I stopped trusting my AI coding agent's "done" — so I built gates

Описание и применение

Автор создал инструмент FlowSkill, который проверяет завершение работы AI‑кодера через механические и семантические ворота, предотвращая «пустые» завершения и обеспечивая надёжные сборки.

Задача

AI coding agents reported "done" without verifying success, leading to broken builds and missing tests.

Результат

FlowSkill prevents hollow completes by requiring mechanical and semantic verification before marking a task as done, reducing debugging overhead and ensuring reliable builds.

Рабочий процесс

• Describe the task to FlowSkill
• Run the AI agent to generate code
• Execute /flow check to run mechanical gates (build, tests, linter)
• If mechanical gates pass, run semantic gate (SKILL.md) to verify task intent
• If any gate fails, log failure to DEBT.md and abort the attempt
• Optionally run /flow doctor for environment checks

Доказательства

My coding agent kept telling me "done." The build was broken. The tests it claimed to pass didn't exist.

Источник

FlowSkill is a small open-source harness that sits between your coding agent and the word "done."

Источник

Two kinds of gates: Mechanical gates (flow.sh) — does it build? Do the tests pass? Does the linter stay quiet?

Источник

Semantic gates (SKILL.md) — does the change actually do what was asked?

Источник

If a gate fails, the attempt dies there and the failure gets logged to DEBT.md — a record of what didn't work, so you stop paying for the same dead ideas twice.

Источник