Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code…
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.
A simulated technical interview for backend developers, based on the candidate’s resume. It asks foundational questions, explores past projects, and includes one system-design exercise.
A code-review checklist for examining current changes file by file. It covers correctness, security, performance, style, and maintainability, then groups findings by severity.
A workflow for running a project’s automated tests and interpreting the results. It selects a test command based on whether the project is Python, Go, Node.js, or Rust.
★not rated 44 2d agoA7 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: