Stop Being Your Agent's QA: A Skill That Makes AI Coding Agents Prove Their Work

Every AI coding session ends the same way: the agent says "Done ✓" - and you spend the next 30 minutes manually clicking through everything to find out it isn't. I got tired of being my agent's test suite. So I built stop-manual-testing - a skill that flips the loop: every task ends with machine-checkable criteria the agent must actually run and pass before it's allowed to say "done". How it works - Every task ends with a verification list the agent can execute itself: commands, checks, expected outputs - If a check can't be automated, the skill tells you exactly what to verify by hand - and why - The agent converges in a closed loop instead of handing you "Done ✓" and hoping for the best It's modular, checks can run in parallel, and it works across agent-driven workflows. Kaiji-Z / stop-manual-testing Stop manually testing your AI agent. A skill that builds a machine-checkable verification system so the agent self-verifies and converges in a closed loop. | 让 AI agent 自己搭机器可判定的验证体系,在闭环里自己收敛,停止手动测试。 stop-manual-testing A skill that stops you from manually testing your AI agent. The agent reads it, builds a machine-checkable verification system, and self-converges in a closed loop - collapsing the ~90% of dev time you spend staring at runs and judging by gut feel. 中文 · English English A skill for AI coding agents (Claude Code / Codex / ZCode / Cursor). Load it once, and instead of you manually clicking through the UI and eyeballing whether the agent "got better or worse this run," the agent builds itself a verification system where correctness is machine-checkable - then iterates inside a closed loop until it converges. The pain it solves If you develop AI agents, you are likely stuck here: - ~90% of your time goes to manual testing - opening the web page, typing inputs, watching the agent step by step, judging with your own brain whether it got better… If you're spending more time reviewing your agent's work than actually creating, give it a try - feedback welcome. Top comments (0)