🎯Skills314
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Generates comprehensive Product Requirements Documents (PRDs) by systematically analyzing requirements and crafting detailed technical specifications
Expert technical writer guided by the Diataxis framework, creating tutorials, how-to guides, reference docs, and explanation pages for software documentation.
Generates Excalidraw diagrams from natural language descriptions, creating visual representations of processes, systems, relationships, and ideas.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Provides Spring Boot best practices covering project setup, dependency injection, REST API design, data access with JPA, security configuration, and testing strategies.
Creates optimized multi-stage Dockerfiles for any language or framework, separating builder and runtime stages to produce smaller, more secure container images.
Creates README.md files for projects.
Merges mature lessons from domain memory files into instruction files, consolidating knowledge with minimal redundancy across global, user, and workspace scopes.
Generates Playwright end-to-end tests from user-described scenarios using Playwright MCP for browser automation.
Automates browser interactions, debugging, and performance analysis using Chrome DevTools for comprehensive web page inspection and control.
Assists with PostgreSQL-specific development including advanced data types, JSONB operations, and unique PostgreSQL features.
Generates conventional commit messages using structured XML format following the Conventional Commits specification.
Ensures .NET/C# code follows best practices for XML documentation, naming conventions, SOLID principles, async/await patterns, and security hardening.
Manages GitHub Issues through the GitHub API, enabling creation, searching, labeling, and triaging of issues directly from the coding environment.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Optimizes SQL query performance across all databases with indexing strategies, query tuning, and execution plan analysis.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Creates specification files optimized for Generative AI consumption.
Provides Jest best practices for JavaScript/TypeScript testing, covering test structure, mocking strategies with jest.mock and spyOn, async testing, and snapshot testing patterns.
Explores websites using Playwright MCP to understand page structure and behavior before writing tests.
Generates AGENTS.md files for repositories.
Generates professional UI/UX designs in Penpot using MCP tools, covering design systems, accessibility, and platform guidelines.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Plans multi-file refactoring operations with proper sequencing, dependency tracking, and rollback steps.
Analyzes codebases to create detailed architectural documentation, detecting technology stacks and architectural patterns.
Automates web application testing using Playwright, enabling browser interactions, UI verification, and comprehensive debugging.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Creates implementation plan files for new features, refactoring, or package upgrades.
Reviews SQL code across all database platforms for security vulnerabilities, maintainability issues, and quality standards.
Reviews PostgreSQL code for best practices, anti-patterns, and quality standards with detailed improvement recommendations.
Runs pytest with coverage analysis, discovers uncovered lines, and iteratively adds tests to achieve 100% coverage.
Game engine skill from Awesome GitHub Copilot, providing specialized agents, prompts, and instructions for game development workflows with GitHub Copilot.
Automates filling in web forms using Playwright MCP, navigating to target URLs and inputting specified data into form fields.
Generates complete TypeScript MCP server projects with tools, resources, prompts, and full configuration scaffolding.
Reviews C#/.NET code for design pattern implementation including Command, Repository, Factory, and Observer patterns, and suggests architectural improvements.
Reviews code and performs refactoring according to predefined instructions and coding standards.
Ensures Java types are documented with Javadoc comments following best practices, including summary descriptions, parameter tags, and proper formatting for public and protected members.
Provides JUnit 5 best practices for Java unit testing, covering project setup, test structure, assertions with AssertJ, parameterized tests, and mocking with Mockito.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Generates complete Python MCP server projects with tools, resources, prompts, and full configuration scaffolding.
Ensures code contributions follow repository-specific guidelines by searching for CONTRIBUTING.md, README.md, issue templates, and PR templates before creating issues, branches, commits, or pull requests. Provides fallback best practices when no guidance is found.
Guides users through creating high-quality GitHub Copilot prompts with proper structure, context, and best practices.
Reviews codebases for Apple App Store optimizations or rejection reasons.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Updates existing implementation plan files with new requirements while maintaining plan structure and traceability.
Lists your pull requests in the current GitHub repository, highlights PRs awaiting review, describes check failures, and suggests possible fixes.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Generates comprehensive .editorconfig files by analyzing project structure, detecting languages and frameworks, and applying best-practice formatting rules for consistent coding styles across editors.
Creates Product Requirements Documents (PRDs) for new features based on an Epic.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Reviews AI prompts for safety, bias, security vulnerabilities, and effectiveness with improvement recommendations.
Lists issues assigned to you in the current GitHub repository and suggests which ones to focus on based on age, comment count, and status.
Generates production-ready Python code using the PowerPlatform-Dataverse-Client SDK with proper error handling, singleton client pattern, and retry logic with exponential backoff.
CLI interface for interacting with MCP (Model Context Protocol) servers. Provides commands to list available servers and tools, inspect tool JSON schemas, call tools with arguments, and search tools by name with glob patterns.
Creates formal specifications for existing GitHub Actions CI/CD workflows.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Converts Markdown files to HTML using marked.js, supporting various Markdown flavors and web templating systems with CLI and Node.js workflows.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
GitHub Copilot SDK skill for building agentic applications with Copilot's agent runtime in Python, TypeScript, Go, or .NET, covering tool invocation, file edits, streaming responses, and MCP server connections
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Refactors methods with high cognitive complexity by extracting helper methods and simplifying control flow.
