aichemist

Codebase exploration specialist for mapping patterns and architecture before implementation. Use this agent when you need to understand an area of the codebase before making changes — finding similar features, tracing data flow, or identifying extension points. <example> Context: Starting a new ticket and need to understand existing patterns. user: "Find how similar features are implemented before we start." assistant: "I'll use the code-explorer-agent to trace existing patterns and return the key files." </example> <example> Context: Need to understand the architecture of an area before touching it. user: "Map the architecture around the payment flow." assistant: "I'll use the code-explorer-agent to identify entry points, data flow, and extension points." </example> <example> Context: Need to trace how a request moves through the backend before adding a new endpoint. user: "I need to understand how API requests flow through the system before I add a new one." assistant: "I'll use the code-explorer-agent to map the request path — entry point, middleware, handlers, and persistence — and return the key files." </example>

Expert code reviewer providing thorough, constructive feedback on code quality, security, and best practices. Use this agent PROACTIVELY when the user asks for feedback on code, wants a second opinion, or when reviewing changes before committing. <example> Context: User has written code and wants feedback. user: "Can you review this function I just wrote?" assistant: "I'll use the Code Review Agent to review this for correctness, security, and best practices." </example> <example> Context: User is about to commit or push changes. user: "I think this is ready to commit, anything I should check?" assistant: "I'll use the Code Review Agent to do a quick review before you commit." </example> <example> Context: User is unsure about code quality or patterns. user: "Is this the right way to handle this error?" assistant: "I'll use the Code Review Agent to evaluate the error handling approach." </example>

Domain-Driven Design expert for strategic modeling guidance, tactical pattern review, and design discussions. Use this agent PROACTIVELY when you encounter domain modeling questions, aggregate design, or code that deals with entities, value objects, and bounded contexts. <example> Context: User is designing a new feature that involves business rules and data consistency. user: "I need to add an order cancellation feature. Orders can only be cancelled if they haven't shipped yet." assistant: "I'll use the DDD Agent to help design this - the cancellation rule is a domain invariant that should be enforced by the Order aggregate." </example> <example> Context: User is reviewing code that has entities with public setters. user: "Here's my Order class, does this look right?" assistant: "I'll use the DDD Agent to review this. I notice the Order class has public setters which could allow invariants to be bypassed." </example> <example> Context: User asks about relationships between domain objects. user: "Should Order hold a reference to Customer or just the CustomerId?" assistant: "I'll use the DDD Agent - this is a key aggregate boundary question." </example>

Expert .NET software engineer for building, debugging, and optimizing .NET applications. Use this agent PROACTIVELY when working with C#, F#, .NET projects, or when the user needs help with async patterns, SOLID principles, testing, or .NET-specific APIs. <example> Context: User is working on a C# file or .NET project. user: "Can you help me implement this API endpoint?" assistant: "I'll use the .NET Coding Agent to implement this endpoint following ASP.NET Core best practices." </example> <example> Context: User encounters a .NET-specific issue or error. user: "I'm getting a deadlock with my async code." assistant: "I'll use the .NET Coding Agent to analyze the async pattern - this is likely a sync-over-async issue." </example> <example> Context: User asks about .NET testing or architecture. user: "How should I structure the tests for this service?" assistant: "I'll use the .NET Coding Agent to design the test structure using xUnit and proper mocking patterns." </example> <example> Context: User needs to implement error handling or validation. user: "What's the best way to handle errors in this method?" assistant: "I'll use the .NET Coding Agent - I'll suggest using FluentResults or a Result pattern instead of exceptions for control flow." </example>

Expert code simplifier that refines recently modified code for clarity, consistency, and maintainability while preserving exact functionality. Use this agent PROACTIVELY when the user asks to simplify, tighten, or clean up code, or when a code-writing task produces a diff worth reviewing for clarity before handoff. <example> Context: User has just finished implementing a feature and the diff contains nested conditionals. user: "I added the retry logic — does this look OK?" assistant: "I'll use the simplify agent to tighten the nesting and check it against our project conventions before you commit." </example> <example> Context: User explicitly asks for a clarity pass on recently edited code. user: "Can you tighten up this method? It feels noisier than it should." assistant: "I'll use the simplify agent — it'll flag unnecessary nesting, dead code, and redundant abstractions while keeping behavior intact." </example> <example> Context: A parent agent has completed a code-writing task and wants a clarity review before handoff. user: "Done implementing the feature — what does the final diff look like?" assistant: "Before summarizing, I'll delegate to simplify-agent to check the diff against our simplification rules and apply any tightening." </example> <example> Context: Language-specific cleanup — the agent defers to the stack agent for opinions. user: "This C# method handles errors with try/catch for flow control. Can it be cleaner?" assistant: "I'll use the simplify agent, which will consult dotnet-agent for the .NET-specific guidance (FluentResults over exceptions) while applying our universal simplification rules." </example>

This skill should be used when the user asks to "track tasks with beads", "use bd", "add a beads task", "show ready tasks", "claim a task", "list bd tasks", "create a bd issue", "show my tasks", "what's ready to work on", "update task status", or mentions beads task IDs like "bd-a1b2". Provides beads (bd) integration for AI-native task tracking with automatic sidecar storage outside the repo by default.

Use this BEFORE any creative work — creating features, building components, adding functionality, or modifying existing behavior. Explores user intent, requirements, and design through structured dialogue before any implementation begins. Trigger phrases: "I want to build", "let's add", "how should I implement", "I'm thinking of", "new feature", "let's create", "design this", "help me plan", "should I use X or Y".

This skill should be used when the user asks about "my calendar", "what's on my schedule", "what meetings do I have", "what's today's agenda", "what's coming up this week", "next meeting", "prepare me for my next meeting", "meeting prep", "brief me on", "briefing for", or asks about specific calendar events. Provides Microsoft 365 calendar integration via the m365 CLI.

This skill should be used when the user asks to "capture this", "save this to obsidian", "add to obsidian", "quick capture", "capture to vault", "capture this thought", "capture this insight", "capture this code", "save this insight", "jot this down", or wants to save a thought, snippet, or note to Obsidian without interrupting their workflow.

This skill should be used when the user asks to "review my code", "do a code review", "review this PR", "review this pull request", "check my changes", "review changes against main", "review against develop", "post review comments", "review and comment on PR", "code review with Jira context", "review my branch", or asks for a review with specific options like "with --comment", "against base branch". Provides comprehensive code review using parallel specialized agents, confidence-based filtering, Jira integration, and optional inline PR comments.

5 hooks across 3 events