orchestkit

Automated accessibility testing with axe-core, Playwright, and jest-axe for WCAG compliance. Use when adding or validating a11y tests, running WCAG checks, or auditing UI accessibility.

Curate and add documents to the golden dataset with multi-agent validation. Use when adding test data, creating golden datasets, saving examples.

LLM guardrails with NeMo, Guardrails AI, and OpenAI. Input/output rails, hallucination prevention, fact-checking, toxicity detection, red-teaming patterns. Use when building LLM guardrails, safety checks, or red-team workflows.

Vercel agent-browser CLI for headless browser automation. 93% less context than Playwright MCP. Snapshot + refs workflow with @e1 @e2 element references. Use when automating browser tasks, web scraping, form automation, or content capture.

Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.

Advanced RAG with Self-RAG, Corrective-RAG, and knowledge graphs. Use when building agentic RAG pipelines, adaptive retrieval, or query rewriting.

DDD aggregate design patterns for consistency boundaries and invariants. Use when designing aggregate roots, enforcing business invariants, handling cross-aggregate references, or optimizing aggregate size.

Alembic migration patterns for SQLAlchemy 2.0 async. Use when creating database migrations, managing schema versions, handling zero-downtime deployments, or implementing reversible database changes.

Comprehensive API design patterns for REST, GraphQL, and gRPC. Use when designing APIs, creating endpoints, adding routes, implementing pagination, rate limiting, or authentication patterns.

API versioning strategies including URL path, header, and content negotiation. Use when migrating v1 to v2, handling breaking changes, implementing deprecation or sunset policies, or managing backward compatibility.

Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Use when writing ADRs, recording decisions, or evaluating options.

Assess task complexity with automated codebase metrics. Use before starting work to determine if task needs breakdown.

Python asyncio patterns with TaskGroup, structured concurrency, and modern 3.11+ features. Use when implementing concurrent operations, async context managers, or high-performance async services.

Authentication and authorization patterns. Use when implementing login flows, JWT tokens, session management, password security, OAuth 2.1, Passkeys/WebAuthn, or role-based access control.

Enforces FastAPI Clean Architecture with blocking validation. Use when implementing router-service-repository patterns, enforcing layer separation, or validating dependency injection in backend code.

View and manage your personal best practices library with success/failure patterns. Use when viewing best practices, checking patterns, reviewing success/failure history.

Biome 2.0+ linting and formatting for fast, unified code quality. Includes type inference, ESLint migration, CI integration, and 421 lint rules. Use when migrating from ESLint/Prettier or setting up new projects.

Use when creating or developing anything, before writing code or implementation plans. Brainstorming skill refines ideas through structured questioning and alternatives.

Capture content from JavaScript-rendered pages, login-protected sites, and multi-page documentation using agent-browser CLI. Use when capturing browser content, extracting web data, saving page content.

LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.

Backend caching patterns with Redis including write-through, write-behind, cache-aside, and invalidation strategies. Use when implementing Redis cache, managing TTL/expiration, preventing cache stampede, or optimizing cache hit rates.

Advanced Celery patterns including canvas workflows, priority queues, rate limiting, multi-queue routing, and production monitoring. Use when implementing complex task orchestration, task prioritization, or enterprise-grade background processing.

Configure Claude Code statusline with context window monitoring using CC 2.1.6 fields. Use when configuring statusline, monitoring context, displaying HUD.

SOLID principles, hexagonal architecture, ports and adapters, and DDD tactical patterns for maintainable backends. Use when implementing clean architecture, decoupling services, separating domain logic, or creating testable architecture.

Creates git commits with conventional format, branch protection, and pre-commit validation. Use when committing changes, staging files, generating commit messages, saving changes, or pushing changes.

Interactive OrchestKit configuration wizard. Use when you need to configure OrchestKit settings, MCP servers, or plugin options.

Database and HTTP connection pooling patterns for Python async applications. Use when configuring asyncpg pools, aiohttp sessions, or optimizing connection lifecycle in high-concurrency services.

Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.

Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.

Consumer-driven contract testing with Pact for API compatibility. Use when testing microservice integrations, verifying API contracts, preventing breaking changes, or implementing provider verification.

Core Web Vitals optimization for LCP, INP, CLS with 2026 thresholds, performance budgets, and RUM. Use when improving page performance, diagnosing CWV regressions, or setting performance budgets.

CQRS (Command Query Responsibility Segregation) patterns for separating read and write models. Use when optimizing read-heavy systems, implementing event sourcing, or building systems with different read/write scaling requirements.

Create GitHub pull requests with validation and auto-generated descriptions. Use when creating pull requests, opening PRs, submitting code for review.

Dashboard UI patterns with widget composition, real-time data updates, responsive grid layouts, and data tables for React applications. Use when building dashboards, widgets, or data tables.

SQL and NoSQL schema design with normalization, indexing, and migration patterns. Use when designing database schemas, creating tables, optimizing slow queries, or planning database migrations.

Database version control and change management patterns. Use when managing schema history, coordinating database changes across environments, implementing audit trails, or versioning database objects.

Visualize OrchestKit architecture decisions over time, tracking CC version evolution and best practices adoption. Use when reviewing decisions, understanding rationale, or generating timeline docs.

Use when building secure AI pipelines or hardening LLM integrations. Defense-in-depth implements 8 validation layers from edge to storage with no single point of failure.

Use this skill when creating or evolving design systems for applications. Provides design token structures, component architecture patterns, documentation templates, and accessibility guidelines. Ensures consistent, scalable, and accessible UI design across products.

Distributed locking patterns with Redis and PostgreSQL for coordination across instances. Use when implementing exclusive access, preventing race conditions, or coordinating distributed resources.

OrchestKit health diagnostics command that validates plugin configuration and reports issues. Use when running doctor checks or troubleshooting plugin health.

Domain-Driven Design tactical patterns for complex business domains. Use when modeling entities, value objects, domain services, repositories, or establishing bounded contexts.

End-to-end testing with Playwright 1.57+. Use when testing critical user journeys, browser automation, cross-browser testing, AI-assisted test generation, or validating complete application flows.

Use when deploying to Cloudflare Workers, Vercel Edge, or Deno Deploy. Covers edge middleware, streaming, runtime constraints, and globally distributed low-latency patterns.

Text embeddings for semantic search and similarity. Use when converting text to vectors, choosing embedding models, implementing chunking strategies, or building document similarity features.

RFC 9457 Problem Details for standardized HTTP API error responses. Use when implementing problem details format, structured API errors, error registries, or migrating from RFC 7807.

Error pattern analysis and troubleshooting for Claude Code sessions. Use when handling errors, fixing failures, troubleshooting issues.

Event sourcing patterns for storing state as a sequence of events. Use when implementing event-driven architectures, CQRS, audit trails, or building systems requiring full history reconstruction.

Use when completing tasks, code reviews, or deployments to verify work with evidence. Collects test results, build outputs, coverage metrics, and exit codes to prove work is complete.

Deep codebase exploration with parallel specialized agents. Use when exploring a repo, finding files, or discovering architecture with the explore agent.

FastAPI 2026 advanced patterns including lifespan, dependencies, middleware, and Pydantic settings. Use when configuring FastAPI lifespan events, creating dependency injection, building Starlette middleware, or managing async Python services with uvicorn.

Manage the OrchestKit feedback system that learns from your usage. Use when providing feedback, reporting issues, suggesting improvements.

LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.

Fix GitHub issue with parallel analysis and implementation. Use when fixing issues, resolving bugs, closing GitHub issues.

Keyboard focus management patterns for accessibility. Covers focus traps, roving tabindex, focus restore, skip links, and FocusScope components for WCAG-compliant interactive widgets. Use when implementing focus traps or keyboard navigation.

React Hook Form v7 with Zod validation, React 19 useActionState, Server Actions, field arrays, and async validation. Use when building complex forms, validation flows, or server action forms.

LLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.

Quick recovery from common git mistakes including undo commits, recover branches, and reflog operations. Use when you need to undo, recover, or fix Git history.

GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.

Use when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and multi-agent analysis patterns for test data.

Use when backing up, restoring, or validating golden datasets. Prevents data loss and ensures test data integrity for AI/ML evaluation systems.

Use when validating golden dataset quality. Runs schema checks, duplicate detection, and coverage analysis to ensure dataset integrity for AI evaluation.

gRPC with Python using grpcio and protobuf for high-performance microservice communication. Use when implementing service-to-service APIs, streaming data, or building polyglot microservices requiring strong typing.

High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.

HyDE (Hypothetical Document Embeddings) for improved semantic retrieval. Use when queries don't match document vocabulary, retrieval quality is poor, or implementing advanced RAG patterns.

Use this skill for internationalization (i18n) in React applications. Covers ALL user-facing strings, date/time handling, locale-aware formatting (useFormatting hook), ICU MessageFormat, Trans component, and RTL/LTR support.

Idempotency patterns for APIs and event handlers. Use when implementing exactly-once semantics, deduplicating requests, or building reliable distributed systems.

Image optimization with Next.js 15 Image, AVIF/WebP formats, blur placeholders, responsive sizes, and CDN loaders. Use when improving image performance, responsive sizing, or Next.js image pipelines.

Full-power feature implementation with parallel subagents, skills, and MCPs. Use when implementing features, building features, creating features, or developing features.

Input validation and sanitization patterns. Use when validating user input, preventing injection attacks, implementing allowlists, or sanitizing HTML/SQL/command inputs.

Integration testing patterns for APIs and components. Use when testing component interactions, API endpoints with test databases, or service layer integration.

Automatic GitHub issue progress updates from commits and sub-task completion. Use when tracking issue progress from commits or automating status updates.

LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token usage, or implementing prompt versioning.

LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, debugging with state history, or avoiding re-running expensive operations.

LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.

LangGraph human-in-the-loop patterns. Use when implementing approval workflows, manual review gates, user feedback integration, or interactive agent supervision.

LangGraph parallel execution patterns. Use when implementing fan-out/fan-in workflows, map-reduce over tasks, or running independent agents concurrently.

LangGraph conditional routing patterns. Use when implementing dynamic routing based on state, creating branching workflows, or building retry loops with conditional edges.

LangGraph state management patterns. Use when designing workflow state schemas, using TypedDict vs Pydantic, implementing accumulating state with Annotated operators, or managing shared state across nodes.

LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.

Code splitting and lazy loading with React.lazy, Suspense, route-based splitting, intersection observer, and preload strategies for optimal bundle performance. Use when implementing lazy loading or preloading.

LLM output evaluation and quality assessment. Use when implementing LLM-as-judge patterns, quality gates for AI outputs, or automated evaluation pipelines.

Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.

Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.

Advanced MCP patterns for tool composition, resource management, and scaling. Build custom MCP servers, compose tools, manage resources efficiently. Use when composing MCP tools or scaling MCP servers.

MCP security patterns for prompt injection defense, tool poisoning prevention, and permission management. Use when securing MCP servers, validating tool descriptions, implementing allowlists.

Building MCP (Model Context Protocol) servers for Claude extensibility. Use when creating MCP servers, building custom Claude tools, extending Claude with external integrations, or developing tool packages for Claude Desktop.

Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information across sessions, or when referencing what we discussed last time or in a previous session.

Auto-sync session context, decisions, and patterns to Mem0 for cross-session continuity. Use when persisting session memory or syncing decisions.

Graph-first memory orchestration - knowledge graph (PRIMARY, always available) with optional mem0 cloud enhancement for semantic search. Use when designing memory orchestration or combining graph and mem0.

Message queue patterns with RabbitMQ, Redis Streams, and Kafka. Use when implementing async communication, pub/sub systems, event-driven microservices, or reliable message delivery.

Use this skill for implementing Motion (Framer Motion) animations in React applications. Covers animation presets, page transitions, modal animations, list stagger effects, hover interactions, skeleton loaders, and RTL-aware animation patterns.

Mock Service Worker (MSW) 2.x for API mocking. Use when testing frontend components with network mocking, simulating API errors, or creating deterministic API responses in tests.

Multi-agent coordination and synthesis patterns. Use when orchestrating multiple specialized agents, implementing fan-out/fan-in workflows, or synthesizing outputs from parallel agents.

CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.

Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.

Transactional outbox pattern for reliable event publishing. Use when implementing atomic writes with event delivery, ensuring exactly-once semantics, or building event-driven microservices.

OWASP Top 10 security vulnerabilities and mitigations. Use when conducting security audits, implementing security controls, or reviewing code for common vulnerabilities.

Performance and load testing with k6 and Locust. Use when validating system performance under load, stress testing, identifying bottlenecks, or establishing performance baselines.

Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid search, semantic + keyword retrieval, vector search optimization, metadata filtering, or choosing between HNSW and IVFFlat indexes.

Enforce 2026 folder structure standards - feature-based organization, max nesting depth, unidirectional imports. Blocks structural violations. Use when creating files or reviewing project architecture.

Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.

Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when designing prompts, improving accuracy, managing prompt lifecycle.

Property-based testing with Hypothesis for discovering edge cases automatically. Use when testing invariants, finding boundary conditions, implementing stateful testing, or validating data transformations.

Progressive Web App patterns with Workbox 7.x, service worker lifecycle, offline-first strategies, and installability. Use when building PWAs, service workers, or offline support.