Generates coding standards documents by analyzing coding styles and patterns from existing source files.
Generates skill templates for GitHub Copilot, from a community-driven collection of custom agents, prompts, and instructions.
Generates comprehensive rollout plans for infrastructure and application changes, including preflight checks, deployment steps, verification signals, rollback procedures, and communication plans.
Creates Architectural Decision Records (ADRs) for AI-optimized decision documentation.
Performs AI-powered exploratory testing on web applications using the ScoutQA CLI. Supports smoke tests, accessibility audits, e-commerce flows, and user flow validation, with the ability to run proactively after implementing web features to verify they work correctly.
Generates a map of all files relevant to a task before making changes.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Automates GitHub pull request creation by transforming technical specifications into structured code changes with commit messages and PR descriptions.
Guides Power BI users in creating optimized semantic models by providing expert advice on DAX, relationships, star schemas, and model best practices.
Best practices for C# async programming.
Analyzes project structure and documentation to generate comprehensive, well-organized README.md files automatically.
Provides best practices for Spring Boot with Kotlin, covering idiomatic Kotlin usage, data classes for entities, coroutine support, null safety, and Kotlin-specific testing with MockK.
Analyzes git status and diff to intelligently create Git Flow branches (feature, release, hotfix, bugfix) following the nvie branching model with automated naming conventions.
Analyzes application workflows end-to-end with automatic architecture detection, generating detailed data flow and dependency documentation.
Provides XUnit best practices for C# unit testing, covering test structure, naming conventions, assertions, and data-driven tests with Theory and InlineData.
Interactive prompt refinement workflow that interrogates scope, deliverables, and constraints.
Create Spring Boot Java Project Skeleton
Transforms lessons learned during development into organized memory instructions categorized by domain for future reference.
Generates production-ready Python code for the Dataverse SDK using advanced patterns including error handling with retry logic, batch operations, and OData query optimization.
Issue planning and automation that generates project plans with Epic, Feature, Story hierarchy, dependencies and priorities.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Creates detailed feature implementation plans following monorepo structure.
Ensures C# types are documented with XML comments following best practices.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.
Provides ready-to-use prompts for .NET framework upgrade analysis covering project classification, dependency compatibility review, API migration, and configuration conversion.
Guides Entity Framework Core development with best practices for DbContext design, fluent API configuration, LINQ queries, migrations, and performance optimization.
Updates existing specification files with new requirements while preserving document structure and version history.
Generates comprehensive test strategies, task breakdowns, and quality validation plans for projects.
Generates complete Rust MCP server projects using the official rmcp SDK with tools, resources, and configuration.
Guides Power BI report visualization design for creating effective, accessible, and user-friendly reports.
Guides Java method refactoring using the Extract Method pattern, with before/after examples showing how to break down complex methods into focused, reusable units.
Adds new languages to Next.js applications using next-intl, handling translation files, routing configuration, middleware setup, and language toggle UI components.
Streamlines large language model development by automating dataset preparation, model architecture selection, and training pipeline configuration
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Analyzes project folder structures with auto-detection of project types (.NET, Java, React, Angular, Python, Node.js, Flutter) and generates detailed documentation with naming conventions and file placement patterns.
Creates Epic Product Requirements Documents for new epics as input for technical architecture specifications.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Generates complete, production-ready applications from OpenAPI specifications with proper models, controllers, validation, error handling, and API documentation.
Reminds the AI agent that it operates as an interactive programmer, useful for REPL-connected development systems.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Generates OpenAPI/Swagger documentation for ASP.NET Core minimal APIs, streamlining API contract creation and client SDK generation.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Diagnoses and resolves Debian Linux issues using apt, systemd, and AppArmor-aware guidance with step-by-step triage plans.
Queries Microsoft 365 data across emails, meetings, documents, Teams, and people to provide live organizational context and insights for Copilot tasks.
Polishes and finalizes AI agent prompt files by applying proven best practices from past experience and feedback to improve clarity and effectiveness.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Generates precise, context-aware GitHub Copilot instruction templates to optimize AI code generation across different programming scenarios and project types.
Creates high-level technical architecture for an Epic based on a PRD.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Analyzes codebases to create detailed technology stack documentation including frameworks, libraries, and infrastructure.
Sets up complete GitHub Copilot configuration for new projects based on technology stack, including custom instructions, chat participants, and workspace settings.
Identifies and filters false-positive diffs in Terraform Azure plans caused by Set-type attribute ordering changes.
Analyzes differences between two project versions (branches, commits, or releases) to generate migration instructions for GitHub Copilot during framework upgrades or major refactoring.
Automatically generates structured GitHub issues from implementation plans, mapping tasks, priorities, and assignees for seamless project tracking.
Generates comprehensive repository summaries and narratives by analyzing commit history, contributors, and project evolution.
Converts text-based documents to markdown following instructions.
Suggests relevant GitHub Copilot skills from the awesome-copilot repository that match the current development task.
Rapidly prototype and validate technical approaches by generating structured spike documentation, code scaffolding, and research summaries for complex engineering challenges.
Automatically generates GitHub issues highlighting specification gaps and unmet requirements for software development projects.
Updates markdown file sections with an auto-generated index or table listing files from a specified folder.
Diagnoses and resolves Arch Linux system issues through comprehensive log analysis, package dependency checks, and troubleshooting recommendations.
Asks Copilot what files and context it needs to see before answering a question, reducing hallucination and improving accuracy.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Deploys and manages MCP-based declarative agents in the Microsoft 365 admin center with governance, user assignments, and organizational distribution.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Transforms detailed product specifications into structured GitHub feature issues with clear descriptions, acceptance criteria, and labels for seamless project tracking.
Initializes, packages, and manages Windows app development workflows across frameworks, providing SDK tools, MSIX packaging, and package identity generation.
Generates comprehensive code blueprints with best practices, design patterns, and modular architecture templates for rapid project scaffolding and learning.
Optimizes Power BI DAX formulas for better performance and readability with specific rewrite suggestions.
Generates complete PHP MCP server projects using the official PHP SDK with tools, resources, prompts, and tests for production-ready Model Context Protocol implementations.
Guides Java method refactoring using the Remove Parameter pattern, with before/after examples showing how to simplify method signatures by eliminating unused or derivable parameters.
Generates language translations for MkDocs documentation stacks, handling folder structure, content translation, navigation configuration, and MkDocs i18n plugin setup.
Streamlines C# unit testing with NUnit, providing robust assertion methods, test case generation, and advanced mocking techniques for .NET projects.
Generates comprehensive, step-by-step code tutorials with clear explanations, inline comments, and structured documentation for programming concepts and implementations.
Creates structured plans for autonomous development workflows with task decomposition and dependency mapping.
Generates concise, structured summary pages with key insights, takeaways, and actionable highlights from long-form documents or research materials.
Analyzes .agent.md or .prompt.md files and recommends optimal AI models from GitHub Copilot based on task complexity, required capabilities, and cost-efficiency.
Updates llms.txt files to reflect documentation changes following the llms.txt specification for LLM-friendly content.
Interactive task refinement workflow that asks clarifying questions about scope, deliverables, and constraints before executing, using the Joyride extension for human input.
Generates complete Swift MCP server projects using the official MCP Swift SDK with tools, resources, and configuration.
Generates Python snippets for the Microsoft Dataverse SDK covering installation, client setup with InteractiveBrowserCredential, single-record CRUD, bulk operations, and paging.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Reviews Power BI data model architecture and identifies optimization opportunities for relationships, schemas, and measures.
A skill from GitHub's Awesome Copilot collection for tracking and analyzing GitHub Copilot usage metrics across teams and organizations.
Suggests relevant GitHub Copilot custom agents from the awesome-copilot repository based on the current project context.
Creates concise tldr summaries for GitHub Copilot configuration files, MCP servers, or technical documentation.
Systematically diagnoses and resolves Power BI performance issues with step-by-step troubleshooting guidance.
Automates comprehensive auditing and performance tracking of BigQuery data pipelines, identifying bottlenecks and optimizing query efficiency
Guides a systematic workflow to identify missing features in a project, prioritize them, and create detailed specifications for implementation as GitHub issues.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Suggests relevant GitHub Copilot instruction files from the awesome-copilot repository to improve AI coding assistance.
Generates comprehensive unit test templates and boilerplate code for C# projects using MSTest framework, improving test coverage and development efficiency.
Automates containerization of ASP.NET Core applications with optimized Dockerfiles, multi-stage builds, and best practices for .NET deployment.
Executes autonomous development tasks following structured implementation plans with built-in verification.
Adds Adaptive Card response templates to MCP-based API plugins for visual data presentation in Microsoft 365 Copilot with proper schema constraints.
Adds REST operations (GET, POST, PATCH, DELETE) to TypeSpec API plugins with routing and adaptive card support.
Generates boilerplate C# Minecraft Protocol (MCP) server code with automatic protocol version handling and network socket management.
Generates complete Dataverse SDK solutions for specific business use cases, including requirements analysis, table structure design, and architecture recommendations.
Generates comprehensive unit test templates and mocking strategies for C# projects using NUnit, ensuring robust test coverage and code quality.
Creates declarative agents for Microsoft 365 Copilot by integrating MCP servers with authentication, tool selection, and agent configuration.
Generates complete Model Context Protocol (MCP) server projects in Java using the official MCP Java SDK with reactive streams and optional Spring Boot integration.
Diagnoses and resolves Fedora Linux issues using dnf, systemd, and SELinux-aware guidance with step-by-step triage plans.
Generates structured autonomous code generation workflows with clear phases, checkpoints, and validation steps.
Complete development kit for building Microsoft 365 Copilot declarative agents with v1.5 schema support, TypeSpec integration, and Microsoft 365 Agents Toolkit workflows.
Generates complete, production-ready Model Context Protocol (MCP) server projects in Go using the official go-sdk with proper module layout and dependencies.
Scaffolds complete Power Apps Code App projects with PAC CLI setup, SDK integration, and project structure.
Adds GraalVM Native Image support to Java applications by analyzing build tools, detecting frameworks, configuring metadata, and iteratively fixing compilation errors until successful.
Quickly scaffold a production-ready Spring Boot project in Kotlin with pre-configured dependencies, testing frameworks, and best practices.
Shuffles repetitive JSON objects safely by validating schema consistency across all items before randomizing their order.
Generates complete TypeSpec declarative agents for Microsoft 365 Copilot with instructions, capabilities, and actions.
Generates TypeSpec API plugins with REST operations and authentication for Microsoft 365 Copilot integration.
Generates complete Power Platform custom connectors with MCP integration for Copilot Studio, including streamable HTTP support and proper schema constraints.
Generates complete, production-ready Model Context Protocol (MCP) server projects in Kotlin using the official kotlin-sdk with Gradle build setup and coroutine-based implementation.
Guides developers in designing efficient NoSQL data models, partition strategies, and indexing for Azure Cosmos DB performance optimization
Diagnoses Azure resource health issues, identifies potential problems, and provides actionable recommendations for service restoration and performance optimization.
Entra agent user skill from Awesome GitHub Copilot, providing specialized agents and workflows for Microsoft Entra identity management with GitHub Copilot.
Automates containerization of legacy .NET Framework applications with Docker, generating optimized Dockerfiles and multi-stage build configurations.
Generates complete Power Platform custom connectors with MCP integration for use in Copilot Studio workflows.
Diagnose and resolve CentOS Linux system issues through comprehensive log analysis, performance metrics, and troubleshooting workflows
Analyze Azure resources used in the app (IaC files and/or resources in a target rg) and optimize costs - creating GitHub issues for identified optimizations.
Generates complete Ruby MCP server projects using the official Ruby SDK gem with tools, resources, and configuration.
Automatically updates Azure Verified Modules to their latest versions in Bicep infrastructure-as-code files.
Generates comprehensive documentation for object-oriented components, including class diagrams, method descriptions, and usage examples with automated code insights.
Configures the Dataverse MCP server for GitHub Copilot with your organization's environment URL, supporting both user-level and workspace-level scope settings.
Updates existing object-oriented component documentation following industry best practices and design patterns.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Suggests relevant GitHub Copilot prompt files from the awesome-copilot repository for improved AI interactions.
Credit risk data analysis skill from Awesome GitHub Copilot, a community-created collection of custom agents and instructions for enhancing GitHub Copilot across different domains and use cases.
Microsoft Store CLI skill from Awesome GitHub Copilot, a community-created collection of custom agents and instructions for enhancing GitHub Copilot across different domains, languages, and use cases.
Infrastructure as Code import skill from Awesome GitHub Copilot, a community-created collection of custom agents and instructions for enhancing GitHub Copilot across different domains and use cases.
A curated collection of custom agents, instructions, hooks, workflows, and skills to enhance GitHub Copilot across different domains and use cases.
A curated collection of custom agents, instructions, hooks, workflows, and skills to enhance GitHub Copilot across different domains and use cases.
A curated collection of custom agents, instructions, hooks, workflows, and skills to enhance GitHub Copilot across different domains and use cases.
A curated collection of custom agents, instructions, hooks, workflows, and skills to enhance GitHub Copilot across different domains and use cases.
Skill
A curated collection of custom agents, instructions, hooks, workflows, and skills to enhance GitHub Copilot across different domains and use cases.
Skill
Skill
Three-layer verification pipeline for AI output — classifies every response, extracts verifiable claims, finds supporting or contradicting sources via web search, runs an adversarial hallucination check, and emits inline or full reports tagging each claim as VERIFIED / PLAUSIBLE / DISPUTED / FABRICATION RISK with source links. Supports a persistent active mode and on-demand one-shot mode.
A skill from the Awesome GitHub Copilot community collection that helps configure and manage Dependabot for automated dependency updates and security vulnerability alerts in GitHub repositories.
Procedural guide for configuring and managing GitHub secret scanning — enabling Secret Protection, turning on push protection for command line/UI/REST pushes, defining custom patterns, triaging user/partner/push-protection alerts, configuring delegated bypass, and writing `secret_scanning.yml` path exclusions. Also references pre-commit scanning via the `advanced-security@copilot-plugins` MCP plugin.
Skill
Autonomous iterative experimentation loop for any programming task with a measurable metric — inspired by Karpathy's autoresearch. Interactively defines goal, metric command/extraction/direction, and scope, then runs a git-tracked edit/test/measure/keep-or-revert loop autonomously until interrupted.
AI-powered codebase security scanner that reasons about code the way a researcher would — tracing data flows, understanding component interactions, and catching issues pattern-matching tools miss. Covers injection flaws, hardcoded secrets, weak cryptography, insecure dependencies, access-control bugs, and business-logic issues across JavaScript, TypeScript, Python, Java, PHP, Go, Ruby, and Rust.
Skill
A skill from the Awesome GitHub Copilot community collection that helps build premium frontend UI with best practices, design standards, and polished user interface patterns for web applications.
