Building products
with AI.

Claude Code가 토큰을 낭비하고 있었다. 코드 한 줄 안 쓰고 3주 만에 고쳤다.

Claude Code Is Wasting Your Tokens. I Fixed It in 3 Weeks Without Writing a Single Line of Code.

1,056 tests. 102 benchmarks. 60-90% token savings. Built entirely by Claude Code agents.

agency-agents: 120 AI Specialist Personas That Prove Prompts Need Personality, Not Just Instructions

A 31k-star collection of AI agent definitions with unique personalities, workflows, and success metrics across 12 divisions. The next evolution beyond 'Act as a developer.'

impeccable: Why Every AI-Generated UI Looks the Same, and 17 Commands to Fix It

A skill pack that fights the 'generic trap' in LLM-generated frontends. Anti-patterns, 7 domain references, and 17 steering commands for Claude Code, Cursor, and Gemini CLI.