Rohan Paul@rohanpaul_ai · XGitHub亲自下场推spec-driven开发，把vibe coding的随意感压回“先写规约再写代码”的老派流程，但这次规约是给AI读的，做coding agent的团队应该认真研究一下。
GitHub 发布开源工具包 Spec Kit，旨在解决 "vibe coding" 的最大弱点——AI 常在规则未明确时就开始编码。它把流程从 "让 AI 直接构建" 改为 "先写产品规范，再让 AI 根据规范实现"。当前 AI 编码模式常因松散提示直接跳入代码，导致需求薄弱、边界遗漏和反复返工。Spec Kit 推动反向流程：先定义产品功能，再澄清差距、制订技术计划、分解任务，最后让 agent 执行。规范成为可执行的开发合约，支持 Copilot、Claude Code、Codex、Gemini、Cursor、Qwen 等 30+ agent 集成。项目已获 109K+ 星标。
GitHub released Spec Kit， an open-source toolkit to fix vibe coding's biggest weakness： the AI often starts coding before the product rules are clear.
109K+ stars ⭐️
It turns vibe coding from "ask the AI to build it" into "write the product spec first， then make the AI build from that spec."
Most AI coding today starts with a loose prompt， then jumps straight into code， which often produces working demos but weak requirements， missing edge cases， and messy rework.
Spec Kit pushes the process the other way： first define what the product must do， then clarify gaps， then create a technical plan， then break that plan into tasks， then let the agent implement against those written artifacts.
So here the spec is no longer disposable documentation； it becomes an executable development contract that guides Copilot， Claude Code， Codex， Gemini， Cursor， Qwen， and 30+ other agent integrations.