Advanced pytest patterns including custom markers, plugins, hooks, parallel execution, and pytest-xdist. Use when implementing custom test infrastructure, optimizing test execution, or building reusable test utilities.

Use when assessing task complexity, before starting complex tasks, or when stuck after multiple attempts. Provides quality-gates scoring (1-5) and escalation workflows.

Query decomposition for multi-concept retrieval. Use when handling complex queries spanning multiple topics, implementing multi-hop retrieval, or improving coverage for compound questions.

Radix UI unstyled accessible primitives for dialogs, popovers, dropdowns, and more. Use when building custom accessible components, understanding shadcn internals, or needing polymorphic composition.

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, constructing context from retrieved documents, adding citations, or implementing hybrid search.

API rate limiting with token bucket, sliding window, and Redis distributed patterns. Use when implementing rate limits, throttling requests, handling 429 Too Many Requests, protecting against API abuse, or configuring SlowAPI with Redis.

React Aria (Adobe) accessible component patterns for building WCAG-compliant interactive UI with hooks. Use when implementing buttons, dialogs, comboboxes, menus, and other accessible components in React applications.

Use when building Next.js 16+ apps with React Server Components. Covers App Router, streaming SSR, Server Actions, and React 19 patterns for server-first architecture.

Data visualization with Recharts 3.x including responsive charts, custom tooltips, animations, and accessibility for React applications. Use when building charts or dashboards with Recharts.

GitHub release workflow with semantic versioning, changelogs, and release automation using gh CLI. Use when creating releases, tagging versions, or publishing changelogs.

React render performance patterns including React Compiler integration, memoization strategies, TanStack Virtual, and DevTools profiling. Use when debugging slow renders, optimizing large lists, or reducing unnecessary re-renders.

Reranking patterns for improving search precision. Use when implementing cross-encoder reranking, LLM-based relevance scoring, or improving retrieval quality in RAG pipelines.

Production-grade fault tolerance for distributed systems. Use when implementing circuit breakers, retry with exponential backoff, bulkhead isolation patterns, or building resilience into LLM API integrations.

Responsive design with Container Queries, fluid typography, cqi/cqb units, and mobile-first patterns for React applications. Use when building responsive layouts or container queries.

Comprehensive PR review with 6-7 parallel specialized agents. Use when reviewing pull requests, checking PRs, code review.

Comprehensive test execution with parallel analysis and coverage reporting. Use when running test suites or troubleshooting failures with the run-tests workflow.

Saga patterns for distributed transactions with orchestration and choreography approaches. Use when implementing multi-service transactions, handling partial failures, or building systems requiring eventual consistency with compensation.

CSS Scroll-Driven Animations with ScrollTimeline, ViewTimeline, parallax effects, and progressive enhancement for performant scroll effects. Use when implementing scroll-linked animations or parallax.

Automated security scanning for dependencies and code. Use when running npm audit, pip-audit, Semgrep, secret detection, or integrating security checks into CI/CD.

shadcn/ui component patterns including CVA variants, OKLCH theming, cn() utility, and composition. Use when adding shadcn components, building variant systems, or customizing themes.

SQLAlchemy 2.0 async patterns with AsyncSession, async_sessionmaker, and FastAPI integration. Use when implementing async database operations, connection pooling, or async ORM queries.

Multi-PR development for large features. Stack dependent PRs, manage rebases, and get faster reviews on smaller changes. Use when creating stacked PRs.

Strawberry GraphQL library for Python with FastAPI integration, type-safe resolvers, DataLoader patterns, and subscriptions. Use when building GraphQL APIs with Python, implementing real-time features, or creating federated schemas.

Real-time data streaming with SSE, WebSockets, and ReadableStream. Use when implementing streaming responses, real-time data updates, Server-Sent Events, WebSocket setup, live notifications, push updates, or chat server backends.

Use when planning system architecture to ensure nothing is missed. Provides structured questions covering scalability, security, data, and operational dimensions before implementation.

CC 2.1.16 Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.

Temporal.io workflow orchestration for durable, fault-tolerant distributed applications. Use when implementing long-running workflows, saga patterns, microservice orchestration, or systems requiring exactly-once execution guarantees.

Test data management with fixtures and factories. Use when creating test data strategies, implementing data factories, managing fixtures, or seeding test databases.

Enforce testing best practices - AAA pattern, naming conventions, isolation, coverage thresholds. Blocks non-compliant tests. Use when writing or reviewing tests.

End-to-end type safety with Zod, tRPC, Prisma, and TypeScript 5.7+ patterns. Use when creating Zod schemas, setting up tRPC, validating input, implementing exhaustive switch statements, branded types, or type checking with ty.

Unit testing patterns and best practices. Use when writing isolated unit tests, implementing AAA pattern, designing test isolation, or setting coverage targets for business logic.

VCR.py HTTP recording for Python tests. Use when testing Python code making HTTP requests, recording API responses for replay, or creating deterministic tests for external services.

Comprehensive feature verification with parallel analysis agents. Use when verifying implementations, testing changes, validating features, or checking correctness.

View Transitions API for smooth page transitions, shared element animations, and SPA/MPA navigation in React applications. Use when adding view transitions or page animations.

GPT-5/4o, Claude 4.5, Gemini 2.5/3, Grok 4 vision patterns for image analysis, document understanding, and visual QA. Use when implementing image captioning, document/chart analysis, or multi-image comparison.

Advanced Vite 7+ patterns including Environment API, plugin development, SSR configuration, library mode, and build optimization. Use when customizing build pipelines, creating plugins, or configuring multi-environment builds.

WCAG 2.2 AA accessibility compliance patterns for web applications. Use when auditing accessibility or implementing WCAG requirements.

Manage multiple Claude Code instances across git worktrees. Check status, claim/release file locks, sync decisions, and prevent conflicts. Use when coordinating multiple worktrees or Claude instances.

Safe database schema changes without downtime using expand-contract pattern and online schema changes. Use when deploying schema changes to production without service interruption.

ffmpeg audio mixing patterns for video production. Use when mixing narration with music, implementing ducking, or balancing volume levels for demos

Step-by-step recipes for demo videos. Use when creating skill demos, agent showcases, plugin installs, or tutorial walkthroughs with precise timing

ElevenLabs TTS integration for video narration. Use when generating voiceover audio, selecting voices, or building script-to-audio pipelines

Best practices for HeyGen - AI avatar video creation API. Use when creating AI avatar videos, generating talking head videos, or integrating HeyGen with Remotion.