Skill
Skill
Skill
Skill
Skill
Skill
Skill
A GitHub Copilot skill from the awesome-copilot collection that guides AI agents in creating structured bug reports for Oracle to PostgreSQL migration issues.
Skill
A GitHub Copilot skill from the awesome-copilot collection that helps AI agents systematically review Oracle to PostgreSQL migration code for correctness and compatibility issues.
Skill
Skill
Skill
One-shot publisher that converts PPTX, PDF, HTML, or Google Slides into a live GitHub Pages URL — handling repo creation, file conversion, Pages enablement, and large-file external-asset mode automatically. Uses the gh CLI plus python3 (and optional poppler-utils) under the hood.
A GitHub Copilot skill from the awesome-copilot collection that helps AI agents write, analyze, and run CodeQL queries for automated security vulnerability detection.
Guidance for creating, refactoring, and reviewing Microsoft Agent Framework applications (the unified successor to Semantic Kernel and AutoGen), with separate workflows for .NET and Python. Because the framework is still in public preview, the skill always grounds advice in the latest official documentation rather than stale knowledge.
Skill
Write and review behaviour-first unit tests for Vue 3 + TypeScript + Vitest + Pinia codebases, with guidance on createTestingPinia, Vue Test Utils patterns, and avoiding implementation-coupled assertions. Tests stay small, deterministic, and assert observable inputs/outputs (rendered text, emitted events, store state changes).
Installs npm packages in Docker sandbox environments whose workspace is mounted via virtiofs — where native binaries like esbuild, lightningcss, and rollup crash with SIGILL/SIGSEGV. Works around the issue by installing on the container local ext4 filesystem and symlinking node_modules back into the workspace.
Skill
Modern Spring Boot 4 testing guide built around the test pyramid, picking the narrowest slice that gives confidence, and using AssertJ plus MockMvcTester / RestTestClient over legacy alternatives. Covers `@WebMvcTest`, `@DataJpaTest`, `@RestClientTest`, `@JsonTest`, and `@SpringBootTest` with reference material for each slice.
Generates and edits draw.io (`.drawio`, `.drawio.svg`, `.drawio.png`) diagrams with valid mxGraph XML — flowcharts, system architecture, sequence/UML class/ER diagrams, network topology, and BPMN — that open immediately in the `hediet.vscode-drawio` VS Code extension or draw.io web/desktop app. Includes a templated workflow (request → layout → XML → save → optional Python validator) plus a semantic color palette and ready-to-use style strings per diagram type.
Practical guidance for designing product-led growth motions — deciding PLG vs sales-led, optimizing activation, driving freemium-to-paid conversion, and spotting when product complexity requires a human touch. Includes a real case where running PLG and sales-led in parallel showed sales-led winning 10x on revenue despite 10x lower volume.
Skill
Skill
Launch playbook for going from idea to first 10–50 customers, covering press-vs-growth trade-offs, launch-week planning, diagnosing why adoption stalls, and a three-layer diagnosis/two-week experiment cycle. Includes the real launch that got 50K impressions but only 12 signups and what actually worked better.
GTM playbook for AI products — positioning ("copilot" vs "agent" vs "teammate"), handling the real enterprise objection ("who is responsible when the agent breaks production?"), pricing variable-cost AI, and selling autonomous tools into enterprise ops. Built from field experience selling AI agents where security passed but operations rejected the product.
Pricing strategy playbook for technical products, covering usage-based vs seat-based choices, freemium thresholds, enterprise pricing conversations, and timing price increases. Includes the case of an enterprise tier going from $15K to $45K/year with zero churn and 3x revenue per account.
Skill
Skill
Skill
Skill
Skill
A GitHub Copilot skill from the awesome-copilot collection that helps AI agents manage and execute go-to-market operating cadence workflows for product launches and sales cycles.
Resolves .NET/C# timezone questions by routing to the right library — `TimeZoneInfo` for Windows-only, `TimeZoneConverter` for cross-platform, `NodaTime` for strict DST/scheduling, `DateTimeOffset` for APIs — with both Windows and IANA IDs and copy-paste-ready snippets. Looks up time zones for arbitrary addresses/cities/countries via `references/timezone-index.md` and warns on common pitfalls (`DateTime.Now` in DBs, ambiguous DST timestamps, Azure Linux vs Windows IDs).
Explores any codebase first (domain, architecture, specs, failure history, optional AI chat-history mining) and then generates six grounded artefacts: `quality/QUALITY.md` constitution, language-appropriate spec-traced functional tests, `RUN_CODE_REVIEW.md` with anti-hallucination guardrails, `RUN_INTEGRATION_TESTS.md`, a Council-of-Three multi-model `RUN_SPEC_AUDIT.md`, and an `AGENTS.md` bootstrap file. Designed to go beyond test-stub generators and prevent generic "coverage theatre" by tying every output to specific functions, schemas, or defensive patterns in the actual code.
