Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计通过

write-a-prd写一个 prd

Agent Skill

write-a-prd 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

总安装

291

周安装

12

GitHub Stars

7

下载量

95
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:write-a-prd(写一个 prd)
来源仓库:https://github.com/helderberto/skills
仓库路径:skills/write-a-prd
安装命令:
npx skills add https://github.com/helderberto/skills --skill write-a-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/helderberto/skills --skill write-a-prd

简介

write-a-prd 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词或任务场景快速定位候选结果时使用。

  • 适用于研究检索类任务,可结合来源仓库和原始 README 核验具体用法。
  • 通过 npx skills add 命令从 GitHub 安装,需确认权限范围和维护状态。
  • 使用前建议检查是否会触发联网、命令执行或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

PRD Writing

Skip steps already satisfied. If user provided a description via arguments, skip to Step 2.

Workflow

1. Gather problem description

Ask the user for a detailed description of the problem and any solution ideas.

2. Explore codebase

Verify assertions and map current state: data models, services, API routes, frontend structure, and test patterns. Note what exists vs. what must be built.

3. Interview

Interview relentlessly. Lead with your recommended answer as the first option (Recommended); the user confirms by selecting it or corrects via another option. Group related questions when possible (up to 4). Use AskUserQuestion when available; otherwise present options as a numbered list. If a question can be answered by exploring code, explore instead of asking.

Walk these branches (skip any already resolved):

  • Scope & Surface -- Where does this live? New page/view or integrated? Which user roles?
  • Data & Concepts -- Precise definitions for each new concept. What data exists, what's missing?
  • Behavior & Interaction -- How does the user interact? Sorting, filtering, search, time ranges?
  • Display & Output -- Numbers, tables, charts, forms? Exportable? URL-driven state?
  • Access & Privacy -- Who sees what? Role-based restrictions? Sensitive data concerns?
  • Boundaries -- What is explicitly out of scope? Adjacent features to defer?
  • Integration -- Schema changes? New or extended services? External dependencies?

4. Design modules

Sketch major modules to build or modify. Favor deep modules -- a simple interface (1-3 entry points) hiding a large implementation that rarely changes, over shallow modules where the interface is nearly as complex as the implementation.

Signals of shallow design: many small functions with 1:1 query mapping, callers compose multiple calls, adding a feature requires changing the interface.

Present modules to user. Confirm which need tests (multiSelect): list each module as an option with a description of what tests would cover. Use AskUserQuestion when available; otherwise present as a checklist for the user to confirm.

5. Write PRD

Save to prds/<kebab-case-name>.md (create prds/ if missing).

# Feature Name

## Problem Statement

The problem from the user's perspective. Focus on pain and impact.

## Solution

The solution from the user's perspective. Describe the experience, not the architecture.

## User Stories

Long numbered list. Cover happy path, edge cases, error states.

1. As a <actor>, I want <feature>, so that <benefit>

## Implementation Decisions

### New Modules
- Module name, purpose, and public interface (function signatures with param types)
- Why each module exists as a separate unit

### Architectural Decisions
- Key definitions (precise meaning of domain terms)
- Data flow from storage to display
- State management approach

### Schema Changes
- New tables/columns needed, or "None required"

### API Contracts
- New routes, request/response shapes

### Navigation
- Where the feature is accessed, new routes added

Do NOT include file paths or code snippets -- they go stale.

## Testing Decisions

- What makes a good test (behavior, not implementation)
- Which modules need tests
- Key test cases (empty state, boundaries, isolation)
- Prior art: similar test patterns in the codebase

## Out of Scope

Explicit list. Be specific -- vague exclusions invite scope creep.

Error Handling

  • prds/ missing -- create it
  • Scope larger than expected -- surface and re-scope with user before continuing

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.22%
按下载量换算36

Claude

30.35%
按下载量换算29

Cursor

17.1%
按下载量换算16

Gemini CLI

9.32%
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

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills