Token导航 LogoToken导航

Agent Skill · 前端设计

create-prd(创建 PRD)

create-prd 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

create-prd 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 8,797。

总安装 259周安装 11GitHub Stars 1下载 91核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:create-prd(创建 PRD)
来源仓库:https://github.com/yldgio/vibe-grimoire
仓库路径:skills/create-prd
安装命令:
npx skills add https://github.com/yldgio/vibe-grimoire --skill create-prd
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/yldgio/vibe-grimoire --skill create-prd

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

create-prd 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合围绕仓库状态和协作事项进行整理。适用于需要跟踪代码变更、管理 Issue 或审查 Pull Request 的场景。可结合项目现有流程,自动提取关键信息并生成报告。

安装命令:npx skills add https://github.com/yldgio/vibe-grimoire --skill create-prd。建议确认权限范围,避免触发不必要的命令执行或文件读写。

来源仓库内路径:skills/create-prd

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/yldgio/vibe-grimoire --skill create-prd;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

create-prd 怎么安装?

在终端执行 npx skills add https://github.com/yldgio/vibe-grimoire --skill create-prd。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

create-prd 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

create-prd 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

create-prd 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

create-prd 用的人多吗?

公开数据是累计安装 259 次,近一周安装 11 次,下载 91 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

create-prd 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
create-prd

创建 PRD · 本页

2591调用外部服务未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Create PRD

Guide the user from a problem statement to a fully-formed PRD, then submit it to their preferred destination.

Skill workflow — these skills chain naturally: create-prd → pre-mortem *(optional stress-test)* → plan-from-prd *(phased plan)* → prd-slice *(tracker work items)*


Process

1. Gather the problem statement

Ask the user for a detailed description of:

  • The problem they are trying to solve
  • Any ideas or constraints they already have in mind

2. Explore the codebase

Use a subagent to explore the repo and verify the user's assertions. Understand the current architecture, existing patterns, and potential integration points.

3. Interview the user

Relentlessly interview the user about every aspect of the plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.

As user stories accumulate, continuously assess the overall complexity of the feature. When the scope feels large — many moving parts, cross-cutting concerns, or a broad user-facing surface area — challenge the user to identify a first sufficient MVP wave before expanding further. Ask: *"What is the smallest version of this that delivers real value?"* This is not about counting stories; it is about understanding whether the work can be meaningfully shipped in phases.

3a. Pre-mortem stress-test *(optional)*

If the PRD is growing large, assumptions are unclear, or requirements conflict, pause here and invoke the pre-mortem skill before proceeding to Step 4. It will interrogate the design, surface contradictions, and return either a risk document or an annotated PRD. Resume from Step 4 once pre-mortem is complete.

4. Design modules *(optional — skip if the user wants a lightweight PRD)*

Sketch the major modules to build or modify. Actively look for opportunities to extract deep modules — ones that encapsulate significant functionality behind a simple, stable, testable interface.

Review with the user:

  • Do these modules match their expectations?
  • Which modules should have tests written for them?

5. Write the PRD

Use the <prd-template> below to write the PRD.

6. Submit the PRD

Ask the user where they want it saved: GitHub, Azure DevOps, or local file.

Run a subagent to submit so you keep your main context clean:

  • GitHub: Use the gh-cli skill (gh issue create) with appropriate labels and assignees.
  • Azure DevOps: Use the azure-devops-cli skill (az boards work-item create) with appropriate tags and assignees.
  • Local file: Save to ./prds/<feature-name>.md.

Problem Statement

The problem that the user is facing, from the user's perspective.

Solution

The solution to the problem, from the user's perspective.

User Stories

A LONG, numbered list of user stories. Each user story should be in the format of:

  1. As an, I want a, so that

This list of user stories should be extremely extensive and cover all aspects of the feature.

Implementation Waves *(omit for small features)*

When the feature is complex — many stories, broad surface area, or multiple cross-cutting concerns — describe how delivery will be broken into successive waves. Each wave should be independently demonstrable and deliver a coherent user experience on its own.

  • Wave 1 (MVP): The smallest version that delivers real value. Define what "done" looks like for this wave.
  • Wave 2: Additional depth or breadth that builds on Wave 1.
  • *(add waves as needed)*

Prefer grouping stories into waves so that parallel workstreams within a wave share no blocking dependencies.

Implementation Decisions

A list of implementation decisions that were made. This can include:

  • The modules that will be built/modified
  • The interfaces of those modules that will be modified
  • Technical clarifications from the developer
  • Architectural decisions
  • Schema changes
  • API contracts
  • Specific interactions

Do NOT include specific file paths or code snippets. They may end up being outdated very quickly.

Testing Decisions

A list of testing decisions that were made. Include:

  • A description of what makes a good test (only test external behavior, not implementation details)
  • Which modules will be tested
  • Prior art for the tests (i.e. similar types of tests in the codebase)

Out of Scope

A description of the things that are out of scope for this PRD.

Further Notes

Any further notes about the feature.

The skill's work is complete when the PRD has been submitted to the user's chosen destination. Return control to the user.

平台分布

Codex

33.64%
按下载量换算31

Claude

33.33%
按下载量换算30

Cursor

20.57%
按下载量换算19

Gemini CLI

10.4%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills