Tyler-R-Kendrick

Use when making backend architecture decisions — choosing API styles, database types, caching strategies, authentication mechanisms, and server-side design patterns for scalable, maintainable systems. USE FOR: backend architecture decisions, choosing API styles, choosing database types, server-side design patterns, backend system design DO NOT USE FOR: specific pattern details (use sub-skills: data-modeling, api-design, caching, authentication), frontend architecture (use dev/frontend), infrastructure (use iac)

Use when writing or debugging regular expressions for pattern matching, validation, search, and text transformation. Covers regex syntax, common patterns, lookahead/lookbehind, character classes, quantifiers, and differences between regex flavors (PCRE, JavaScript, Python, .NET, POSIX). USE FOR: regular expressions, regex, pattern matching, text validation, search and replace, PCRE, regex lookahead, regex lookbehind, character classes, quantifiers, capturing groups, non-capturing groups, regex anchors DO NOT USE FOR: HTML/XML parsing (use a proper parser), complex data extraction (use jq or a programming language), natural language processing

Use when configuring dev containers or GitHub Codespaces. Covers devcontainer.json schema, features, lifecycle hooks, port forwarding, and customizations. USE FOR: devcontainer.json configuration, GitHub Codespaces setup, lifecycle hooks, port forwarding, VS Code customizations, dev container features DO NOT USE FOR: specific language setup (use the sub-skills: dotnet, python, typescript), Docker-in-Docker configuration (use docker-in-docker), sidecar services (use multi-container-workspaces)

Use when building or maintaining a design system — the coordinated set of design tokens, component libraries, documentation, and tooling that ensures visual and behavioral consistency across products. USE FOR: design system architecture, choosing token formats vs component frameworks, connecting Figma to code, design-to-development workflows, multi-platform consistency DO NOT USE FOR: specific token authoring (use design-tokens), Figma workflows (use figma), component cataloging (use storybook), token transformation (use style-dictionary), cross-framework components (use mitosis)

Use when selecting algorithms, analyzing complexity, or reasoning about data structure choices. Covers Big-O notation, space vs time tradeoffs, amortized analysis, and algorithmic problem-solving strategy based on Knuth's "The Art of Computer Programming." USE FOR: algorithm selection, Big-O analysis, complexity comparison, choosing data structures, algorithmic problem-solving strategy DO NOT USE FOR: specific algorithm implementations (use sub-skills), system architecture (use dev/architecture), design patterns (use dev/design-patterns)

Guidance for Behavior-Driven Development (BDD) patterns and Gherkin syntax in .NET. USE FOR: writing Gherkin feature files, structuring Given-When-Then scenarios, creating scenario outlines with data tables, organizing BDD step definitions, mapping business requirements to executable specifications with Reqnroll or SpecFlow. DO NOT USE FOR: unit test design (use xUnit/NUnit directly), performance testing, API contract testing (use Pact), or end-to-end browser automation (use Playwright).

Guidance for Testcontainers integration testing library for .NET. USE FOR: spinning up real databases in Docker for integration tests, testing against PostgreSQL/SQL Server/Redis/RabbitMQ containers, verifying EF Core migrations against a real database, testing message broker consumers, replacing in-memory test doubles with real infrastructure in CI/CD pipelines. DO NOT USE FOR: unit testing (use Moq/AutoFixture), production container orchestration (use Kubernetes), load testing, or scenarios where Docker is unavailable.

Use when modeling software architecture using the C4 model (Context, Container, Component, Code) by Simon Brown. Covers hierarchical system decomposition, Structurizr DSL, and C4 diagramming best practices. USE FOR: C4 model diagrams, system context diagrams, container diagrams, component diagrams, code-level diagrams, Structurizr DSL authoring, architecture decomposition, workspace definitions, C4 views and styles DO NOT USE FOR: general flowcharts (use mermaidjs), enterprise architecture frameworks (use togaf or archimate), data models (use erd)

Use for WCAG compliance testing and assistive technology validation. Covers axe-core (programmatic API, Playwright/React integrations), Pa11y (CLI and CI runner), Lighthouse accessibility audits, Storybook addon-a11y, and WAVE. Includes WCAG 2.1/2.2 levels, common violations, automated vs manual testing guidance. USE FOR: axe-core, Pa11y, Lighthouse accessibility, WCAG compliance, Storybook addon-a11y, screen reader testing, accessibility audits, ARIA validation, Section 508 compliance, keyboard navigation testing DO NOT USE FOR: visual appearance testing (use visual-testing), functional E2E tests (use e2e-testing), performance audits (use performance-testing)

Identify and quantify cost savings across Azure subscriptions by analyzing actual costs, utilization metrics, and generating actionable optimization recommendations. USE FOR: optimize Azure costs, reduce Azure spending, reduce Azure expenses, analyze Azure costs, find cost savings, generate cost optimization report, find orphaned resources, rightsize VMs, cost analysis, reduce waste, Azure spending analysis, find unused resources, optimize Redis costs. DO NOT USE FOR: deploying resources (use azure-deploy), general Azure diagnostics (use azure-diagnostics), security issues (use azure-security)

Use when transforming design tokens into platform-specific outputs using Style Dictionary. Covers configuration, transforms, formats, DTCG support, and multi-platform builds. USE FOR: Style Dictionary configuration, token transforms, platform-specific token output (CSS, SCSS, iOS, Android, Compose), custom formats, DTCG-to-platform pipelines DO NOT USE FOR: authoring token files (use design-tokens), Figma variable management (use figma), component documentation (use storybook)

