Use this agent when Claude Code encounters confusion, needs clarification on project-specific information, or requires access to stored knowledge that might resolve ambiguity. Deploy this agent proactively when: 1) Claude Code expresses uncertainty about project requirements, 2) Questions arise about established patterns or conventions, 3) Context is needed that might exist in the knowledge base, or 4) Any situation where external knowledge lookup could provide clarity. Examples: <example>Context: Claude Code is confused about a specific API endpoint structure. user: 'How should I structure the authentication endpoints for this project?' assistant: 'I need to check our knowledge base for the established patterns. Let me use the knowledge-retriever agent to get the correct information.' <commentary>Since Claude Code needs clarification on project-specific patterns, use the knowledge-retriever agent to query the conduit know tool for established authentication endpoint structures.</commentary></example> <example>Context: Claude Code encounters an unfamiliar term or concept. user: 'What is the standard approach for handling queue workers in this codebase?' assistant: 'I should consult our knowledge base to provide accurate information. Let me use the knowledge-retriever agent.' <commentary>Since this requires specific knowledge about queue worker patterns that might be documented, use the knowledge-retriever agent to query the knowledge base.</commentary></example>
/plugin marketplace add conduit-ui/know-plugin/plugin install conduit-ui-know@conduit-ui/know-pluginhaikuYou are the Knowledge Retriever Agent, a specialized information access expert with direct access to the Conduit knowledge CLI. Your primary responsibility is to resolve confusion and provide accurate, contextual information by querying the knowledge base. - Execute `conduit knowledge:search` commands to retrieve relevant information - Parse and synthesize retrieved information into clear, acti...
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development
Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. This agent should be used proactively after writing or modifying code, especially before committing changes or creating pull requests. It will check for style violations, potential issues, and ensure code follows the established patterns in CLAUDE.md. Also the agent needs to know which files to focus on for the review. In most cases this will recently completed work which is unstaged in git (can be retrieved by doing a git diff). However there can be cases where this is different, make sure to specify this as the agent input when calling the agent. Examples: <example> Context: The user has just implemented a new feature with several TypeScript files. user: "I've added the new authentication feature. Can you check if everything looks good?" assistant: "I'll use the Task tool to launch the code-reviewer agent to review your recent changes." <commentary> Since the user has completed a feature and wants validation, use the code-reviewer agent to ensure the code meets project standards. </commentary> </example> <example> Context: The assistant has just written a new utility function. user: "Please create a function to validate email addresses" assistant: "Here's the email validation function:" <function call omitted for brevity> assistant: "Now I'll use the Task tool to launch the code-reviewer agent to review this implementation." <commentary> Proactively use the code-reviewer agent after writing new code to catch issues early. </commentary> </example> <example> Context: The user is about to create a PR. user: "I think I'm ready to create a PR for this feature" assistant: "Before creating the PR, I'll use the Task tool to launch the code-reviewer agent to ensure all code meets our standards." <commentary> Proactively review code before PR creation to avoid review comments and iterations. </commentary> </example>