Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Junliu1066/vibe-coding-kit --skill vibe-coding-requirementsgit clone --depth 1 https://github.com/Junliu1066/vibe-coding-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/junliu1066/vibe-coding-kit/vibe-coding-requirements)<a href="https://agentmods.dev/skills/junliu1066/vibe-coding-kit/vibe-coding-requirements"><img src="https://agentmods.dev/badge/skills/junliu1066/vibe-coding-kit/vibe-coding-requirements/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/junliu1066/vibe-coding-kit/vibe-coding-requirements"><img src="https://agentmods.dev/badge/skills/junliu1066/vibe-coding-kit/vibe-coding-requirements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00249 | $0.05091 |
| Opus 5.5 | $0.00100 | $0.02036 |
| Sonnet 5.5 | $0.00050 | $0.01018 |
| Haiku 4.5 | $0.00025 | $0.00509 |
Grade A, and why
vibe-coding-requirements scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求对齐：把想法说成 AI 能落地的需求
这是 vibe-coding-kit 的入口 Skill。它服务的人多半不写代码，靠 AI 把想法变成能跑的东西。最容易踩的坑不是技术，而是需求没说清，AI 朝着错误方向飞速实现。把需求说对，后面省一半返工。
套件里还有三个 Skill，在不同时刻用：
- 需要选技术栈 / 看不懂 AI 给的方案 →
vibe-coding-architecture- demo 验证过了、要做成正式系统 →
vibe-coding-production- 开发中 AI 越改越乱 / 改坏退不回去 / AI 忘事 →
vibe-coding-survival（开发全程都建议配合它）
先确认：用户现在在哪一站？
| 用户想要 | 怎么办 |
|---|---|
| 还不确定要不要做 | 先做阶段零，可能根本不用写代码 |
| 快速跑个 demo 验证想法 | 阶段零 + 阶段一，需求说清就开干，其余先不管 |
| demo 过了，要做成正式系统 | 做完本 Skill，转 vibe-coding-architecture 和 vibe-coding-production |
| 已经在做、过程中失控 | 转 vibe-coding-survival |
判断方法：直接问。"你现在是想先跑个 demo 看看效果，还是打算做一个要长期运行、可能给别人用的正式系统？"
开问之前：先分诊，能推断的别问 ★
账本（流程状态）： 本 skill 是流程第一阶段 S1·需求对齐的"自助路径"（访谈式入口是
vibe-coding-prd，两者满足同一个 S1）。开始前读一下docs/进度账本.md（不存在就照examples/进度账本-模板.md建一个，初始化到 S1）；这里的"分诊"结论就是账本里 S1.1 的轻/重判定，产出"需求基准描述"对应 S1 的核心退出条件。轻量 demo 不必逐步报门，但别跳过分诊和四要素。
新手最容易把对齐做成"审问"——一口气抛十几个问题，用户答到一半就烦了。好的需求对齐，问得少而准。 在准备每一个问题前，先过这条原则：
能自己（或从用户已经说的话）推断出来的，就别问；只把真需要用户拍板的留成问题。
具体两步：
- 先分诊，定深度。 用一句话判断这个需求的"分量"，深度随风险走：
- 轻（自己用、一次性、跑个 demo）→ 只问最关键的一两件事，快速进入"补全"。
- 重（要给别人用、要长期运行、一旦出错有代价）→ 四要素逐项问，再做"数据旅程"深扫。
- 能推断的，转成"推荐项"让用户一眼确认，而不是开放式问题。 比如用户说"帮我整理电脑里的图片"，你不必问"你用什么设备、要不要联网"——直接推断"本机运行、不联网、单文件脚本"，作为推荐默认值摆出来，用户点头或否决即可（见下方「推荐选项」写法）。
这一步把"深度自适应"落到实处：简单需求轻问快走，复杂需求才展开深问。
推荐选项写法：别让用户面对空白，也别替他做主
非技术用户最怕两件事：一是被一堆开放式问题问懵（"你想用什么技术？"——他哪知道），二是 AI 自作主张、闷头跑偏。正确的中间地带是：先把你的理解和默认假设讲出来，每条都做成"一眼能确认"的推荐项，用户点头或换一个即可。
固定结构（卡住时直接照搬）：
我先把需求理解一下，下面这些是我替你定的默认值（不对就直接说，我改）：
1. 谁在用：自己一个人用 [✓ 就这样] [换一个：给同事/给客户…]
2. 它活在哪：本机双击运行的小脚本 [✓ 就这样] [换一个：网页/常开服务器…]
3. 数据存哪：结果直接写回原文件夹 [✓ 就这样] [换一个：要长期保存/要数据库…]
4. 成本：不调用任何要花钱的服务 [✓ 就这样] [换一个：可以接受 AI 接口按量计费]
（最多 5 条，每条一句话。你不回，我就按这些往下走。）
- 每条假设 = 一道带推荐值的选择题，而不是空白填空。
- 默认值一律取最简可行那个（最省钱、最少依赖、最好维护）。
- 用户沉默 = 默认通过，但关键的、一旦定错代价大的（涉及钱、别人的数据、是否长期运行）必须等他明确点头。
这正是本套件"你有权说不""渐进式复杂度"两条信条的默认动作：不审问、不擅自做主，用推荐项把决定权轻轻交还给用户。
阶段零：先别急着写代码
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 252 lines · 249 tokens per session scan A 7eafd7772b12
vibe-coding-requirements is a skill published in the GitHub repository Junliu1066/vibe-coding-kit (99 stars, last pushed 3mo ago), licensed MIT. It adds 249 tokens to every session and 5,091 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
postgres
Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations. Trigger when user asks to: Explore an existing PostgreSQL database to understand its objects and relationships Design or modify PostgreSQL tables…
no-code-app
Use when building an app on a no-code/low-code platform (Bubble, Softr, Glide over Airtable or Xano) — picking the platform, modeling the data, keeping usage-metered cost predictable, and planning the exit before lock-in. NOT a hand-written coded app (that is nextjs), NOT wiring SaaS tools together with no app UI…
postcss-best-practices
PostCSS best practices and configuration guidelines for modern CSS processing and optimization.
autogen-development
Expert guidance for Microsoft AutoGen multi-agent framework development including agent creation, conversations, tool integration, and orchestration patterns.
cloudflare-development
Cloudflare Workers, Pages, KV, D1, R2, and Durable Objects development best practices for edge computing applications.
grpc-development
Best practices for building high-performance services with gRPC and Protocol Buffers. Use when designing RPC services, defining protobuf schemas, implementing streaming APIs, setting up gRPC interceptors, or building cross-language service communication.