microsoft/waza

CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness

About the project

microsoft/waza is a Go command-line tool for building and evaluating AI agent skills through test suites, benchmarks, and model comparisons. It is for developers who need to measure and improve how reliably agent skills work. The catalogue entries are Waza's own skills, instructions, agent, and MCP integration.

Latest release azd-ext-microsoft-azd-waza_0.39.0 — Waza azd Extension v0.39.0 · 20 Oct 2026

24 files for Claude Code, Codex, GitHub Copilot and OpenCode: agent-collaboration, error-recovery, git-workflow, reviewer-protocol and 20 more — 8,659 tokens loaded in every session.

1,424Stars on the repository
24Files it configures its agents with
8,659Tokens loaded in every session
4Agents configured

Instructions

Skills

Agents

These files are microsoft/waza's own configuration — they tell Claude Code, Codex, GitHub Copilot and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.