superpowers

Deprecated - use the superpowers:brainstorming skill instead

do general code cleanup

Deprecated - use the superpowers:executing-plans skill instead

run and fix tests

find and implement low hanging fruits

Use this agent when the user wants to create a new agent configuration or needs help designing a custom agent. This agent guides users through a structured discovery process to build high-quality agent specifications. Examples: - User: "I need to create an agent that helps me write better commit messages" Assistant: "I'm going to use the Task tool to launch the agent-prompt-wizard to guide you through creating this agent configuration through a series of clarifying questions." - User: "Can you help me design an agent for reviewing my German-language Zettelkasten notes?" Assistant: "Let me use the agent-prompt-wizard to work with you on designing this specialized agent through structured questions." - User: "I want to make an agent but I'm not sure how to specify what it should do" Assistant: "Perfect - I'll use the agent-prompt-wizard which will ask you targeted questions to help clarify and design your agent."

Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Great work! Now let me use the code-reviewer agent to review the implementation against our plan and coding standards" <commentary>Since a major project step has been completed, use the code-reviewer agent to validate the work against the plan and identify any issues.</commentary></example> <example>Context: User has completed a significant feature implementation. user: "The API endpoints for the task management system are now complete - that covers step 2 from our architecture document" assistant: "Excellent! Let me have the code-reviewer agent examine this implementation to ensure it aligns with our plan and follows best practices" <commentary>A numbered step from the planning document has been completed, so the code-reviewer agent should review the work.</commentary></example>

Use this agent when the user needs to create, modify, or review Elixir, Phoenix, or Phoenix LiveView code. This includes: - Writing backend business logic in contexts (e.g., Accounts, Fulfilment, Warehouse) - Creating or modifying Phoenix LiveView modules - Implementing database schemas, migrations, and queries with Ecto - Setting up routes, controllers, and LiveView sessions - Working with PubSub, GenServers, or other Elixir/OTP patterns - Reviewing backend code for idiomatic Elixir patterns and anti-patterns - Implementing authentication, authorization, or session management - Creating background jobs with Oban - Writing backend tests with ExUnit Examples: Example 1: user: "I need to create a new LiveView for managing warehouse terminals with CRUD operations" assistant: "I'll use the phoenix-backend-dev agent to implement the Terminal LiveView with proper Phoenix patterns and core components." <The assistant would then launch this agent to handle the task> Example 2: user: "Can you review this Fulfilment context module I just wrote? I want to make sure it follows Elixir best practices" assistant: "Let me use the phoenix-backend-dev agent to review your code for idiomatic patterns and potential anti-patterns." <The assistant would then launch this agent to review the code> Example 3: user: "I've just implemented a new order allocation function. Here's the code: [code snippet]" assistant: "I'll use the phoenix-backend-dev agent to review this implementation for Elixir best practices and Phoenix patterns." <The assistant would then launch this agent proactively to review the newly written code> Example 4: user: "Create a new schema for tracking inventory movements with proper Ecto associations" assistant: "I'll launch the phoenix-backend-dev agent to create the schema following Phoenix conventions and Ecto best practices." <The assistant would then launch this agent to handle the schema creation>

You are a specialized agent that helps users write effective prompts for AI systems, particularly Claude.

Use this agent when working with React Three Fiber (R3F) and/or Jotai state management. This includes:

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when asked to clean up code, or after introducing a new larger feature. Identifies bad patterns, fix warnings.

Use this when writing any kind of UI components in any language (heex, react, web components, and so on). Helps with making them composable and flexible.

Use when user explicitly mentions 'deep work' or signals substantial work ('let's build/implement X'). Sets session preferences upfront to enable autonomous execution. If uncertain, ask: 'Deep Work session or interactive style?'

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

1 hook across 1 event