Best practices for writing production Go code. Use when writing, reviewing, or refactoring Go code. Covers error handling, concurrency, naming conventions, testing patterns, performance...
Comprehensive guide to using LLMs throughout the game development lifecycle - from design to implementation to testingUse when "ai game development, llm game dev, claude game, gpt game, ai coding...
Build AI agents using the Azure AI Agents Python SDK (azure-ai-agents). Use when creating agents hosted on Azure AI Foundry with tools (File Search, Code Interpreter, Bing Grounding, Azure AI...
Simplify complex code through the Error Reduction Hierarchy: Define out > Mask > Aggregate > Crash. Use when code is too complex, has scattered error handling, configuration explosion, or callers...
Guide routine design using the Pseudocode Programming Process (PPP). Produce pseudocode design, header comments, and implementation plan. Use when designing routines, stuck on where to start...
Parallel code review using 3 concurrent subagents (3 LLM perspectives: business logic, design/naming, security). Generates merged review report. Use when "review this code/PR", "code review",...
Use when creating or developing, before writing code or implementation
Comprehensive frontend code review skill for React/Vue/Angular applications, focusing on component architecture, HTML/CSS structure, accessibility compliance, and performance optimization. Use...
Route AI coding queries to local LLMs in air-gapped networks. Integrates Serena MCP for semantic code understanding. Use when working offline, with local models (Ollama, LM Studio, Jan,...
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build,...
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build,...
Find failure modes, edge cases, ambiguities, and exploit paths in plans, code, or designs. Use when reviewing proposals, auditing security, stress-testing logic, or validating assumptions.
Runs systematic tests on Claude Code customizations. Executes sample queries, validates responses, generates test reports, and identifies edge cases for agents, commands, skills, and hooks.
Modern file and content search using fd, ripgrep (rg), and fzf. Triggers on: fd, ripgrep, rg, find files, search code, fzf, fuzzy find, search codebase.
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and...
Write comprehensive unit tests for code. Use when asked to (1) write tests for new or existing code, (2) add unit tests, (3) test a function/module/class, (4) verify code still works after...
Expert helper for Terraform and infrastructure-as-code best practices
Build production-grade Laravel REST APIs using opinionated architecture patterns with Laravel best practices. Use when building, scaffoling, or reviewing Laravel APIs with specifications for...
Summarize recent SpecStory AI coding sessions in standup format. Use when the user wants to review sessions from .specstory/history, prepare for standups, track work progress, or understand what...
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained...