Vibe Code Reviewer — Reviews AI-generated code for the mistakes that sink vibe-coded apps: exposed API keys, missing auth, SQL injection, client-trusted payments. Built for non-engineers — plain-language findings, severity ratings, copy-paste fixes. Catches the security holes behind the "45% of AI code is vulnerable" stat before you ship.
I have spent more than 25 years in programming and web development, with a strong focus on performance, security, and writing lean code that does not waste resources. Good code should be clear, fast, safe, and practical to maintain. That same mindset is what I bring to this skill.
A senior-engineer-style code review assistant: severity-ranked findings, security smell detection, and constructive feedback across 8 language families.
Compare client feedback with your latest draft text. Get a clear revision checklist with source quotes, unresolved conflicts, and version-specific approval status.
Production-grade code quality standards for AI coding agents: no-hacks policy, core values hierarchy, universal clean code principles, language-agnostic pitfalls, multi-stack security checks, and TypeScript-first depth with coverage-gap patterns. Grounded in real production failure modes, with standards and tooling spanning 19 languages.
编程专家.Skill P8级编程助手,覆盖：软件/网站项目总控、API设计、Bug诊断、代码生成、代码审查、重构、测试用例、性能基准、技术选型、文档生成、任务拆解、Spec驱动、Karpathy规范、CMS二次开发、前端设计、MySQL、项目知识图谱。支持 @标识 显式调用跳过路由。
I'll read your final draft the way a hostile but fair referee would—finding the pressure points, specifying the most likely fatal objection, and giving you a clear publication recommendation with the specific revision that would change it. I start by characterizing your argument in my own words so you can check whether I've understood it before you weigh anything else I say. Optionally: tell me the target journal and I'll calibrate to its standards. Not for your peer reviewing commitments.
Guides, a 56-item checklist, a ready PR template, and a fill-in team policy for code review culture. Includes 10 good/bad comment pairs and 30 situational review comments, unified by a blocker/suggestion/nit/question/praise severity system.
粘贴一段git diff，即可获得一份可直接提交评审的Pull Request材料包：结构化的PR描述(概要、改动与原因、测试说明)、风险提示(数据库迁移、API/契约变更、配置改动、删除操作)、把最高风险的改动优先呈现给评审者的"评审关注地图"，以及针对该diff量身定制的自查清单。专为使用Claude Code、Codex等编码智能体开发并提交PR的开发者打造。仅根据你粘贴的diff生成内容，无法判断的地方标注[FILL IN]。无需API密钥，不访问仓库，不涉及个人数据。