratory testing on web applications using the ScoutQA CLI, including smoke tests, accessibility audits, and user flow validation.

Open a GitHub PR dashboard in the browser for a specified date range and role filter.

Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend.

Merge, split, rotate, encrypt, decrypt, fill forms, watermark, stamp, and repair PDF files using the command-line tool PDFtk Server.

Build .NET MVVM ViewModels with CommunityToolkit.Mvvm source generators, base classes, and commands for WPF, WinUI, MAUI, Uno, and Avalonia.

Generates a comprehensive .editorconfig file based on project analysis and user preferences, ensuring consistent coding styles across editors.

Write effective unit tests with XUnit, covering standard and data-driven testing approaches.

Write effective unit tests with TUnit, covering standard tests, data-driven tests, and migration from xUnit.

Write effective unit tests with NUnit, covering standard and data-driven testing approaches.

Follow best practices for asynchronous programming in C#, including naming, return types, exception handling, performance, and common pitfalls.

Refines task prompts through iterative questioning about scope, deliverables, and constraints, then copies the final markdown to the clipboard.

Guides users through defining goals, metrics, and scope, then runs an autonomous loop of code changes, testing, measuring, and keeping or discarding results for any programming task with a measurable outcome.

Implement iterative evaluation and refinement loops for AI agent outputs, using self-critique, evaluator-optimizer patterns, and rubric-based scoring to improve quality.

Update the llms.txt file in the repository root to reflect changes in documentation, specifications, or repository structure, following the llms.txt specification.

Create concise tldr summaries for GitHub Copilot customization files, MCP server documentation, or Copilot documentation from URLs or queries.

Creates and maintains a personal context portfolio of structured markdown files describing identity, role, team, tools, communication style, and preferences.

Interprets shorthand, quasi-code, and natural language descriptions to produce production-quality code, bridging gaps between varying technical expertise levels.

Debug LLM applications using the Phoenix CLI: fetch traces, analyze errors, structure trace review with open and axial coding, inspect datasets, review experiments, and query the GraphQL API.

Publish and manage Windows applications in the Microsoft Store using the msstore CLI, including credential configuration, submission management, packaging, and CI/CD integration.

Integrate Microsoft Graph SDK into .NET, TypeScript/JavaScript, or Python projects to access Microsoft 365 data and services.

Build web-based games and game engines using HTML5 Canvas, WebGL, and JavaScript with frameworks like Phaser, Three.js, and Babylon.js.

Runs a three-layer verification pipeline on AI-generated output: extracts verifiable claims, finds supporting or contradicting sources via web search, and produces a structured verification report with source links for human review.

Ensure C# types are documented with XML comments following best practices for summaries, parameters, returns, and exceptions.

Generate an llms.txt file from repository structure, following the llms.txt specification to help LLMs navigate and understand the project.

Embed Copilot's agentic workflows in any application using Python, TypeScript, Go, or .NET.

Analyze a codebase and generate a structured map of files relevant to a task before making changes.

Interactive training for the GitHub Copilot CLI with guided lessons, quizzes, scenario challenges, and a full reference covering slash commands, shortcuts, modes, agents, skills, MCP, and configuration.

Write, debug, and maintain Windows batch files (.bat/.cmd) for system administration, automation, and CLI tool development.

Downloads, exports, and inspects Arize traces and spans to debug LLM application behavior using the ax CLI.

Convert Markdown files to professionally formatted Word (.docx) documents with embedded PNG images using pure JavaScript.

Write effective unit tests with JUnit 5, covering standard and data-driven testing approaches.

Go-to-market strategy for AI products, covering positioning, pricing, and enterprise objections.

Create standardized, semantic git commits using the Conventional Commits specification by analyzing diffs to determine type, scope, and message.

Extracts key definitions, points, keywords, diagrams, exam-ready sentences, and practice questions from provided study material and syllabus.

Configure and manage GitHub Dependabot for automated dependency updates, security alerts, and vulnerability scanning across multiple ecosystems.

Generates a structured HTML prep file for the next working day by pulling calendar data via WorkIQ, classifying meetings, detecting conflicts, finding learning and deep-work slots, and providing productivity recommendations.

Turn engineering work into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates by mining Copilot CLI session logs, git history, and GitHub PRs.

Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs.

Translates Copilot CLI prompts, errors, and technical output into plain English with color-coded risk indicators for non-technical users.

Manage DNS records for domains registered with Namecheap via their API, including setup and credential configuration.

Installs and configures Language Server Protocol servers for Copilot CLI to enable code intelligence features like go-to-definition, find-references, hover, and type info.

Ensure Java types are documented with Javadoc comments following best practices for documentation.

Refines task understanding through iterative questioning before executing, using the Joyride extension for human input.

Creates CodeTour .tour files — persona-targeted, step-by-step walkthroughs that link to real files and line numbers for any repository.

Transforms lessons learned into domain-organized memory instructions that persist across VS Code contexts, with global and workspace scopes.

Improve code structure and readability without changing external behavior through surgical refactoring techniques.

Performs a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fitness, and safety — producing a scored report with prioritized remediation actions.

Guides users to install and run the ai-ready skill for making repositories AI-ready with AGENTS.md, instructions, and CI workflows.

Generate personalized status briefings by pulling from configured data sources like GitHub, email, Teams, and Slack, then synthesizing updates in your own communication style.

Interact with MCP servers from the command line to discover, inspect, and call tools for external systems like GitHub, filesystems, databases, and APIs.

Analyzes documents and produces a Word document with inline highlighted screenshots from the source material, enabling visual verification of every factual claim.

Provides guidance on the history and correct usage of the em dash, enforcing a strict policy of never using em or en dashes in code or data files, and replacing them with hyphens. Also covers general punctuation rules for code comments.

Get best practices for Entity Framework Core, covering data context design, entity design, performance, migrations, querying, change tracking, security, and testing.

Opens a browser-based whiteboard for sketching ideas with sticky notes, then reads the visual snapshot and clipboard data to provide conversational analysis and suggestions.

Generate draw.io diagrams as .drawio files and export them to PNG, SVG, or PDF with embedded XML.