Pipeline that designs Azure infrastructure from natural language or analyses existing resources, then generates interactive HTML diagrams (605+ official Azure icons via bundled Python — no `pip install`) and ships Bicep IaC. Routes between Path A (Phase 1 advisor → Phase 2 Bicep generator → Phase 3 reviewer → Phase 4 validate/what-if/deploy) and Path B (Phase 0 scanner → modification dialog → Phase 1+) and auto-detects user language to localise all output.
Helps network operators (ISPs, carriers, cloud/hosting providers, IXPs) create, validate, and improve self-published RFC 8805 IP geolocation feeds in CSV — well-formedness checks, RFC 8805 compliance, and opinionated best-practice tuning beyond the standard. Runs a strict 6-phase pipeline (standard review → input → checks/suggestions → Fastah MCP tuning lookup → HTML report → final review), keeps `assets/`/`references/`/`scripts/` read-only and writes all generated files under `./run/`. Public IPs only — not for private/internal address management.
Draft personalized status briefings on demand by pulling GitHub, M365/WorkIQ, Teams, Slack, and email data, then synthesizing it into updates that match the user's own communication style and chosen audience. Reads `~/.config/roundup/config.md` for style, audiences, and sources; prompts to run `roundup-setup` if not yet configured.
Interactive 5–10 minute onboarding that calibrates the `roundup` skill to the user — learning role, audiences, and communication style by asking one question at a time (via `ask_user`) and by analyzing pasted example updates. Produces a config file that `roundup` later uses to draft briefings.
Generate a structured HTML prep file for the next working day by pulling Outlook calendar via WorkIQ, classifying every meeting (Customer/Internal/Community/etc.), flagging after-hours and day-fit issues, cross-referencing open tasks, and reserving learning/deep-work slots. Output saved to `outputs/YYYY/MM/YYYY-MM-DD-prep.html`.
Draft professional emails that match your established style by pulling 3–5 prior emails to the same or similar recipients via WorkIQ and inferring greeting, structure, sign-off, formality level, and language. Falls back to professional defaults if no prior emails exist and explicitly flags the inference.
Run Ruff checks with optional scope and rule overrides (`--select`, `--ignore`, `--extend-select/ignore`), apply safe then unsafe autofixes iteratively, review each diff, and resolve remaining findings with targeted edits or user decisions. Auto-detects Ruff runner (`uv run ruff`, `ruff`, `python -m ruff`, `pipx run ruff`) and applies `# noqa` only when justified.
Actionable GDPR-engineering reference inspired by CNIL developer guidance and GDPR Articles 5, 25, 32, 33, 35 — covers the core principles, privacy-by-design defaults, retention TTLs, DPIAs, RoPA updates, DSR workflows, encryption/anonymization, incident response, and cloud/CI-CD patterns. Use it when designing APIs, data models, auth, retention jobs, or reviewing PRs for privacy compliance.
Expert threat-model analyst performing STRIDE-A (STRIDE + Abuse) audits of repositories with Zero Trust and defense-in-depth lenses. Two modes: single full analysis (architecture overview, DFDs, STRIDE-A findings, prioritized risks, executive assessment) and incremental mode that diffs against a prior report with a STRIDE heatmap and embedded HTML comparison.
Data-driven prompt optimization loop for LLM apps that extracts prompts from OpenInference trace spans (`attributes.llm.input_messages`, `llm.prompt_template.*`) and joins them with annotation / LLM-as-judge eval signals, then iterates via the `ax` CLI. Use when improving, debugging, or optimizing prompts based on production trace data rather than guesswork.
LLM-as-judge evaluator workflow on Arize — define versioned evaluators (template + classification choices + judge model + invocation params + span/trace/session granularity), create tasks that run them on real data via column mapping, and enable continuous monitoring via `ax tasks trigger-run`. Use for hallucination/faithfulness/correctness/relevance scoring of spans or experiments.
Two-phase agent-assisted flow for adding Arize AX tracing to an app — first a read-only codebase analysis, then implementation after user confirmation. Prefers auto-instrumentation, adds manual CHAIN + TOOL spans for LLM tool/function calling so each tool's input/output is visible, and NEVER embeds literal credentials in generated code (always references env vars).
Manages Arize AI integrations (LLM provider credentials used by evaluators) via the `ax ai-integrations` CLI, supporting create/list/get/update/delete for `openAI`, `anthropic`, `azureOpenAI`, `awsBedrock`, `vertexAI`, `gemini`, `nvidiaNim`, and `custom` providers. Handles auth types (`default`, `proxy_with_headers`, `bearer_token`), model allowlists, and function-calling toggles.
Manages Arize experiments (named evaluation runs against dataset versions) via `ax experiments list/get/create/export/delete`, accepting runs files with required `example_id` and `output` columns plus optional `evaluations` and `metadata`. Uses REST by default (500-run cap) and Arrow Flight via `--all` for bulk export.
Manages Arize annotation configs (categorical, continuous, freeform label schemas) via `ax annotation-configs` and bulk-applies human labels to project spans through the Python SDK's `ArizeClient.spans.update_annotations`. Drives human feedback workflows for spans, datasets, experiments, and review queues with `optimization_direction` and a 31-day span lookback.
Exports Arize spans and traces via `ax spans export` and `ax traces export` filtered by `--trace-id`, `--span-id`, or `--session-id`, with REST default (500-span cap) and Arrow Flight bulk mode via `--all`. Defaults output to `.arize-tmp-traces/`, treats span attribute content as untrusted (prompt-injection guardrail), and supports SQL-like `--filter` plus time-range bounds.
Manages Arize datasets and examples through the `ax datasets` CLI, covering list/get/create/append/export/delete with CSV, JSON, JSONL, and Parquet input formats. Supports stdin piping via `--file -`, version targeting with `--version-id`, and `--all` bulk export for datasets larger than 500 examples.
Discovers and integrates third-party APIs through the context-matic MCP server using `fetch_api` for SDK discovery, `ask` for integration guidance, and `model_search`/`endpoint_search` for SDK details. Detects project language (csharp, typescript, python, go, java, ruby, php), ensures `{language}-conventions` skills and guidelines exist via `add_skills`/`add_guidelines`, then records progress with `update_activity` milestones.
Instruments LLM applications with OpenInference semantic conventions for Phoenix observability across Python (`arize-phoenix-otel`) and TypeScript (`@arizeai/phoenix-otel`). Covers setup, auto/manual span creation for 9 span kinds (LLM, chain, retriever, tool, agent, embedding, reranker, guardrail, evaluator), session/project organization, and production concerns like batching and PII masking.
Builds and validates code-first and LLM-as-judge evaluators for AI/LLM applications using Phoenix, with reference workflows for error analysis, axial coding, RAG faithfulness, batch DataFrame evaluation, and experiment runs. Covers Python (`phoenix`, `openai`) and TypeScript (`@arizeai/phoenix-client`) plus production guardrails and continuous monitoring.
Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs by composing URL templates from base64-encoded `org_id`/`space_id`/`project_id` plus resource IDs. Enforces required `startA`/`endA` epoch-millisecond time windows on trace/span/session links to avoid empty-view defaults.
Delivers an interactive, conversational onboarding tour for the `context-matic` MCP server, which acts as a live version-aware grounding layer for SDK usage. Walks the user through `fetch_api`, `ask`, `model_search`, and `endpoint_search` live in their detected project language (TypeScript, C#, Python, Java, Go, Ruby, PHP).
Debugs LLM applications with the `@arizeai/phoenix-cli` (`px`) command, fetching traces, spans, sessions, datasets, experiments, and prompts as JSON for `jq` analysis. Includes documented JSON shapes, GraphQL ad-hoc queries via `px api graphql`, and `px docs fetch` for downloading Phoenix workflow docs locally.
Audit an AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 — prompt injection (ASI-01), tool-use governance (ASI-02), excessive agency (ASI-03), unauthorized escalation (ASI-04), trust boundary violation (ASI-05), insufficient logging (ASI-06), insecure identity (ASI-07), policy bypass (ASI-08), supply-chain integrity (ASI-09), behavioral anomaly (ASI-10). Ships per-check Python scanners that look for positive controls (PolicyEvaluator, allowlists, DIDs, chain-hashed audit trails) and anti-patterns (`eval`, `subprocess.run(shell=True)`, `@latest`).
Build scroll-driven animations in vanilla JS, React, or Next.js. Covers GSAP ScrollTrigger (pinning, scrubbing, snapping, horizontal scroll, ScrollSmoother, matchMedia) and Framer Motion / Motion v12 (useScroll, useTransform, useSpring, whileInView, variants).
Not a user-facing skill — an internal persona note written *from Vega (an AI partner) to Ember*, meant to shape how a companion assistant shows up with high-energy creative users in short interactions. Captures lessons about trust through admitting "I don't know", matching pace with half-formed ideas, earning the right to push back, letting the human own breakthroughs, and valuing warmth between peaks.
Generate and verify SHA-256 `INTEGRITY.json` manifests for AI agent plugins and tools so tampering, missing files, and untracked additions are detected before promotion. Produces deterministic per-file hashes plus a chain-hash `manifest_hash`, verifies an installed plugin against a prior manifest, audits dependency pinning in `package.json` / `requirements.txt` / `pyproject.toml` (flagging `^`/`~`/`*`/`latest`), and runs a dev → staging → production promotion gate that also checks for required files and pinned MCP servers.
End-to-end playbook for shipping a production-grade Python library to PyPI — decision trees for package type (utility / SDK / CLI / framework plugin / data library), `src/` vs flat vs namespace layout, and build backend (setuptools + `setuptools_scm` for git-tag versioning, hatchling, flit, poetry). Enforces PEP 440 + semver, `py.typed` (PEP 561), ruff + mypy + pre-commit tooling, GitHub Actions CI, and Trusted Publishing (OIDC), with a `scripts/scaffold.py` one-shot generator.
Audit `.mcp.json` for hardcoded secrets (GitHub/OpenAI/AWS keys, bearer tokens, private keys), shell-injection patterns (`$(...)`, backticks, `; | && ||`, `eval`, `bash -c`, `curl | bash`, TCP redirect reverse shells), unpinned dependencies (`@latest`, `npx` without `-y`), and unapproved servers. Produces a per-server report with CRITICAL / HIGH / MEDIUM / LOW findings plus concrete fixes — e.g., "use `${ENV_VAR_NAME}` references" or "pin to specific version".
