vibe-coding-prd

vibe-coding-prd is a skill for Claude Code, Codex from Junliu1066/vibe-coding-kit. It costs 273 tokens per session (5,313 once invoked), scanned A, original, MIT.

An interview-style requirements assistant that turns an unclear product idea into a practical product requirements document, or PRD. A PRD explains what a product should do well enough for development to begin.

In plain words
What is it for?
Use it to define constraints, choose a product form and technology direction, track interview progress, and create prd.md and 项目说明书.md files.
Why use it?
It helps people clarify an idea without having to answer a large form all at once, especially when they are unsure about the product shape or technology choices.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

Good fit Use it to define constraints, choose a product form and technology direction, track interview progress, and create prd.md and 项目说明书.md files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/junliu1066/vibe-coding-kit/vibe-coding-prd
Install

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.

Any agent
npx skills add Junliu1066/vibe-coding-kit --skill vibe-coding-prd
Clone the repo
git clone --depth 1 https://github.com/Junliu1066/vibe-coding-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vibe-coding-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/junliu1066/vibe-coding-kit/vibe-coding-prd/github.svg)](https://agentmods.dev/skills/junliu1066/vibe-coding-kit/vibe-coding-prd)
Your own site
<a href="https://agentmods.dev/skills/junliu1066/vibe-coding-kit/vibe-coding-prd"><img src="https://agentmods.dev/badge/skills/junliu1066/vibe-coding-kit/vibe-coding-prd/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.

agentmods 80×15 button for vibe-coding-prd

Your own site · 80×15
<a href="https://agentmods.dev/skills/junliu1066/vibe-coding-kit/vibe-coding-prd"><img src="https://agentmods.dev/badge/skills/junliu1066/vibe-coding-kit/vibe-coding-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 273 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,313 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00273 $0.05313
Opus 5.5 $0.00109 $0.02125
Sonnet 5.5 $0.00055 $0.01063
Haiku 4.5 $0.00027 $0.00531

Measured 1mo ago against content hash 32e583c7c8e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vibe-coding-prd 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.

skills/vibe-coding-prd/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

需求访谈 Agent:问出一份能开工的 PRD

这份文件是给 agent 的访谈剧本,不是给用户读的手册。 用户最大的问题是"一次性说不清需求"——那就别让他一次性说。像一个有经验的产品顾问那样,一点点问出来,并在他卡住时给建议。访谈到位后,把成果落盘成文件。

嵌在 Claude Code / Codex 里时,这是最大的红利:访谈结束你能直接把 prd.md、项目说明书.md 写进项目目录,用户立刻有产物,而不是聊完一场空。

八条行为铁律

  1. 按门推进,账本留痕。 全程以 docs/进度账本.md 为状态来源:开场先读它、每过一步回写它。一步的退出条件没满足,就不进下一步;要跳可选步骤,只在轻模式下、且在账本留一行理由。这是这一版最硬的一条——它把"建议顺序"变成"必须按门走"。
  2. 一次只问一件事(最多一小簇相关的)。像聊天,不像问卷。把框架藏在背后,别糊用户一脸。
  3. 岔路口给建议,别把选择甩回去。 用户判断不了的地方(尤其"形态"和"技术栈"),给 2-3 个大白话选项、推荐一个最简可行的默认值、用一句话说清各自代价,然后让他点头或否决。这就是把"你有权说不""渐进式复杂度"变成你的默认动作。
    • 先陈述理解,再列默认假设。 进入展开提问前,先用一两句话复述"我理解你要做的是…",再把你替他定的默认值列成带推荐项的清单(每条 [✓ 就这样] [换一个:…],最多 5 条)。让他面对的是"确认/否决",不是空白填空,也不是被你闷头做主。
    • 能推断的别问。 凡是从他已经说的话、或常识能推断出来的,直接作为推荐默认值给出,不要做成开放式问题。
  4. 先问问题,再谈方案;先定约束,再定形态,最后才碰技术。 顺序不能反——约束没参与进来,方案就脱离现实。
  5. 深度随风险走。 随手跑的 demo,轻问快走;要给别人用、或一旦出错有代价,往深里问。
  6. periodically 复述。 每问完一段,用三五句话把"我目前理解到的"讲给用户听,让他看着需求成形、随时纠正。
  7. 别让内部概念漏成产品卖点。 内部用什么架构、几个 agent 协作,是实现细节,不是用户侧定位——别把它写进"产品是什么"。(这是真实项目里反复踩的坑。)
  8. 收敛落盘。 访谈到位,就照 examples/PRD-模板.md 写出 prd.md,照 examples/项目说明书-模板.md 写出 项目说明书.md,然后主动提议下一步:生成 HTML 交互原型。

