Create and update ai-context.md files that document modules for AI assistants. Use when adding documentation for packages, apps, or external references that should be discoverable via /modules commands.

Architectural dependency analysis and impact assessment. Use for: (1) Blast radius - who depends on a service, what breaks if I change it; (2) Dependency tree - what does a service depend on (ancestors/upstream); (3) Root cause analysis - find shared dependencies when multiple services fail; (4) Architecture metrics - coupling (density), depth (diameter), connectivity; (5) Domain discovery - identify module boundaries via cut vertices; (6) Hot services - critical infrastructure with many dependents; (7) Impact assessment before changes; (8) Debugging cascading failures; (9) Identifying god services, tight coupling, deep hierarchies. Provides graph-based analysis via CLI commands: analyze, blast-radius, ancestors, common-ancestors, metrics, domains, hot-services. All agents can use this for architectural questions.

Implement reactive state management with Effect Atom for React applications

Execute system commands and manage processes using Effect's ChildProcess module from effect/unstable/process. Use this skill when spawning child processes, running shell commands, capturing command output, or managing long-running processes with cleanup.

Decide between Context Tag witness and capability patterns for dependency injection, understanding coupling trade-offs

> Efficient patterns for finding files and content in the beep-effect codebase.

Generate comprehensive predicates and orders for domain types using typeclass patterns

Complete feature development with validation, documentation updates, and git workflow. Use when finishing a feature (equivalent to /done-feature in Claude/Codex).

Build type-safe command-line applications with Effect's unstable CLI module for argument parsing, validation, and dependency injection.

Master the Effect AI LanguageModel service for text generation, structured output, streaming, and tool calling. Use when working with LLM interactions, schema-validated responses, or building conversational AI systems.

Build prompts for Effect AI using messages, parts, and composition operators. Covers the complete Prompt API for constructing, merging, and manipulating conversations with language models.

Configure and compose AI provider layers using @effect/ai packages. Covers Anthropic, OpenAI, OpenRouter, Google, and Amazon Bedrock providers with config management, model abstraction, and runtime overrides for language model integration.

Define and implement AI tools using @effect/ai's Tool and Toolkit APIs. Use when building LLM integrations with type-safe tool definitions, parameter validation, and handler implementations. Covers user-defined tools, provider-defined tools, and toolkit composition.

Test Effect concurrency primitives including PubSub, Deferred, Latch, Fiber coordination, SubscriptionRef, and Stream. Use this skill when testing concurrent effects, event-driven systems, or fiber coordination.

Replacing native Array, Object, String, and Number methods with Effect modules. Trigger on: data transformation, collection operations, array/object manipulation, string processing, pipe/flow composition.

Replacing try/catch, null/undefined, and if/else with Effect patterns. Trigger on: error handling, null checks, Option, Match, TaggedErrorClass, try/catch replacement.

Canonical Effect-first development guide for this repo. Trigger on: new features, refactors, bug fixes, API boundaries, typed errors, Option usage, schema decoding, service wiring, and test authoring.

Creating services with ServiceMap.Service, IdentityComposer keys, and Layer composition. Trigger on: new service, service definition, Layer wiring, dependency injection, ServiceMap.

Write comprehensive tests using @effect/vitest for Effect code and vitest for pure functions. Use this skill when implementing tests for Effect-based applications, including services, layers, time-dependent effects, error handling, and property-based testing.

Focused Effect v4 error handling. Use for replacing catchAll patterns, designing typed errors, and Option/Match boundary handling.