I Tried TDD With an AI Assistant and It Caught a Bug
Test-driven development with AI sounds like extra work. I spent a weekend building an auth module test-first and found a security bug my normal workflow missed.
Ultra-compressed response mode for AI coding assistants — cuts output tokens by ~75% while keeping technical accuracy, ~3x faster
Makes Claude Code produce distinctive frontend interfaces by rejecting generic AI aesthetics and demanding a clear creative direction for every project
Matt Pocock’s skill for finding deep architectural improvements in your codebase based on domain language and ADRs
Official Remotion Agent Skill — teaches your AI assistant the best practices for writing videos with React, from animation and subtitles to 3D and transitions
A methodical debugging framework that isolates root causes through hypothesis-driven investigation and targeted fixes for complex software issues
Vercel Labs
64 performance rules for React and Next.js from Vercel’s team. Install it in Claude Code and the AI writes code that follows Vercel conventions automatically.
Vercel’s official web design best practices covering responsive layouts, accessibility, performance, and component architecture
Test-driven development with AI sounds like extra work. I spent a weekend building an auth module test-first and found a security bug my normal workflow missed.
Search the open agent skill registry with find-skills, discover new capabilities, and install them — all from your terminal. No browser needed.
Create, test, and publish your own AI agent skills. Step-by-step guide covering skill structure, triggers, quality checks, and installation.
Build a Model Context Protocol server from scratch. Step-by-step guide covering setup, tool definitions, and configuration for Claude Code and Cursor.
AI-generated code can hide bugs in unexpected places. I used a systematic debugging methodology to find a root cause that had stumped me for hours.