Use when selecting, implementing, or reasoning about data structures. Covers arrays, linked lists, stacks, queues, hash tables, trees (BST, AVL, Red-Black, B-Tree, Trie), heaps, and graphs (adjacency list, adjacency matrix). Based on Knuth's TAOCP Vol. 1. USE FOR: choosing data structures by access pattern, understanding operation complexities, implementing fundamental data structures, comparing data structure tradeoffs DO NOT USE FOR: graph algorithms on data structures (use graph-algorithms), sorting data (use sorting-searching)

Creational design patterns from the Gang of Four — Factory Method, Abstract Factory, Builder, Prototype, and Singleton. Patterns that abstract the instantiation process to make systems independent of how objects are created, composed, and represented. USE FOR: object creation, factory patterns, builder pattern, prototype cloning, singleton instances, decoupling instantiation from usage DO NOT USE FOR: composing/adapting objects (use structural), inter-object communication (use behavioral)

Use when running pre-trained ONNX models for inference in .NET with ONNX Runtime. Covers session management, tensor inputs/outputs, execution providers (CPU/GPU/DirectML), model optimization, and integration with ASP.NET Core. USE FOR: running pre-trained ONNX models in .NET, image classification inference, NLP model inference, cross-framework model deployment (PyTorch/TensorFlow to .NET), GPU-accelerated inference with CUDA or DirectML DO NOT USE FOR: training ML models from scratch (use mlnet or Python), calling cloud-hosted LLMs (use microsoft-extensions-ai or azure-ai-inference), building agent workflows (use agent-framework), custom ML pipelines with feature engineering (use mlnet)

USE FOR: Building cross-platform native mobile and desktop applications with .NET MAUI targeting iOS, Android, Windows, and macOS from a single C# and XAML codebase. Use when you need native platform APIs, device hardware access, and native UI controls. DO NOT USE FOR: Web applications (use Blazor or ASP.NET Core), Linux desktop targets (use Avalonia), or game development (use Unity or MonoGame).

Use when managing cloud infrastructure through Kubernetes with Crossplane. Covers providers, managed resources, compositions, XRDs, claims, and the control plane pattern. USE FOR: Kubernetes-native cloud provisioning, Crossplane compositions, XRDs and claims, control plane pattern DO NOT USE FOR: standalone CLI-driven IaC (use terraform or pulumi), Kubernetes application deployment (use kubernetes or helm)

Use when writing Kubernetes manifests for deploying and managing containerized applications. Covers Deployments, Services, ConfigMaps, Secrets, Ingress, and resource management. USE FOR: Kubernetes manifests, Deployments, Services, Ingress, ConfigMaps, resource management, kubectl DO NOT USE FOR: Helm chart templating (use helm), cloud resource provisioning (use terraform or crossplane), container image builds (use docker)

Use when applying OWASP standards to identify and mitigate common security vulnerabilities. Covers OWASP Top 10 (2021), OWASP API Security Top 10 (2023), and CWE/SANS Top 25 with mitigation strategies for each category. USE FOR: OWASP Top 10, API Security Top 10, CWE Top 25, web application vulnerabilities, vulnerability classification, security baseline, broken access control, injection, XSS, SSRF DO NOT USE FOR: AI/LLM-specific vulnerabilities (use ai-security), security tool configuration (use security-testing), cryptographic implementation (use cryptography)

Use when creating, packaging, or distributing Agent Skills. Covers the SKILL.md specification, frontmatter schema, naming conventions, marketplace publishing, and the skills-ref validator. USE FOR: creating SKILL.md files, packaging reusable agent capabilities, marketplace publishing, frontmatter schema validation DO NOT USE FOR: project-level agent guidance (use agents-md), agent runtime configuration (use adl or cagent)

Use when building custom machine learning models in .NET with ML.NET. Covers data loading, training pipelines, prediction engines, AutoML, model evaluation, and deployment for classification, regression, clustering, and anomaly detection. USE FOR: training custom ML models in .NET, binary and multi-class classification, regression and forecasting, clustering and anomaly detection, AutoML experimentation, model serialization and deployment DO NOT USE FOR: running pre-trained ONNX models (use onnx), calling cloud-hosted LLMs (use microsoft-extensions-ai or azure-ai-inference), building AI agent workflows (use agent-framework), deep learning with GPU training (use TorchSharp or Python)

USE FOR: Building high-performance reverse proxies, API gateways, and load balancers using YARP (Yet Another Reverse Proxy) from Microsoft. Use when you need customizable request routing, load balancing, header transforms, session affinity, health checks, and dynamic configuration for proxying traffic to backend services. DO NOT USE FOR: Simple API gateway features like request aggregation and built-in rate limiting (use Ocelot), service mesh capabilities like mTLS and circuit breaking (use Istio or Linkerd), or CDN-style edge caching (use a CDN like Cloudflare or Azure Front Door).

Use when documenting .NET APIs with OpenAPI (Swagger) specifications, generating client SDKs, and configuring Swashbuckle or NSwag. USE FOR: API documentation with OpenAPI/Swagger, Swashbuckle configuration, NSwag client generation, XML comment documentation, API versioning with OpenAPI, minimal API documentation DO NOT USE FOR: general REST API design patterns (use aspnet-core), API gateway configuration, GraphQL schema documentation

Use when implementing the mediator pattern with Mediator.NET (source-generated) for high-performance in-process command/query dispatch in .NET. USE FOR: source-generated mediator pattern, in-process command dispatch, query handling, notification pub/sub, high-performance zero-reflection dispatch DO NOT USE FOR: distributed messaging (use masstransit or nservicebus), reflection-based mediator with large ecosystem (use mediatr), actor concurrency (use akka-net)

USE FOR: Reactive collection management using observable caches and lists with LINQ-style operators for filtering, sorting, grouping, transforming, and binding to UI collections. DO NOT USE FOR: Simple ObservableCollection scenarios, non-reactive LINQ queries, or server-side data access (use Entity Framework or Dapper).

Guidance for Migrant fast binary serialization library for .NET. USE FOR: fast binary serialization of complex object graphs, version-tolerant deserialization, simulation state snapshots, game save/load systems, deep object cloning via serialization, internal data persistence with circular reference support. DO NOT USE FOR: cross-language interop (use protobuf-net), REST API responses (use System.Text.Json), human-readable data formats, or long-term archival storage with strict schema guarantees.

Use when planning or conducting authorized penetration tests against web applications, APIs, networks, and mobile apps. Covers pen testing methodologies (OWASP, PTES, OSSTMM), scoping and rules of engagement, tool selection, reporting, and remediation verification. USE FOR: penetration testing, pen test methodology, PTES, OSSTMM, OWASP Testing Guide, web app pen testing, API pen testing, network pen testing, mobile pen testing, vulnerability assessment, bug bounty, responsible disclosure, rules of engagement DO NOT USE FOR: automated security scanning in CI/CD (use security-testing), threat modeling before implementation (use threat-modeling), AI/LLM-specific adversarial testing (use ai-security or red-teaming)

Event-Driven Architecture (EDA), Event Sourcing, and CQRS -- complementary but independent patterns for building reactive, scalable systems with rich audit trails and temporal queries. USE FOR: event-driven architecture, event sourcing, CQRS, event stores, projections, eventual consistency, compensating transactions, temporal queries DO NOT USE FOR: messaging channel patterns (use dev/integration-patterns), message routing (use dev/integration-patterns/message-routing), domain modeling (use domain-driven-design)

Use when identifying code smells and applying systematic refactoring techniques — based on Martin Fowler's "Refactoring." USE FOR: code smell identification, refactoring technique selection, safe code transformation, incremental improvement workflows, legacy code improvement DO NOT USE FOR: clean code principles (use clean-code), design pattern application (use dev/design-patterns), architecture restructuring (use dev/architecture)

Use when a user corrects, rejects, edits, or redirects an LLM/agent response and the correction should become a reusable reasoning strategy. Converts feedback into generalized learnings for ~/.agents/STEERING.md with linked RDF/Turtle evidence. USE FOR: user corrections, preference feedback, rejected agent behavior, reasoning strategy updates, steering file maintenance DO NOT USE FOR: storing task facts (use memory), ordinary skill authoring (use agent-skills), project instruction files unrelated to feedback (use agents-md)

Use when addressing cross-cutting security concerns that apply to all languages, frameworks, and platforms. Covers OWASP standards, threat modeling, authentication, cryptography, supply chain security, and AI security. USE FOR: application security strategy, security architecture, choosing security controls, OWASP compliance, security tool selection, secure development lifecycle DO NOT USE FOR: specific language security implementations (use language-specific skills), infrastructure hardening (use iac skills), network security appliance configuration

Use when building or running multi-agent systems with Docker cagent. Covers YAML agent configuration, MCP tool integration, sub-agents, Docker MCP Gateway, and the cagent CLI. USE FOR: multi-agent orchestration, YAML agent configuration, Docker MCP Gateway, running agent teams locally DO NOT USE FOR: declarative agent definitions without runtime (use adl), agent-to-agent protocol (use a2a), tool server development (use mcp)

Use when configuring or using SSH for remote access, secure file transfer, tunneling, and key management. Covers ssh, scp, sftp, ssh-keygen, SSH config, agent forwarding, port forwarding, and ProxyJump for jump hosts. USE FOR: SSH, scp, sftp, ssh-keygen, SSH config, SSH keys, agent forwarding, port forwarding, SSH tunneling, ProxyJump, jump hosts, authorized_keys, known_hosts, SSH hardening DO NOT USE FOR: general network security (use security skills), VPN configuration, remote desktop protocols

Use when producing agent/LLM evals, synthetic simulation data, or self-improvement pipelines for prompts, code, skills, agents, harnesses, and workflows. Covers AgentEvals/AgentV, Agent Skills evals, ASSERT, GEPA, Trace, VISTA, Agent Lightning, SkillOpt, Simula-style data design, progressive disclosure, deterministic workspaces, and release evidence. USE FOR: eval creation, EVAL.yaml, AgentEvals, AgentV, evals.json, ASSERT, judge-traces, behavior taxonomy, judges, graders, rubrics, synthetic data, simulation data, Simula, QDC, source-grounded generation, prompt optimization, agent improvement, skill improvement, harness hardening, progressive disclosure, deterministic workflows, GEPA, Trace, VISTA, Agent Lightning, SkillOpt DO NOT USE FOR: ordinary unit/integration tests without AI quality criteria (use testing), refactoring without eval or trace feedback (use refactor), generic Agent Skills packaging without eval or improvement work (use agent-skills)

Use when building CI/CD pipelines as code with Dagger. Covers Dagger Functions, modules, container-based execution, caching, and SDK usage in TypeScript, Python, and Go. USE FOR: CI/CD pipelines as code, Dagger Functions and modules, container-based build steps, reproducible pipelines DO NOT USE FOR: cloud infrastructure provisioning (use terraform or pulumi), container image authoring (use docker), Kubernetes deployment (use kubernetes)

Use when writing Dockerfiles, Docker Compose files, or managing container images. Covers multi-stage builds, layer caching, Compose services, and image best practices. USE FOR: Dockerfiles, Docker Compose, multi-stage builds, container image optimization, local service orchestration DO NOT USE FOR: Kubernetes deployment (use kubernetes or helm), cloud provisioning (use terraform or pulumi), CI/CD pipelines (use dagger)

Use when writing Pulumi programs for cloud infrastructure using TypeScript, Python, Go, or C#. Covers resource declarations, stacks, Outputs, component resources, and preview/up workflow. USE FOR: infrastructure in TypeScript/Python/Go/C#, imperative IaC, Pulumi stacks, component resources DO NOT USE FOR: declarative HCL-based IaC (use terraform), Azure-only Bicep DSL (use bicep), Kubernetes manifests (use kubernetes)

Guidance for building command-line interfaces and terminal applications in Python. USE FOR: building CLI tools with argparse/click/typer, rich terminal output, TUI applications with textual, CLI testing strategies, output formatting, exit codes DO NOT USE FOR: Python project setup or packaging (use project-system), installing CLI tools (use package-management)

Use when writing shell scripts or working with Bash, Zsh, or POSIX-compatible shells on macOS and Linux. Covers scripting fundamentals, variables, control flow, functions, pipes, process management, and common patterns for automation and developer tooling. USE FOR: Bash, Zsh, shell scripting, POSIX shell, pipes, redirection, process substitution, shell functions, shell variables, .bashrc, .zshrc, shebang, here documents, command substitution, shell arithmetic DO NOT USE FOR: PowerShell scripting (use powershell-core), Windows batch files, complex data processing beyond text (consider Python or jq)

Use when making HTTP requests from the command line for API testing, debugging, and automation. Covers curl, wget, and HTTPie with common patterns for REST APIs, authentication, file uploads, and response inspection. USE FOR: curl, wget, HTTPie, HTTP from CLI, API testing from terminal, REST API debugging, request headers, response inspection, file download, form submission, bearer tokens, basic auth from CLI DO NOT USE FOR: API testing frameworks (use testing/api-testing), load testing (use testing/performance-testing), browser automation (use testing/e2e-testing)

Use when working with TypeScript projects, tooling, and ecosystem. Covers the type system, project configuration, package management, CLI development, and library packages. USE FOR: TypeScript language features, choosing build tools, package managers, project structure, type system guidance, runtime selection DO NOT USE FOR: specific tool configuration details (use the sub-skills: project-system, package-management, cli, packages)

Use when configuring Docker-in-Docker inside a dev container or Codespace. Covers the DinD feature, Docker Compose, building images, and running containers from within the dev environment. USE FOR: running Docker inside dev containers, DinD feature configuration, building images in Codespaces, Compose inside containers DO NOT USE FOR: general devcontainer.json schema (use devcontainer), sidecar services via Compose (use multi-container-workspaces), production Docker builds (use iac/docker)

Use when implementing Command Query Separation (CQS) or CQRS patterns to separate read and write operations in .NET applications. USE FOR: separating read/write models, CQS pattern implementation, CQRS architecture, dedicated command and query handlers, read/write model optimization DO NOT USE FOR: simple CRUD without separation concerns (use entity-framework-core), distributed messaging between services (use masstransit or nservicebus), in-process mediator with pipeline behaviors (use mediatr)

Guidance for Handlebars.NET template engine for .NET. USE FOR: logic-less HTML templating, email template rendering, code generation templates, report formatting, Mustache-compatible templates with helpers and partials. DO NOT USE FOR: sandboxed user-generated templates (use DotLiquid), full C# expression templates (use Razor), complex data transformations, server-side view rendering in ASP.NET.

Guidance for gRPC in .NET using Grpc.AspNetCore and Grpc.Net.Client. USE FOR: gRPC service definitions, proto file compilation, unary and streaming RPCs, gRPC client factory, deadline/cancellation, interceptors, gRPC-Web for browser clients. DO NOT USE FOR: REST/HTTP APIs (use ASP.NET Core), real-time browser push (use SignalR), custom TCP protocols (use dotnetty), email protocols (use mimekit).

USE FOR: Writing and running pattern-based static analysis rules for C# to detect security vulnerabilities, enforce coding standards, find anti-patterns, and automate code migrations. DO NOT USE FOR: Compile-time diagnostics (use Roslyn analyzers), dependency-level metrics (use NDepend), or runtime security scanning (use OWASP ZAP or Burp Suite).

USE FOR: Building Blazor applications with real-time state synchronization using Stl.Fusion computed observables, automatic invalidation, and server-to-client state replication. DO NOT USE FOR: Simple Blazor components without real-time needs, SignalR-only applications, or scenarios where standard Blazor state management (Fluxor, cascading values) is sufficient.

Guidance for Hyperion high-performance polymorphic serializer for .NET. USE FOR: Akka.NET actor message serialization, polymorphic type handling, object graph serialization with circular references, high-throughput binary serialization, version-tolerant deserialization of actor system messages. DO NOT USE FOR: human-readable serialization (use System.Text.Json), cross-language interop (use protobuf-net or Bond), REST API payloads, or long-term data storage requiring schema evolution.

Use when writing or improving integration tests that verify multiple components working together. Covers Testcontainers, ASP.NET WebApplicationFactory, Supertest, pytest with real databases, Spring Boot testing, test database patterns, and CI/Docker-in-Docker strategies. USE FOR: integration tests, Testcontainers, WebApplicationFactory, testing with real databases, testing multi-component interactions, service integration tests DO NOT USE FOR: isolated function tests (use unit-testing), full browser tests (use e2e-testing), service boundary verification (use contract-testing)

Use for load, stress, and scalability testing of applications and APIs. Covers k6 (Grafana), JMeter, Gatling, Artillery, and Lighthouse for web performance audits. Includes test type definitions, key metrics, thresholds, CI integration patterns, and performance budgets. USE FOR: k6, JMeter, Gatling, Artillery, Lighthouse, load testing, stress testing, performance benchmarks, Core Web Vitals, throughput testing, spike testing, soak testing, capacity planning, performance budgets DO NOT USE FOR: functional API testing (use api-testing), browser E2E tests (use e2e-testing), visual regression (use visual-testing)