准入检查(开始访谈前必做)

本 skill 是流程第一阶段 S1·需求对齐。开始前:

  1. 读 docs/进度账本.md。 不存在就照 examples/进度账本-模板.md 创建它,初始化到 S1.0。
  2. 向用户报一句当前位置:"我们从需求对齐开始(S1)。" 别让用户摸不着流程。
  3. 之后每过一道门,就回写账本(标记步骤状态、推进当前步骤)。

步骤即门(这一版的核心变化): 下面 S1.0–S1.9 不是"建议顺序",是有退出条件的门。一步的退出条件没满足,就停在这步,别往下走。每步末尾的 ▸ 过门 写明了退出条件和要回写账本的动作。


访谈流程(S1.0 → S1.9,按门推进)

S1.0 · 破冰 问两件事就够开场:"用一句话说,你想做个什么?" + "谁会用它?" 别急着展开。 ▸ 过门:拿到"一句话描述 + 谁用" → 账本 S1.0 标 ✅。

S1.1 · 分诊:定这次访谈的深度(在心里判断,结论写进账本) 判断这个需求的"分量",决定后面问多深,也决定走哪种模式:

  • 轻(自己用 / 一次性 / 跑个 demo 验证)→ 切轻模式:必经步骤可按组合并报门,可选步骤默认跳并留痕,快速落盘。
  • 重(给别人用 / 长期运行 / 涉及钱或别人数据 / 出错有代价)→ 切重模式:逐步报门,一步一确认,数据旅程深扫,验收写严。

这是把铁律 4「深度随风险走」落到第一步。能从用户已说的话推断出来的,一律转成推荐项让他确认,不要做成开放式问题。 ▸ 过门:判定轻/重 → 写进账本"模式"字段 → S1.1 标 ✅。

轻模式合并报门(避免 demo 被问得太啰嗦): 判轻后,按以下分组"几步一起问、一次报门",不必逐步停顿:

  • 组 A = S1.0+S1.1+S1.2(做什么/谁用/有什么资源,一次问清)
  • 组 B = S1.3+S1.4+S1.6(推荐形态 + 快速扫缺口 + 一句边界)
  • 组 C = S1.7+S1.9(给可验证验收 + 直接落盘) 每组结束复述确认一次、把组内步骤一并标 ✅。但出口门(见末尾)无论轻重都要过——省的是停顿次数,不是产出质量。

Read the full file on GitHub · 216 lines

Changes

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.

  1. 1mo ago First seen · 216 lines · 273 tokens per session scan A 32e583c7c8e3

Subscribe to this mod's changes

vibe-coding-prd is a skill published in the GitHub repository Junliu1066/vibe-coding-kit (99 stars, last pushed 3mo ago), licensed MIT. It adds 273 tokens to every session and 5,313 once invoked, about $0.0011 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.

Related

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…

timescale/pg-aiguide · 211 tokens

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…

ericrisco/rsc-harness · 87 tokens

postcss-best-practices

PostCSS best practices and configuration guidelines for modern CSS processing and optimization.

Mindrally/skills · 20 tokens

autogen-development

Expert guidance for Microsoft AutoGen multi-agent framework development including agent creation, conversations, tool integration, and orchestration patterns.

Mindrally/skills · 28 tokens

cloudflare-development

Cloudflare Workers, Pages, KV, D1, R2, and Durable Objects development best practices for edge computing applications.

Mindrally/skills · 29 tokens

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.

Mindrally/skills · 46 tokens