Create Manim animations for demo videos. Use when visualizing agent workflows, skill pipelines, or architecture diagrams as animated MP4 overlays

Audio selection for tech demo videos. Use when choosing background music, timing SFX, setting volume levels, or matching mood to content

Scene-by-scene narration scripts for videos. Use when writing voiceover scripts, adding timing markers, or creating CTA patterns for demos

Compose final demo videos using Remotion. Use when combining terminal recordings with animations, adding branded overlays, or rendering multi-format video exports

Transitional intro cards between video scenes. Use when adding "Coming Up Next" cards, scene transitions, or visual breathing room in demos

Terminal recording for demo videos. Use when recording CLI sessions with VHS or asciinema, simulating Claude Code output, or converting casts to MP4

Thumbnail and first-frame optimization for CTR. Use when designing thumbnails, fixing frame-0 visibility issues, or optimizing for platform requirements

Video rhythm and timing for maximum engagement. Use when planning cut frequency, optimizing retention, or adapting pacing for different platforms

Pre-production planning for tech demo videos. Use when planning scenes, structuring narrative flow, or applying AIDA framework to video content

Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Use when writing ADRs, recording decisions, or evaluating options.

[QUALITY] Assess and rate quality 0-10 with pros/cons analysis. Use when evaluating code, designs, or approaches.

[QUALITY] Assess task complexity with codebase metrics. Use when determining if a task needs breakdown.

Biome 2.0+ linting and formatting for fast, unified code quality. Includes type inference, ESLint migration, CI integration, and 421 lint rules. Use when migrating from ESLint/Prettier or setting up new projects.

[BUILD] Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.

[CONFIG] Configure OrchestKit settings. Use when customizing MCP servers, plugin options, or preferences.

Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.

Multi-directory context patterns for monorepos. Use when working with --add-dir, per-service CLAUDE.md, or separating root vs service context

Enforce 2026 folder structure standards - feature-based organization, max nesting depth, unidirectional imports. Blocks structural violations. Use when creating files or reviewing project architecture.

Use when assessing task complexity, before starting complex tasks, or when stuck after multiple attempts. Provides quality-gates scoring (1-5) and escalation workflows.

5 Whys, Fishbone diagrams, Fault Tree Analysis, and systematic debugging approaches. Use when investigating bugs, analyzing incidents, or identifying root causes of problems.

Use when planning system architecture to ensure nothing is missed. Provides structured questions covering scalability, security, data, and operational dimensions before implementation.

CC 2.1.16 Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.

[GIT] Creates commits with conventional format and validation. Use when committing changes or generating commit messages.

Visualize OrchestKit architecture decisions over time, tracking CC version evolution and best practices adoption. Use when reviewing decisions, understanding rationale, or generating timeline docs.

[QUALITY] OrchestKit doctor for health diagnostics. Use when checking plugin health or troubleshooting issues.

Error pattern analysis and troubleshooting for Claude Code sessions. Use when handling errors, fixing failures, troubleshooting issues.

[EXPLORE] Deep codebase exploration with parallel agents. Use when exploring a repo or discovering architecture.

[CONFIG] Manage OrchestKit feedback system. Use when providing feedback or viewing usage analytics.

[META] OrchestKit skill directory. Use when you want to see available skills or need help.

[BUILD] Full-power feature implementation with parallel subagents. Use when implementing, building, or creating features.

Orchestrate single user-invocable skill across 3 parallel scenarios with synchronized state and progressive difficulty. Use for demos, testing, and progressive validation workflows.

[GIT] PR review with parallel specialized agents. Use when reviewing pull requests or code.

Comprehensive test execution with parallel analysis and coverage reporting. Use when running test suites or troubleshooting failures with the run-tests workflow.

[BUILD] Comprehensive verification with parallel test agents. Use when verifying implementations or validating changes.

[EXPLORE] Coordinate multiple Claude instances across worktrees. Use when managing parallel development.

Core Web Vitals optimization for LCP, INP, CLS with 2026 thresholds, performance budgets, and RUM. Use when improving page performance, diagnosing CWV regressions, or setting performance budgets.

Dashboard UI patterns with widget composition, real-time data updates, responsive grid layouts, and data tables for React applications. Use when building dashboards, widgets, or data tables.

Image optimization with Next.js 16 Image, AVIF/WebP formats, blur placeholders, responsive sizes, and CDN loaders. Use when improving image performance, responsive sizing, or Next.js image pipelines.

Code splitting and lazy loading with React.lazy, Suspense, route-based splitting, intersection observer, and preload strategies for optimal bundle performance. Use when implementing lazy loading or preloading.

Progressive Web App patterns with Workbox 7.x, service worker lifecycle, offline-first strategies, and installability. Use when building PWAs, service workers, or offline support.

Data visualization with Recharts 3.x including responsive charts, custom tooltips, animations, and accessibility for React applications. Use when building charts or dashboards with Recharts.

React render performance patterns including React Compiler integration, memoization strategies, TanStack Virtual, and DevTools profiling. Use when debugging slow renders, optimizing large lists, or reducing unnecessary re-renders.

Responsive design with Container Queries, fluid typography, cqi/cqb units, and mobile-first patterns for React applications. Use when building responsive layouts or container queries.

CSS Scroll-Driven Animations with ScrollTimeline, ViewTimeline, parallax effects, and progressive enhancement for performant scroll effects. Use when implementing scroll-linked animations or parallax.

View Transitions API for smooth page transitions, shared element animations, and SPA/MPA navigation in React applications. Use when adding view transitions or page animations.

Advanced Vite 7+ patterns including Environment API, plugin development, SSR configuration, library mode, and build optimization. Use when customizing build pipelines, creating plugins, or configuring multi-environment builds.

DDD aggregate design patterns for consistency boundaries and invariants. Use when designing aggregate roots, enforcing business invariants, handling cross-aggregate references, or optimizing aggregate size.

Enforces FastAPI Clean Architecture with blocking validation. Use when implementing router-service-repository patterns, enforcing layer separation, or validating dependency injection in backend code.

Backend caching patterns with Redis including write-through, write-behind, cache-aside, and invalidation strategies. Use when implementing Redis cache, managing TTL/expiration, preventing cache stampede, or optimizing cache hit rates.

SOLID principles, hexagonal architecture, ports and adapters, and DDD tactical patterns for maintainable backends. Use when implementing clean architecture, decoupling services, separating domain logic, or creating testable architecture.

CQRS (Command Query Responsibility Segregation) patterns for separating read and write models. Use when optimizing read-heavy systems, implementing event sourcing, or building systems with different read/write scaling requirements.

Domain-Driven Design tactical patterns for complex business domains. Use when modeling entities, value objects, domain services, repositories, or establishing bounded contexts.

Event sourcing patterns for storing state as a sequence of events. Use when implementing event-driven architectures, CQRS, audit trails, or building systems requiring full history reconstruction.

gRPC with Python using grpcio and protobuf for high-performance microservice communication. Use when implementing service-to-service APIs, streaming data, or building polyglot microservices requiring strong typing.