Use when writing or reviewing code for readability, maintainability, and expressiveness — based on Robert C. Martin's "Clean Code." USE FOR: naming conventions, function design, comment quality, formatting standards, error handling strategy, code readability improvements DO NOT USE FOR: architecture layers (use clean-architecture), refactoring techniques (use refactoring), SOLID principles (use solid)

Micro-frontend architecture — composition approaches, Module Federation, single-spa, web components, shared state, and inter-app communication. Covers the patterns and tradeoffs for splitting a frontend across independent teams. USE FOR: micro-frontend architecture, Module Federation, single-spa, runtime composition, independent frontend deployment, cross-team frontend development DO NOT USE FOR: single-team SPA development (use spa), server-side rendering (use ssr), backend service decomposition (use dev/architecture/microservices)

Use when calling Azure-hosted AI models via the Azure.AI.Inference SDK. Covers chat completions, embeddings, streaming, model selection, and Azure AI model catalog integration. USE FOR: calling Azure AI model catalog models, Azure OpenAI chat completions, generating embeddings from Azure-hosted models, streaming chat responses, working with Mistral/Cohere/Llama models on Azure DO NOT USE FOR: provider-agnostic AI abstractions (use microsoft-extensions-ai), building agent workflows with tools (use agent-framework), on-device ML inference (use onnx), training custom ML models (use mlnet)

Use when building serverless event-driven applications with Azure Functions in .NET. Covers the isolated worker model, HTTP/Timer/Queue/Blob triggers, dependency injection, Durable Functions orchestration, and deployment. USE FOR: serverless HTTP APIs, event-driven processing (queues, blobs, timers), Durable Functions for long-running workflows, lightweight microservices without infrastructure management, scheduled background jobs DO NOT USE FOR: always-on web applications with WebSockets (use ASP.NET Core), complex multi-service orchestration with service discovery (use aspire), long-running compute without orchestration (use Azure Container Apps), Dapr-based microservices (use dapr)

USE FOR: Per-user or per-assembly sandboxed file storage in desktop applications, small settings or cache data scoped to user identity, and legacy ClickOnce or partial-trust application scenarios. DO NOT USE FOR: Server-side web applications, cross-machine shared storage, large file storage, modern applications where application data folders are preferred, or .NET Core/5+ applications targeting Linux or macOS (limited support).

Guidance for Python software development across the ecosystem. Covers project configuration, package management, CLI development, and popular libraries. USE FOR: Python project setup, choosing Python tools, understanding Python language features, virtual environments, type hints, async programming, packaging strategy DO NOT USE FOR: specific tool deep-dives (use the sub-skills: project-system, package-management, cli, packages)

Use when implementing or integrating with the Model Context Protocol (MCP) for AI tool servers, resources, prompts, and context management. USE FOR: building MCP tool servers, exposing resources to agents, prompt templates, connecting agents to external APIs DO NOT USE FOR: agent-to-agent communication (use a2a), interactive UI rendering (use mcp-apps), agent payments (use x402 or ap2)

Use when working with C#, F#, .NET libraries, ASP.NET Core, Blazor, Entity Framework Core, and the broader .NET ecosystem. USE FOR: .NET language features, choosing libraries and frameworks, project structure, package selection, architecture decisions DO NOT USE FOR: specific library configuration details (use the sub-skills: web, data, testing, eventing, cloud, etc.)

USE FOR: Defining high-performance validation specifications using Validot's fluent specification builder. Use when you need allocation-free validation with reusable specifications, fast execution, and detailed error output. DO NOT USE FOR: Async validation with database lookups (Validot is synchronous), ASP.NET Core automatic model validation integration (use FluentValidation), or guard-clause-style argument checking (use CommunityToolkit Guard).

Use when identifying consumer protection laws that apply to software products and digital services. Covers terms of service, EULAs, refund policies, dark patterns regulation, subscription practices, the EU Digital Markets Act, and consumer rights across jurisdictions. USE FOR: terms of service, EULA, consumer rights, refund policies, dark patterns, auto-renewal laws, Digital Markets Act, Digital Services Act, FTC Act, CAN-SPAM, children's privacy (COPPA), subscription traps DO NOT USE FOR: data privacy regulations (use privacy-data-protection), content liability (use content-moderation), contract drafting (consult legal counsel)

Guidance for Python package management, dependency resolution, virtual environments, and lockfiles. USE FOR: installing packages, managing dependencies, choosing between pip/uv/poetry/pdm/conda, virtual environment setup, lockfile strategies, private package indexes, pipx for CLI tools DO NOT USE FOR: configuring pyproject.toml or build backends (use project-system), building CLI applications (use cli)

Azure Observability Services including Azure Monitor, Application Insights, Log Analytics, Alerts, and Workbooks. Provides metrics, APM, distributed tracing, KQL queries, and interactive reports.

