The AI tools I use daily — and how.
Four complementary tools: Claude Code (Anthropic) for orchestration, Superpowers (Jesse Vincent) for discipline, RTK (rtk-ai) to trim shell output, monitor-ccu (tiber76) to track cost. Credit for the design and implementation goes entirely to the original authors — I'm just a user.
Claude Code
by Anthropic
The CLI agent from Anthropic that walks alongside me every day. This article is a usage report — credit for the tool goes entirely to Anthropic.
Read article →Superpowers
by Jesse Vincent (obra)
The kit of skills, sub-agents and commands by Jesse Vincent that turns Claude Code from a generalist agent into a disciplined team. Full credit to the author — I'm just a user.
Read article →Claude Design
by Anthropic
Anthropic's AI design workshop. A hands-on retrospective: how Claude Design produced a complete design brief in one pass for Vite Fait, Bien Fait, and how I shipped it across 4 PRs.
Read article →huashu-design
by 花叔 / @AlchainHust
An open-source Claude Code skill that ships HTML, PPTX and MP4 directly — a community alternative to Claude Design. On my radar, not used yet.
Read article →open-design
by nexu-io
Open-source alternative to Claude Design: a local daemon that drives the coding agent CLI you already have (Claude Code, Cursor, Gemini, Copilot…), with 31 skills, 72 design systems and HTML/PDF/PPTX exports. On my radar, not tried yet.
Read article →RTK — Rust Token Killer
by rtk-ai
A CLI proxy written in Rust that filters command output before it reaches Claude. Designed and maintained by rtk-ai — I'm just a grateful user.
Read article →monitor-ccu
by tiber76
A local dashboard that reads Claude Code session files and shows you where your tokens go. Designed and maintained by tiber76 — I'm just a grateful user.
Read article →Claude Code AI Virtual Staff
by tiber76
A virtual team of 13 agents (product, tech, design, QA, security, growth…) you can plug into Claude Code or OpenAI Codex. An alternative to Superpowers for those who want to keep control over every skill and arbitrate inter-agent friction themselves. Article in 'good to know' mode — I don't use this tool daily, full credit goes to tiber76.
Read article →The prompt that bootstraps a project
by Alexandre Quinche
How to write a context prompt that makes the agent autonomous, secures decisions and saves tokens. Practical guide with an example applied to this project.
Read article →