Idempotency patterns for APIs and event handlers. Use when implementing exactly-once semantics, deduplicating requests, or building reliable distributed systems.

Message queue patterns with RabbitMQ, Redis Streams, and Kafka. Use when implementing async communication, pub/sub systems, event-driven microservices, or reliable message delivery.

Transactional outbox pattern for reliable event publishing. Use when implementing atomic writes with event delivery, ensuring exactly-once semantics, or building event-driven microservices.

Saga patterns for distributed transactions with orchestration and choreography approaches. Use when implementing multi-service transactions, handling partial failures, or building systems requiring eventual consistency with compensation.

Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.

LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, debugging with state history, or avoiding re-running expensive operations.

LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.

LangGraph human-in-the-loop patterns. Use when implementing approval workflows, manual review gates, user feedback integration, or interactive agent supervision.

LangGraph parallel execution patterns. Use when implementing fan-out/fan-in workflows, map-reduce over tasks, or running independent agents concurrently.

LangGraph conditional routing patterns. Use when implementing dynamic routing based on state, creating branching workflows, or building retry loops with conditional edges.

LangGraph state management patterns. Use when designing workflow state schemas, using TypedDict vs Pydantic, implementing accumulating state with Annotated operators, or managing shared state across nodes.

LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.

Multi-agent coordination and synthesis patterns. Use when orchestrating multiple specialized agents, implementing fan-out/fan-in workflows, or synthesizing outputs from parallel agents.

Temporal.io workflow orchestration for durable, fault-tolerant distributed applications. Use when implementing long-running workflows, saga patterns, microservice orchestration, or systems requiring exactly-once execution guarantees.

Consumer-driven contract testing with Pact for API compatibility. Use when testing microservice integrations, verifying API contracts, preventing breaking changes, or implementing provider verification.

End-to-end testing with Playwright 1.58+. Use when testing critical user journeys, browser automation, cross-browser testing, AI-assisted test generation, or validating complete application flows.

Integration testing patterns for APIs and components. Use when testing component interactions, API endpoints with test databases, or service layer integration.

Mock Service Worker (MSW) 2.x for API mocking. Use when testing frontend components with network mocking, simulating API errors, or creating deterministic API responses in tests.

Property-based testing with Hypothesis for discovering edge cases automatically. Use when testing invariants, finding boundary conditions, implementing stateful testing, or validating data transformations.

Advanced pytest patterns including custom markers, plugins, hooks, parallel execution, and pytest-xdist. Use when implementing custom test infrastructure, optimizing test execution, or building reusable test utilities.

Test data management with fixtures and factories. Use when creating test data strategies, implementing data factories, managing fixtures, or seeding test databases.

Enforce testing best practices - AAA pattern, naming conventions, isolation, coverage thresholds. Blocks non-compliant tests. Use when writing or reviewing tests.

Unit testing patterns and best practices. Use when writing isolated unit tests, implementing AAA pattern, designing test isolation, or setting coverage targets for business logic.

VCR.py HTTP recording for Python tests. Use when testing Python code making HTTP requests, recording API responses for replay, or creating deterministic tests for external services.

LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.

LLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.

High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.

Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.

Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.

Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.

Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.

Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when designing prompts, improving accuracy, managing prompt lifecycle.

GPT-5/4o, Claude 4.5, Gemini 2.5/3, Grok 4 vision patterns for image analysis, document understanding, and visual QA. Use when implementing image captioning, document/chart analysis, or multi-image comparison.

Advanced RAG with Self-RAG, Corrective-RAG, and knowledge graphs. Use when building agentic RAG pipelines, adaptive retrieval, or query rewriting.

Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.

Text embeddings for semantic search and similarity. Use when converting text to vectors, choosing embedding models, implementing chunking strategies, or building document similarity features.

HyDE (Hypothetical Document Embeddings) for improved semantic retrieval. Use when queries don't match document vocabulary, retrieval quality is poor, or implementing advanced RAG patterns.

CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.

Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid search, semantic + keyword retrieval, vector search optimization, metadata filtering, or choosing between HNSW and IVFFlat indexes.

Query decomposition for multi-concept retrieval. Use when handling complex queries spanning multiple topics, implementing multi-hop retrieval, or improving coverage for compound questions.

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, constructing context from retrieved documents, adding citations, or implementing hybrid search.

Reranking patterns for improving search precision. Use when implementing cross-encoder reranking, LLM-based relevance scoring, or improving retrieval quality in RAG pipelines.

View and manage your personal best practices library with success/failure patterns. Use when viewing best practices, checking patterns, reviewing success/failure history.

Use when deploying to Cloudflare Workers, Vercel Edge, or Deno Deploy. Covers edge middleware, streaming, runtime constraints, and globally distributed low-latency patterns.

GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.

Performance and load testing with k6 and Locust. Use when validating system performance under load, stress testing, identifying bottlenecks, or establishing performance baselines.

GitHub release workflow with semantic versioning, changelogs, and release automation using gh CLI. Use when creating releases, tagging versions, or publishing changelogs.

Slack MCP server integration patterns. Use when setting up team notifications, PR alerts, or CI status updates via Slack bot token

Comprehensive API design patterns for REST, GraphQL, and gRPC. Use when designing APIs, creating endpoints, adding routes, implementing pagination, rate limiting, or authentication patterns.

API versioning strategies including URL path, header, and content negotiation. Use when migrating v1 to v2, handling breaking changes, implementing deprecation or sunset policies, or managing backward compatibility.

RFC 9457 Problem Details for standardized HTTP API error responses. Use when implementing problem details format, structured API errors, error registries, or migrating from RFC 7807.

FastAPI 2026 advanced patterns including lifespan, dependencies, middleware, and Pydantic settings. Use when configuring FastAPI lifespan events, creating dependency injection, building Starlette middleware, or managing async Python services with uvicorn.

API rate limiting with token bucket, sliding window, and Redis distributed patterns. Use when implementing rate limits, throttling requests, handling 429 Too Many Requests, protecting against API abuse, or configuring SlowAPI with Redis.

Strawberry GraphQL library for Python with FastAPI integration, type-safe resolvers, DataLoader patterns, and subscriptions. Use when building GraphQL APIs with Python, implementing real-time features, or creating federated schemas.

Real-time data streaming with SSE, WebSockets, and ReadableStream. Use when implementing streaming responses, real-time data updates, Server-Sent Events, WebSocket setup, live notifications, push updates, or chat server backends.

LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.

Statistical and quality drift detection for LLM applications. Use when monitoring model quality degradation, input distribution shifts, or output pattern changes over time.

Use when completing tasks, code reviews, or deployments to verify work with evidence. Collects test results, build outputs, coverage metrics, and exit codes to prove work is complete.

LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token usage, or implementing prompt versioning.

LLM output evaluation and quality assessment. Use when implementing LLM-as-judge patterns, quality gates for AI outputs, or automated evaluation pipelines.

PII detection and masking for LLM observability. Use when logging prompts/responses, tracing with Langfuse, or protecting sensitive data in production LLM pipelines.

Detect quiet failures in LLM agents - tool skipping, gibberish outputs, infinite loops, and degraded quality. Use when agents appear to work but produce incorrect results.

Reference patterns for parsing skill metadata. Use when extracting phases, examples, or features from SKILL.md files for demo generation

Use this skill when creating or evolving design systems for applications. Provides design token structures, component architecture patterns, documentation templates, and accessibility guidelines. Ensures consistent, scalable, and accessible UI design across products.

Keyboard focus management patterns for accessibility. Covers focus traps, roving tabindex, focus restore, skip links, and FocusScope components for WCAG-compliant interactive widgets. Use when implementing focus traps or keyboard navigation.

Use this skill for internationalization (i18n) in React applications. Covers ALL user-facing strings, date/time handling, locale-aware formatting (useFormatting hook), ICU MessageFormat, Trans component, and RTL/LTR support.

Use this skill for implementing Motion (Framer Motion) animations in React applications. Covers animation presets, page transitions, modal animations, list stagger effects, hover interactions, skeleton loaders, and RTL-aware animation patterns.

User personas, customer journey maps, empathy maps, and experience mapping patterns. Use when synthesizing research into actionable models, understanding user experiences, or aligning teams on customer needs.

Radix UI unstyled accessible primitives for dialogs, popovers, dropdowns, and more. Use when building custom accessible components, understanding shadcn internals, or needing polymorphic composition.

shadcn/ui component patterns including CVA variants, OKLCH theming, cn() utility, and composition. Use when adding shadcn components, building variant systems, or customizing themes.

User interviews, usability testing, surveys, card sorting, and qualitative research methods. Use when gathering user insights, validating designs, or understanding user behavior.

LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, debugging with state history, or avoiding re-running expensive operations.

LangGraph Functional API with @entrypoint and @task decorators. Use when building workflows with the modern LangGraph pattern, enabling parallel execution, persistence, and human-in-the-loop.

LangGraph parallel execution patterns. Use when implementing fan-out/fan-in workflows, map-reduce over tasks, or running independent agents concurrently.

LangGraph conditional routing patterns. Use when implementing dynamic routing based on state, creating branching workflows, or building retry loops with conditional edges.

LangGraph state management patterns. Use when designing workflow state schemas, using TypedDict vs Pydantic, implementing accumulating state with Annotated operators, or managing shared state across nodes.

LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.

ROI, NPV, IRR, payback period, and total cost of ownership analysis for investment decisions. Use when building financial justification for projects, evaluating SaaS investments, or comparing alternatives.

TAM/SAM/SOM market sizing, Porter's Five Forces, competitive analysis, and SWOT frameworks. Use when sizing market opportunities, analyzing competition, or assessing industry dynamics.

OKR framework, KPI trees, leading/lagging indicators, and success metrics patterns. Use when defining goals, measuring outcomes, or building measurement frameworks.

RICE, ICE, WSJF, MoSCoW and other prioritization frameworks for product backlogs. Use when scoring features, ranking initiatives, or deciding what to build next.

Value Proposition Canvas, Jobs-to-be-Done (JTBD), Build/Buy/Partner decisions, and strategic product frameworks. Use when validating value propositions, understanding customer needs, or making strategic technology decisions.

User stories, acceptance criteria, PRDs, and requirements documentation patterns. Use when translating product vision to engineering specs, writing user stories, or creating requirements documents.

SQL and NoSQL schema design with normalization, indexing, and migration patterns. Use when designing database schemas, creating tables, optimizing slow queries, or planning database migrations.

Database version control and change management patterns. Use when managing schema history, coordinating database changes across environments, implementing audit trails, or versioning database objects.

Text embeddings for semantic search and similarity. Use when converting text to vectors, choosing embedding models, implementing chunking strategies, or building document similarity features.

Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid search, semantic + keyword retrieval, vector search optimization, metadata filtering, or choosing between HNSW and IVFFlat indexes.

Test data management with fixtures and factories. Use when creating test data strategies, implementing data factories, managing fixtures, or seeding test databases.

Safe database schema changes without downtime using expand-contract pattern and online schema changes. Use when deploying schema changes to production without service interruption.

Alembic migration patterns for SQLAlchemy 2.0 async. Use when creating database migrations, managing schema versions, handling zero-downtime deployments, or implementing reversible database changes.

Database and HTTP connection pooling patterns for Python async applications. Use when configuring asyncpg pools, aiohttp sessions, or optimizing connection lifecycle in high-concurrency services.

SQL and NoSQL schema design with normalization, indexing, and migration patterns. Use when designing database schemas, creating tables, optimizing slow queries, or planning database migrations.

Database version control and change management patterns. Use when managing schema history, coordinating database changes across environments, implementing audit trails, or versioning database objects.

SQLAlchemy 2.0 async patterns with AsyncSession, async_sessionmaker, and FastAPI integration. Use when implementing async database operations, connection pooling, or async ORM queries.

Safe database schema changes without downtime using expand-contract pattern and online schema changes. Use when deploying schema changes to production without service interruption.

[GIT] Create GitHub pull requests with validation. Use when opening PRs or submitting code for review.

[GIT] Fix GitHub issues with parallel analysis. Use when fixing bugs or resolving issues.

[GIT] Recovery from git mistakes. Use when you need to undo commits, recover branches, or fix history.

Automatic GitHub issue progress updates from commits and sub-task completion. Use when tracking issue progress from commits or automating status updates.

Multi-PR development for large features. Stack dependent PRs, manage rebases, and get faster reviews on smaller changes. Use when creating stacked PRs.

Comprehensive API design patterns for REST, GraphQL, and gRPC. Use when designing APIs, creating endpoints, adding routes, implementing pagination, rate limiting, or authentication patterns.

API versioning strategies including URL path, header, and content negotiation. Use when migrating v1 to v2, handling breaking changes, implementing deprecation or sunset policies, or managing backward compatibility.

RFC 9457 Problem Details for standardized HTTP API error responses. Use when implementing problem details format, structured API errors, error registries, or migrating from RFC 7807.

FastAPI 2026 advanced patterns including lifespan, dependencies, middleware, and Pydantic settings. Use when configuring FastAPI lifespan events, creating dependency injection, building Starlette middleware, or managing async Python services with uvicorn.

API rate limiting with token bucket, sliding window, and Redis distributed patterns. Use when implementing rate limits, throttling requests, handling 429 Too Many Requests, protecting against API abuse, or configuring SlowAPI with Redis.

Real-time data streaming with SSE, WebSockets, and ReadableStream. Use when implementing streaming responses, real-time data updates, Server-Sent Events, WebSocket setup, live notifications, push updates, or chat server backends.

React Hook Form v7 with Zod validation, React 19 useActionState, Server Actions, field arrays, and async validation. Use when building complex forms, validation flows, or server action forms.

React Aria (Adobe) accessible component patterns for building WCAG-compliant interactive UI with hooks. Use when implementing buttons, dialogs, comboboxes, menus, and other accessible components in React applications.

Use when building Next.js 16+ apps with React Server Components. Covers App Router, Cache Components (replacing experimental_ppr), streaming SSR, Server Actions, and React 19 patterns for server-first architecture.

End-to-end type safety with Zod, tRPC, Prisma, and TypeScript 5.7+ patterns. Use when creating Zod schemas, setting up tRPC, validating input, implementing exhaustive switch statements, branded types, or type checking with ty.

Integration testing patterns for APIs and components. Use when testing component interactions, API endpoints with test databases, or service layer integration.

Property-based testing with Hypothesis for discovering edge cases automatically. Use when testing invariants, finding boundary conditions, implementing stateful testing, or validating data transformations.

Advanced pytest patterns including custom markers, plugins, hooks, parallel execution, and pytest-xdist. Use when implementing custom test infrastructure, optimizing test execution, or building reusable test utilities.

Test data management with fixtures and factories. Use when creating test data strategies, implementing data factories, managing fixtures, or seeding test databases.

Enforce testing best practices - AAA pattern, naming conventions, isolation, coverage thresholds. Blocks non-compliant tests. Use when writing or reviewing tests.

Unit testing patterns and best practices. Use when writing isolated unit tests, implementing AAA pattern, designing test isolation, or setting coverage targets for business logic.

LLM guardrails with NeMo, Guardrails AI, and OpenAI. Input/output rails, hallucination prevention, fact-checking, toxicity detection, red-teaming patterns. Use when building LLM guardrails, safety checks, or red-team workflows.

Authentication and authorization patterns. Use when implementing login flows, JWT tokens, session management, password security, OAuth 2.1, Passkeys/WebAuthn, or role-based access control.

Use when building secure AI pipelines or hardening LLM integrations. Defense-in-depth implements 8 validation layers from edge to storage with no single point of failure.

Input validation and sanitization patterns. Use when validating user input, preventing injection attacks, implementing allowlists, or sanitizing HTML/SQL/command inputs.

OWASP Top 10 security vulnerabilities and mitigations. Use when conducting security audits, implementing security controls, or reviewing code for common vulnerabilities.

Automated security scanning for dependencies and code. Use when running npm audit, pip-audit, Semgrep, secret detection, or integrating security checks into CI/CD.

LLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.

Security patterns for LLM integrations including prompt injection defense and hallucination prevention. Use when implementing context separation, validating LLM outputs, or protecting against prompt injection attacks.

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with tool calls.

Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.

Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.

Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when designing prompts, improving accuracy, managing prompt lifecycle.

Enforces FastAPI Clean Architecture with blocking validation. Use when implementing router-service-repository patterns, enforcing layer separation, or validating dependency injection in backend code.

SOLID principles, hexagonal architecture, ports and adapters, and DDD tactical patterns for maintainable backends. Use when implementing clean architecture, decoupling services, separating domain logic, or creating testable architecture.

CQRS (Command Query Responsibility Segregation) patterns for separating read and write models. Use when optimizing read-heavy systems, implementing event sourcing, or building systems with different read/write scaling requirements.

Domain-Driven Design tactical patterns for complex business domains. Use when modeling entities, value objects, domain services, repositories, or establishing bounded contexts.

Event sourcing patterns for storing state as a sequence of events. Use when implementing event-driven architectures, CQRS, audit trails, or building systems requiring full history reconstruction.

Saga patterns for distributed transactions with orchestration and choreography approaches. Use when implementing multi-service transactions, handling partial failures, or building systems requiring eventual consistency with compensation.

Core Web Vitals optimization for LCP, INP, CLS with 2026 thresholds, performance budgets, and RUM. Use when improving page performance, diagnosing CWV regressions, or setting performance budgets.

Image optimization with Next.js 15 Image, AVIF/WebP formats, blur placeholders, responsive sizes, and CDN loaders. Use when improving image performance, responsive sizing, or Next.js image pipelines.

Code splitting and lazy loading with React.lazy, Suspense, route-based splitting, intersection observer, and preload strategies for optimal bundle performance. Use when implementing lazy loading or preloading.

React render performance patterns including React Compiler integration, memoization strategies, TanStack Virtual, and DevTools profiling. Use when debugging slow renders, optimizing large lists, or reducing unnecessary re-renders.

Advanced Vite 7+ patterns including Environment API, plugin development, SSR configuration, library mode, and build optimization. Use when customizing build pipelines, creating plugins, or configuring multi-environment builds.

GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.

Performance and load testing with k6 and Locust. Use when validating system performance under load, stress testing, identifying bottlenecks, or establishing performance baselines.

GitHub release workflow with semantic versioning, changelogs, and release automation using gh CLI. Use when creating releases, tagging versions, or publishing changelogs.

Multi-PR development for large features. Stack dependent PRs, manage rebases, and get faster reviews on smaller changes. Use when creating stacked PRs.

Deep codebase exploration with parallel specialized agents. Use when exploring a repo, finding files, or discovering architecture with the explore agent.

Full-power feature implementation with parallel subagents, skills, and MCPs. Use when implementing features, building features, creating features, or developing features.

Comprehensive PR review with 6-7 parallel specialized agents. Use when reviewing pull requests, checking PRs, code review.

Comprehensive feature verification with parallel analysis agents. Use when verifying implementations, testing changes, validating features, or checking correctness.

LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.

High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.

Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.

GPT-5/4o, Claude 4.5, Gemini 2.5/3, Grok 4 vision patterns for image analysis, document understanding, and visual QA. Use when implementing image captioning, document/chart analysis, or multi-image comparison.

[QUALITY] Add documents to golden dataset with validation. Use when curating test data or saving examples.

Use when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and multi-agent analysis patterns for test data.

Use when backing up, restoring, or validating golden datasets. Prevents data loss and ensures test data integrity for AI/ML evaluation systems.

Use when validating golden dataset quality. Runs schema checks, duplicate detection, and coverage analysis to ensure dataset integrity for AI evaluation.

LLM output evaluation and quality assessment. Use when implementing LLM-as-judge patterns, quality gates for AI outputs, or automated evaluation pipelines.

