Back to directory

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

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.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.