CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness
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_0.38.7 — Waza azd Extension v0.38.7 · 19 Aug 2026
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.
.github/copilot-instructions.md C 1,232 tok AGENTS.md A 2,359 tok .copilot/skills/agent-collaboration/SKILL.md A 22 tok .copilot/skills/error-recovery/SKILL.md A 24 tok .copilot/skills/git-workflow/SKILL.md C 16 tok .copilot/skills/reviewer-protocol/SKILL.md A 13 tok .copilot/skills/secret-handling/SKILL.md A 19 tok .copilot/skills/session-recovery/SKILL.md A 16 tok .copilot/skills/squad-commands/SKILL.md A 34 tok .copilot/skills/squad-conventions/SKILL.md A 15 tok .copilot/skills/squad-version-check/SKILL.md A — .copilot/skills/test-discipline/SKILL.md A 12 tok .github/skills/azd-publish/SKILL.md A 94 tok .github/agents/squad.agent.md A 23 tok