GitHub Spec Kit brings specification-driven discipline to AI coding
掘金 describes GitHub Spec Kit as a specification-driven development toolkit that moves AI coding through constitution, specification, plan, tasks, implementation, and convergence stages. Its clarify stage asks about ambiguous requirements, while converge compares generated code with the specification and appends tasks for uncovered gaps; in one reported CLI todo test, this process found an unhandled corrupted-file case despite 14 passing tests. The toolkit supports more than 20 coding agents, including Claude Code, GitHub Copilot, Codex, Gemini CLI, Cursor, Cline, opencode, Qwen Code, Kiro CLI, and Zed.
Spec Kit gives AI coding agents a structured way to preserve requirements, expose ambiguity, and check generated code against explicit specifications, which is particularly relevant to multi-agent and production feature development.
@[toc]
一、先说痛点：AI 写代码翻车，八成翻在需求传递上
后端同学大概率经历过的场景。
你跟 AI 说："帮我加个退款接口。"
它唰唰唰生成一整套 controller、service、异常处理，编译能过、测试能过、跑起来也没毛病。上线第二天运营来找你：用户把已经发货的订单也退了。
代码没 bug。坑出在那句 prompt 里压根没提"发货状态"这四个字。
#GitHub Spec Kit#Claude Code#GitHub Copilot#Codex#Gemini CLI#Cursor#Cline#opencode#Qwen Code#Kiro CLI#Zed