Vercel agent-browser CLI for headless browser automation. 93% less context than Playwright MCP. Snapshot + refs workflow with @e1 @e2 element references. Use when automating browser tasks, web scraping, form automation, or content capture.

Capture content from JavaScript-rendered pages, login-protected sites, and multi-page documentation using agent-browser CLI. Use when capturing browser content, extracting web data, saving page content.

Advanced MCP patterns for tool composition, resource management, and scaling. Build custom MCP servers, compose tools, manage resources efficiently. Use when composing MCP tools or scaling MCP servers.

MCP security patterns for prompt injection defense, tool poisoning prevention, and permission management. Use when securing MCP servers, validating tool descriptions, implementing allowlists.

Building MCP (Model Context Protocol) servers for Claude extensibility. Use when creating MCP servers, building custom Claude tools, extending Claude with external integrations, or developing tool packages for Claude Desktop.

Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.

LangGraph human-in-the-loop patterns. Use when implementing approval workflows, manual review gates, user feedback integration, or interactive agent supervision.

Multi-agent coordination and synthesis patterns. Use when orchestrating multiple specialized agents, implementing fan-out/fan-in workflows, or synthesizing outputs from parallel agents.

Temporal.io workflow orchestration for durable, fault-tolerant distributed applications. Use when implementing long-running workflows, saga patterns, microservice orchestration, or systems requiring exactly-once execution guarantees.

DDD aggregate design patterns for consistency boundaries and invariants. Use when designing aggregate roots, enforcing business invariants, handling cross-aggregate references, or optimizing aggregate size.

Backend caching patterns with Redis including write-through, write-behind, cache-aside, and invalidation strategies. Use when implementing Redis cache, managing TTL/expiration, preventing cache stampede, or optimizing cache hit rates.

gRPC with Python using grpcio and protobuf for high-performance microservice communication. Use when implementing service-to-service APIs, streaming data, or building polyglot microservices requiring strong typing.

Idempotency patterns for APIs and event handlers. Use when implementing exactly-once semantics, deduplicating requests, or building reliable distributed systems.

Transactional outbox pattern for reliable event publishing. Use when implementing atomic writes with event delivery, ensuring exactly-once semantics, or building event-driven microservices.

Alembic migration patterns for SQLAlchemy 2.0 async. Use when creating database migrations, managing schema versions, handling zero-downtime deployments, or implementing reversible database changes.

Database version control and change management patterns. Use when managing schema history, coordinating database changes across environments, implementing audit trails, or versioning database objects.

Use when deploying to Cloudflare Workers, Vercel Edge, or Deno Deploy. Covers edge middleware, streaming, runtime constraints, and globally distributed low-latency patterns.

Safe database schema changes without downtime using expand-contract pattern and online schema changes. Use when deploying schema changes to production without service interruption.

Dashboard UI patterns with widget composition, real-time data updates, responsive grid layouts, and data tables for React applications. Use when building dashboards, widgets, or data tables.

Progressive Web App patterns with Workbox 7.x, service worker lifecycle, offline-first strategies, and installability. Use when building PWAs, service workers, or offline support.

Responsive design with Container Queries, fluid typography, cqi/cqb units, and mobile-first patterns for React applications. Use when building responsive layouts or container queries.

CSS Scroll-Driven Animations with ScrollTimeline, ViewTimeline, parallax effects, and progressive enhancement for performant scroll effects. Use when implementing scroll-linked animations or parallax.

View Transitions API for smooth page transitions, shared element animations, and SPA/MPA navigation in React applications. Use when adding view transitions or page animations.

Consumer-driven contract testing with Pact for API compatibility. Use when testing microservice integrations, verifying API contracts, preventing breaking changes, or implementing provider verification.

End-to-end testing with Playwright 1.57+. Use when testing critical user journeys, browser automation, cross-browser testing, AI-assisted test generation, or validating complete application flows.

Mock Service Worker (MSW) 2.x for API mocking. Use when testing frontend components with network mocking, simulating API errors, or creating deterministic API responses in tests.

VCR.py HTTP recording for Python tests. Use when testing Python code making HTTP requests, recording API responses for replay, or creating deterministic tests for external services.

Python asyncio patterns with TaskGroup, structured concurrency, and modern 3.11+ features. Use when implementing concurrent operations, async context managers, or high-performance async services.

Advanced Celery patterns including canvas workflows, priority queues, rate limiting, multi-queue routing, and production monitoring. Use when implementing complex task orchestration, task prioritization, or enterprise-grade background processing.

Database and HTTP connection pooling patterns for Python async applications. Use when configuring asyncpg pools, aiohttp sessions, or optimizing connection lifecycle in high-concurrency services.

Distributed locking patterns with Redis and PostgreSQL for coordination across instances. Use when implementing exclusive access, preventing race conditions, or coordinating distributed resources.

Production-grade fault tolerance for distributed systems. Use when implementing circuit breakers, retry with exponential backoff, bulkhead isolation patterns, or building resilience into LLM API integrations.

Advanced RAG with Self-RAG, Corrective-RAG, and knowledge graphs. Use when building agentic RAG pipelines, adaptive retrieval, or query rewriting.

CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.

Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid search, semantic + keyword retrieval, vector search optimization, metadata filtering, or choosing between HNSW and IVFFlat indexes.

Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information across sessions, or when referencing what we discussed last time or in a previous session.

Graph-first memory orchestration - knowledge graph (PRIMARY, always available) with optional mem0 cloud enhancement for semantic search. Use when designing memory orchestration or combining graph and mem0.

Curate and add documents to the golden dataset with multi-agent validation. Use when adding test data, creating golden datasets, saving examples.

Capture content from JavaScript-rendered pages, login-protected sites, and multi-page documentation using agent-browser CLI. Use when capturing browser content, extracting web data, saving page content.

Manage the OrchestKit feedback system that learns from your usage. Use when providing feedback, reporting issues, suggesting improvements.

Manage multiple Claude Code instances across git worktrees. Check status, claim/release file locks, sync decisions, and prevent conflicts. Use when coordinating multiple worktrees or Claude instances.

Automated accessibility testing with axe-core, Playwright, and jest-axe for WCAG compliance. Use when adding or validating a11y tests, running WCAG checks, or auditing UI accessibility.

Keyboard focus management patterns for accessibility. Covers focus traps, roving tabindex, focus restore, skip links, and FocusScope components for WCAG-compliant interactive widgets. Use when implementing focus traps or keyboard navigation.

React Aria (Adobe) accessible component patterns for building WCAG-compliant interactive UI with hooks. Use when implementing buttons, dialogs, comboboxes, menus, and other accessible components in React applications.

WCAG 2.2 AA accessibility compliance patterns for web applications. Use when auditing accessibility or implementing WCAG requirements.