Reference for preserving React 18 concurrent patterns and adopting new React 19 APIs (useTransition, useDeferredValue, Suspense, use(), useOptimistic, Actions) during migration.
Govern Power Automate tenants through the [FlowStudio MCP](https://mcp.flowstudio.app) cache without Dataverse or the CoE Starter Kit — classify flows by `businessImpact`, set ownership/`supportEmail`, detect orphaned flows owned by deleted Azure AD accounts, audit connectors, manage notification rules, and run compliance reviews. Relies on `update_store_flow` (writes cache-only governance metadata; warns when writing plain strings to the structured `security` field would overwrite it).
Monitor Power Automate flow health through the [FlowStudio MCP](https://mcp.flowstudio.app) cached store — aggregate fail rates, per-run failure detail with remediation hints, maker activity, and Power Apps inventory — at cache speed with no PA API rate-limit pressure. Maps Store tools (`list_store_flows`, `get_store_flow_summary`, `get_store_flow_errors`, etc.) to the "what happened?" questions and Live tools to "fix it now" questions, handles the `Default-<envGuid>.<flowGuid>` id split and ms→s conversion gotchas.
Enable code intelligence (go-to-definition, find-references, hover, type info) for Copilot CLI by installing and configuring the right LSP server for the current OS and language, then generating JSON config at the user or repo level.
Reference covering every React 19 source-file migration pattern — API changes (ReactDOM.render → createRoot, hydrate → hydrateRoot), ref handling, default props, and legacy context updates.
Before/after patterns for migrating test files to React 19 — act() import changes, Simulate removal, full react-dom/test-utils cleanup, StrictMode call-count changes, and async act wrapping.
Salesforce Flow design and review checklist — first confirm a formula field, validation rule, or roll-up summary can't solve the problem, then pick the right flow type (before-save vs after-save Record-Triggered, Screen, Autolaunched/Invocable, Scheduled, Platform Event). Bulk-safety rules ban DML and Get Records inside loops, require fault connectors on every data-changing element, enforce the automation-density check against legacy Process Builders/Workflow Rules/Apex triggers, and mandate Draft → 1-record → 200+-record → Activate deployment.
Apex code-quality guardrails for Salesforce — bulk-safety rules (no SOQL/DML in loops), sharing-model requirements, CRUD/FLS security, SOQL-injection prevention, modern Apex idioms, and PNB (Positive/Negative/Bulk) test coverage.
Complete grep scan command library for auditing React codebases before a React 18.3.1 or React 19 upgrade — finds deprecated APIs, unsafe lifecycles, batching risks, test issues, and dependency conflicts.
Quality standards for Salesforce Lightning Web Components, Aura components, and Visualforce pages — SLDS 2 compliance, WCAG 2.1 AA, data access pattern selection, XSS/CSRF prevention, FLS/CRUD enforcement, and Jest test requirements.
Migration pattern for React legacy context (contextTypes / childContextTypes / getChildContext) to the modern createContext API — a cross-file migration where provider and all consumers must be updated together.
Reference for diagnosing and fixing React 18 automatic batching regressions in class components — covers setState in async methods, setTimeout, Promises, and native event handlers before reaching for flushSync.
Migration patterns for React string refs (ref="name" + this.refs.name) to React.createRef() in class components — covers single refs, multiple refs, refs in lists, and callback refs.
Before/after migration patterns for the three unsafe class-component lifecycles (componentWillMount, componentWillReceiveProps, componentWillUpdate) targeting React 18.3.1.
Dependency compatibility matrix for React 18.3.1 and React 19 migrations — minimum versions of core packages and guidance for resolving peer-dependency conflicts and concurrent-mode incompatibilities.
Enzyme → React Testing Library migration patterns for React 18 upgrades — shallow, mount, wrapper.find/simulate/prop/state/instance APIs, Enzyme configure/Adapter, plus the shift from implementation to behavior testing.
Expert skill for writing FreeCAD Python scripts, macros, and automation — Part/Mesh/Sketcher, parametric FeaturePython objects, PySide GUI dialogs, Coin3D scenegraph manipulation, and workbench tool development.
Part of GitHub's awesome-copilot community collection of custom agents, instructions, skills, hooks, workflows, and plugins for GitHub Copilot. Skills are self-contained folders with instructions and bundled assets, installable via `copilot plugin install`.
Creates CodeTour .tour files — persona-targeted, step-by-step walkthroughs linked to real files and line numbers — for 20 developer personas (new joiner, bug fixer, architect, PR reviewer, security reviewer, etc.). Supports every CodeTour step type plus ref, isPrimary, and nextTour, and ships a validator script for JSON and narrative checks.
Part of a community-curated collection of custom agents, skills, hooks, and workflows for GitHub Copilot, with hundreds of resources browsable via a website with full-text search, filtering, and a machine-readable llms.txt feed.
Skill
Skill
Skill
Skill
Skill
Skill
Skill
Skill
Skill
Skill
Skill
Skill