Hexagonal Architecture (Ports and Adapters), Onion Architecture, and their relationship to Clean Architecture -- enabling technology-independent domain logic with high testability. USE FOR: hexagonal architecture, ports and adapters, onion architecture, driving/driven adapters, technology-independent domain design, adapter-based testability DO NOT USE FOR: clean architecture layers specifically (use dev/craftsmanship/clean-architecture), microservice boundaries (use microservices), domain model design (use domain-driven-design)

Monolithic architecture patterns including modular monolith design, monolith-first strategy, and migration paths to microservices via the Strangler Fig pattern. USE FOR: monolith-first strategy, modular monolith design, monolith decomposition, Strangler Fig migration, avoiding Big Ball of Mud, when to keep a monolith DO NOT USE FOR: microservice decomposition (use microservices), event-driven architecture (use event-driven), clean architecture layers (use dev/craftsmanship/clean-architecture)

Use when building rich terminal UIs in .NET with Spectre.Console. Covers tables, trees, progress bars, prompts, live rendering, markup formatting, and the Spectre.Console.Cli command framework. USE FOR: rendering tables and grids in the terminal, progress bars and spinners, interactive prompts and selections, colorized and styled console output, building CLI apps with Spectre.Console.Cli DO NOT USE FOR: executing external processes (use cliwrap), argument parsing without UI (use commandline-cheatsheet), building web UIs (use Blazor), logging output (use ILogger with console provider)

USE FOR: Unified cloud storage abstraction across Azure Blob Storage, AWS S3, Google Cloud Storage, local filesystem, and FTP. Blob read/write, listing, streaming large files, and switching storage providers without code changes. DO NOT USE FOR: Relational data access, message queuing, low-level storage operations requiring provider-specific APIs (e.g., Azure Blob leases, S3 multipart upload tuning), or in-memory caching.

USE FOR: GraphQL-like selective field projection in REST APIs, reducing over-fetching by returning only client-requested fields, dynamic response shaping based on query parameters, and bandwidth optimization for mobile or low-bandwidth clients. DO NOT USE FOR: Full GraphQL implementations (use HotChocolate or GraphQL.NET), server-side data filtering or authorization, complex nested relationship loading, or replacing proper DTOs and view models.

Use when building text parsers in C# using Parakeet, a parser combinator library focused on simplicity and PEG grammars. USE FOR: C# PEG parser combinators, grammar definition, text parsing, DSL implementation, rule-based parsing DO NOT USE FOR: F# parser combinators (use fparsec), high-performance C# parsing (use pidgin), regex-based matching, JSON/XML parsing (use System.Text.Json)

Guidance for DotNetty event-driven asynchronous network application framework. USE FOR: high-performance TCP/UDP servers and clients, custom binary protocol implementations, Netty-style channel pipelines, event loop groups, codec handlers, TLS/SSL socket connections. DO NOT USE FOR: HTTP APIs (use ASP.NET Core), gRPC services (use grpc-dotnet), email sending (use mimekit), high-level stream processing (use system-io-pipelines).

USE FOR: IL weaving at build time to inject cross-cutting concerns such as INotifyPropertyChanged implementation, null-guard checks, method timing, logging, and resource embedding into .NET assemblies. DO NOT USE FOR: Runtime AOP frameworks, source generators that produce C# code, or scenarios where compile-time code generation (Roslyn generators) would be more transparent and debuggable.

USE FOR: Choosing between and implementing .NET web application patterns including MVC, Razor Pages, Minimal APIs, and Blazor. Use when deciding on architecture, project structure, and routing strategies for ASP.NET Core web applications. DO NOT USE FOR: Native mobile/desktop apps (use MAUI or Avalonia), game development (use Unity or MonoGame), or projects that exclusively need a REST API without any server-rendered content (use the aspnet-core skill directly).

Use when identifying financial regulations that apply to software handling payments, banking, or financial data. Covers PCI DSS, PSD2/PSD3, SOX, AML/KYC, Dodd-Frank, MiFID II, open banking, and fintech licensing across jurisdictions. USE FOR: PCI DSS, PSD2, PSD3, SOX, AML, KYC, Dodd-Frank, MiFID II, open banking, fintech licensing, payment processing compliance, money transmission, crypto regulation DO NOT USE FOR: payment gateway integration (use platform-specific skills), encryption implementation (use security/cryptography), financial data modeling (use dev/backend/data-modeling)

Use when creating UML and architecture diagrams using PlantUML's text-based DSL. Covers all major diagram types, syntax, skinparam theming, C4-PlantUML integration, and preprocessing directives. USE FOR: sequence diagrams, class diagrams, activity diagrams, component diagrams, state diagrams, use case diagrams, object diagrams, deployment diagrams, PlantUML syntax, skinparam theming, C4-PlantUML library, preprocessing directives, text-to-UML rendering DO NOT USE FOR: inline Markdown diagrams (use mermaidjs), enterprise architecture (use togaf or archimate), C4-specific DSL (use c4-diagrams with Structurizr)

Use when authoring, structuring, or consuming design tokens in the W3C Design Tokens Community Group (DTCG) format. Covers token types, groups, aliases, composite tokens, and file conventions. USE FOR: W3C DTCG token files, token types (color, dimension, typography), token aliases and references, token groups, composite tokens, .tokens.json files DO NOT USE FOR: transforming tokens into platform code (use style-dictionary), Figma variable management (use figma), component styling (use the relevant framework skill)

Guidance for PdfSharpCore PDF generation and modification library for .NET. USE FOR: creating PDF documents programmatically, drawing text/shapes/images on PDF pages, modifying existing PDFs, merging PDF files, generating reports and invoices as PDF, adding headers/footers/page numbers. DO NOT USE FOR: extracting text from PDFs (use PdfPig), PDF form filling with complex logic, high-volume HTML-to-PDF conversion (use a headless browser), PDF/A compliance.

Guidance for TimeProvider abstraction for testable time-dependent code. USE FOR: making time-dependent code testable, replacing DateTime.UtcNow and DateTimeOffset.UtcNow with injectable abstractions, controlling time in unit tests with FakeTimeProvider, testing expiration logic, scheduling, token lifetimes, and time-based business rules. DO NOT USE FOR: high-precision timing or benchmarking (use Stopwatch), NTP synchronization, or scenarios running on .NET versions prior to .NET 8.

