# Waza

A collection of Claude Code and Codex skills that package common engineering habits, such as planning, UI iteration, release review, and debugging, into runnable playbooks.

Waza turns everyday engineering habits into installed skills that an agent runs as slash commands. Included skills cover pressure-testing a design into a plan before building, iterating on frontend UI with screenshot-driven review, checking a diff against project constraints before merge, systematic root-cause debugging, rewriting prose to read naturally, a staged research workflow for an unfamiliar domain, summarizing a URL or PDF, and auditing agent health across a project's instructions and verifier output.

Each skill is a folder containing reference docs, helper scripts, and notes from real failures. It installs into a shared skills directory so Claude Code, Codex, Cursor, Gemini CLI, Copilot, and other agents that read that directory can all use the same skills, or as a host-specific plugin.

Waza is written in Python and distributed under the MIT license.

Website: https://github.com/tw93/Waza