Use when identifying intellectual property considerations for software products. Covers patents, copyrights, trademarks, trade secrets, and IP assignment with jurisdiction-specific considerations for software companies. USE FOR: software patents, copyright, trademarks, trade secrets, IP ownership, IP assignment, work-for-hire, patent trolls, IP due diligence, prior art, DMCA takedowns DO NOT USE FOR: open-source license selection (use open-source-licensing), content moderation (use content-moderation), drafting patent applications (consult a patent attorney)

Use when modeling enterprise architecture with ArchiMate, the Open Group standard visual notation (v3.2). Covers Business, Application, and Technology layers, element types, relationship types, viewpoints, and modeling best practices. USE FOR: enterprise architecture modeling, layered architecture visualization, Business-Application-Technology mapping, ArchiMate element and relationship notation, architecture viewpoint selection, motivation modeling, cross-layer dependency analysis DO NOT USE FOR: architecture development process (use togaf), system decomposition (use c4-diagrams), general-purpose diagrams (use mermaidjs or d2)

Use when creating text-based diagrams that render in Markdown environments. Mermaid.js is the most widely supported diagrams-as-code tool, with native rendering in GitHub, GitLab, Notion, and many documentation platforms. USE FOR: flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, pie charts, mindmaps, timelines, git graphs, quadrant charts, C4 diagrams in Markdown, diagrams embedded in PRs and wikis, GitHub-native diagram rendering DO NOT USE FOR: enterprise architecture (use togaf or archimate), C4-specific DSL tooling (use c4-diagrams), advanced layout control (use d2)

Use when writing Behavior-Driven Development specifications in Gherkin syntax. Covers Feature files, Scenario/Scenario Outline, Given/When/Then steps, Background, Examples tables, tags, data tables, doc strings, and step definition patterns. USE FOR: BDD acceptance criteria, executable specifications, Given/When/Then scenarios, feature files, Cucumber/SpecFlow/Reqnroll/Behave test specs, scenario outlines with examples, living documentation DO NOT USE FOR: free-form markdown test specs (use gauge), requirements documents (use prd or trd), architecture decisions (use adr)

Use when working with Infrastructure as Code tools and platforms. Covers Terraform, Pulumi, CloudFormation, Bicep, ARM, Kubernetes, Helm, Docker, Crossplane, and Dagger. USE FOR: choosing IaC tools, comparing Terraform vs Pulumi vs CloudFormation, infrastructure strategy DO NOT USE FOR: specific tool syntax (use the sub-skills: terraform, pulumi, bicep, etc.)

Use when working with fundamental CLI tools and utilities that are essential for software development across all languages and platforms. Covers shells, version control, system package managers, containers, remote access, HTTP clients, data processing, and build runners. USE FOR: CLI tools, developer tooling, shell scripting, version control, system package managers, containers, remote access, build automation, text processing, choosing cross-platform dev tools DO NOT USE FOR: language-specific package managers (use language-specific skills like npm/pip/cargo), IDE configuration, language-specific build tools (use language-specific skills)

Use when implementing the Agent-to-Agent (A2A) protocol for inter-agent communication, task delegation, and multi-agent collaboration. USE FOR: agent-to-agent communication, task delegation between agents, Agent Card publishing, multi-agent collaboration DO NOT USE FOR: tool integration (use mcp), agent payments (use ap2 or x402), agent definition (use adl)

Use when implementing the Agent Communication Protocol (ACP) for REST-based agent-to-agent communication, task delegation, and multimodal message exchange. USE FOR: ACP agent servers, ACP client integration, agent discovery via manifests, run lifecycle management, session-based stateful workflows, BeeAI agents DO NOT USE FOR: JSON-RPC agent communication (use a2a), tool integration for LLMs (use mcp), agent payments (use ap2 or x402), agent definition (use adl)

Use when defining AI agents declaratively with Agent Definition Language (ADL). Covers agent identity, LLM configuration, tools, permissions, RAG inputs, and governance metadata. USE FOR: declarative agent blueprints, agent identity and permissions, LLM configuration, governance metadata DO NOT USE FOR: agent runtime orchestration (use cagent), tool integration (use mcp), agent communication (use a2a)

Guidance for AspectCore AOP framework for .NET Core. USE FOR: cross-cutting concerns via interceptors, method-level AOP, dynamic proxies, logging/caching/authorization interception, decorating service interfaces. DO NOT USE FOR: compile-time weaving (use PostSharp), full IL rewriting, non-DI scenarios, .NET Framework-only projects.

Guidance for Nethermind Ethereum client and Ethereum development in .NET. USE FOR: running Ethereum full/archive nodes, interacting with Ethereum via JSON-RPC, building Ethereum plugins, blockchain data indexing, smart contract interaction from .NET, EVM chain development. DO NOT USE FOR: Solidity smart contract authoring (use Foundry/Hardhat), front-end dApp UI (use JavaScript/TypeScript), non-EVM blockchains, cryptocurrency trading bots.

Guidance for AutoMapper convention-based object mapping library. USE FOR: convention-based object-to-object mapping, Profile-based mapping configuration, flattening/unflattening, ProjectTo with EF Core IQueryable, reverse mapping, value resolvers, type converters. DO NOT USE FOR: compile-time source-generated mapping (use mapperly), manual mapping in performance-critical paths, mapping that involves complex business logic.

Guidance for MimeKit and MailKit email libraries in .NET. USE FOR: creating and parsing MIME email messages, sending email via SMTP with MailKit, reading email via IMAP/POP3, attachments, HTML email, S/MIME and PGP signing/encryption. DO NOT USE FOR: SMS/voice messaging (use twilio), HTTP APIs (use ASP.NET Core), custom TCP protocols (use dotnetty), gRPC services (use grpc-dotnet).

Guidance for CryptoNet cryptography library in .NET. USE FOR: RSA encryption/decryption, symmetric AES encryption, X.509 certificate-based crypto, self-signed certificate generation, key pair management, encrypting sensitive data at rest. DO NOT USE FOR: password hashing (use ASP.NET Core Identity), TLS/HTTPS configuration, JWT token signing (use Microsoft.IdentityModel), or authorization (use Casbin/Enforcer).

Guidance for Microsoft Bond schematized data serialization framework. USE FOR: cross-platform schema-first serialization, Compact Binary and Fast Binary wire formats, schema evolution with backward/forward compatibility, high-performance RPC data contracts, strongly typed data interchange between .NET, C++, Python, and Java services. DO NOT USE FOR: JSON REST APIs (use System.Text.Json), human-readable config files, simple key-value storage, or when schema-less flexibility is required.

Guidance for Playwright browser automation and end-to-end testing in .NET. USE FOR: cross-browser end-to-end testing, UI automation, screenshot and visual regression testing, network request interception, mobile viewport emulation, testing SPAs and server-rendered pages, CI/CD browser testing in headless mode. DO NOT USE FOR: unit testing (use xUnit with Moq), API contract testing (use Pact), load testing (use k6 or NBomber), or testing non-web applications.

Use when working with AI agent protocols, standards, interoperability specifications, evaluation contracts, synthetic simulation data, improvement pipelines, and agent steering workflows. Covers MCP, A2A, ACP, Agent Skills, AGENTS.md, ADL, Improve, x402, AP2, MCP Apps, cagent, and learn. USE FOR: agent protocol selection, comparing MCP vs A2A vs ACP, understanding agent standards ecosystem, choosing payment protocols, choosing eval standards, choosing improvement techniques, choosing synthetic data simulation techniques, steering from user feedback DO NOT USE FOR: specific protocol, eval, or improvement implementation details (use the sub-skills: mcp, a2a, acp, improve, learn, x402, etc.)

Use when working with fundamental software development knowledge — patterns, algorithms, architecture, and craftsmanship principles drawn from canonical published works. USE FOR: development fundamentals, pattern selection, architecture decisions, algorithm choice, code quality principles, choosing between architectural styles DO NOT USE FOR: specific pattern implementations (use sub-skills: design-patterns, integration-patterns, algorithms, etc.), testing strategy (use testing), infrastructure (use iac)

Guidance for Casbin.NET authorization library (Enforcer). USE FOR: access control list (ACL) enforcement, role-based access control (RBAC), attribute-based access control (ABAC), policy management, multi-tenant authorization, API endpoint protection. DO NOT USE FOR: authentication or login flows (use ASP.NET Core Identity), encryption (use CryptoNet), relationship-based access control with graph traversal (use Topaz), or input sanitization (use Hygiene).

Use when identifying legal obligations for platforms hosting user-generated content. Covers intermediary liability (Section 230, EU DSA), DMCA takedown procedures, illegal content obligations, CSAM reporting requirements, and content moderation transparency mandates. USE FOR: Section 230, EU Digital Services Act, DMCA, intermediary liability, content moderation, takedown procedures, CSAM reporting, terrorist content regulation, online safety, platform liability, safe harbor DO NOT USE FOR: content filtering implementation (use platform-specific skills), intellectual property strategy (use intellectual-property), consumer protection terms (use consumer-protection)

Use when implementing data protection controls for compliance and privacy. Covers encryption at rest and in transit, PII handling, data classification, GDPR, CCPA, HIPAA requirements, and data retention policies. USE FOR: data encryption, PII handling, GDPR, CCPA, HIPAA, data classification, data retention, data masking, tokenization, privacy by design, data minimization DO NOT USE FOR: cryptographic algorithm selection (use cryptography), access control design (use authentication), audit logging (use logging-monitoring)

Use when identifying and prioritizing security threats during system design. Covers STRIDE and DREAD frameworks, threat modeling processes, data flow diagrams for security, and integrating threat analysis into the SDLC. USE FOR: STRIDE, DREAD, threat modeling, data flow diagrams for security, attack surface analysis, security design review, threat prioritization DO NOT USE FOR: runtime vulnerability scanning (use security-testing), incident response (use logging-monitoring), specific vulnerability remediation (use owasp)

Use when setting up or improving contract tests that verify API compatibility between services. Covers Pact (consumer-driven contracts), PactFlow (bi-directional contracts), Spring Cloud Contract, Pact Broker, can-i-deploy, and strategies for choosing between contract testing approaches. USE FOR: Pact, PactFlow, Spring Cloud Contract, consumer-driven contracts, bi-directional contracts, API compatibility verification, can-i-deploy, Pact Broker DO NOT USE FOR: full user flow tests (use e2e-testing), API functional testing (use api-testing), unit testing (use unit-testing)

Use when designing database schemas, choosing data modeling strategies, or making decisions about data storage architecture across relational, document, graph, key-value, and time-series paradigms. USE FOR: database schema design, data modeling patterns, normalization/denormalization, document modeling, graph modeling, key-value design, time-series modeling, schema migration strategies, database-per-service decisions DO NOT USE FOR: ERD diagramming (use specs/diagramming/erd), API design (use api-design), caching strategy (use caching)

Use when building AI agents with Microsoft.SemanticKernel or Microsoft.Extensions.AI.Agent frameworks. Covers agent creation, tool/plugin registration, multi-agent orchestration, chat completion agents, and OpenAI Assistants integration. USE FOR: building AI agents with tools and plugins, multi-agent chat workflows, Semantic Kernel agent orchestration, OpenAI Assistants API integration, agent-based automation pipelines DO NOT USE FOR: simple chat completions without agent patterns (use microsoft-extensions-ai), inter-service agent communication over A2A protocol (use a2a), ML model training (use mlnet), raw ONNX inference (use onnx)