Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

prd-to-plan计划

Agent Skill

prd-to-plan 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。

总安装

1,646

周安装

70

GitHub Stars

公开资料未说明

下载量

577
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:prd-to-plan(计划)
来源仓库:https://github.com/tahajemmali/skills
仓库路径:skills/prd-to-plan
安装命令:
npx skills add https://github.com/tahajemmali/skills --skill prd-to-plan
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/tahajemmali/skills --skill prd-to-plan

简介

prd-to-plan 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 中整理项目状态。

  • 适用于围绕仓库状态、代码变更或协作事项进行信息组织与查询。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装并使用。
  • 建议确认权限范围和维护状态,涉及写入操作时需验证 token 权限。
  • 可结合原始 README 进一步核验具体功能和调用方式。

SKILL.md

PRD to Plan

Break a PRD into a phased implementation plan using vertical slices (tracer bullets). Output is a Markdown file in ./docs/<feature-name>/plan.md.

Process

1. Confirm the PRD is in context

The PRD should already be in the conversation. If it isn't, ask the user to paste it or point you to the file.

2. Explore the codebase

If you have not already explored the codebase, do so to understand the current architecture, existing patterns, and integration layers.

3. Identify durable architectural decisions

Before slicing, identify high-level decisions that are unlikely to change throughout implementation:

  • Route structures / URL patterns
  • Database schema shape
  • Key data models
  • Authentication / authorization approach
  • Third-party service boundaries

These go in the plan header so every phase can reference them.

4. Draft vertical slices

Break the PRD into tracer bullet phases. Each phase is a thin vertical slice that cuts through ALL integration layers end-to-end, NOT a horizontal slice of one layer.

5. Quiz the user

Present the proposed breakdown as a numbered list. For each phase show:

  • Title: short descriptive name
  • User stories covered: which user stories from the PRD this addresses

Ask the user:

  • Does the granularity feel right? (too coarse / too fine)
  • Should any phases be merged or split further?

Iterate until the user approves the breakdown.

When invoked by afk (no user interaction): Skip the quiz. Use your best judgment on granularity and write the plan directly.

6. Write the plan file

Create ./docs/<feature-name>/ if it doesn't exist. Write the plan as a Markdown file named after the feature (e.g. ./docs/meta-direct-whatsapp/plan.md). Use the template below.

Task formatting (important for execution)

Each phase's "What to build" section controls how ralph executes the phase:

  • Numbered list (1., 2., 3.) — each item becomes a separate implementation task with its own commit. This is the preferred format for phases with multiple deliverables.
  • Bullet list (-, *) — each bullet becomes a separate task.
  • Single paragraph — the entire phase runs as one task.

Use numbered items whenever a phase has more than one logical deliverable. This gives ralph focused, atomic implementation sessions and granular commit history.

Source PRD: <relative path to PRD.md, e.g. docs/feature/PRD.md>

Architectural decisions

Durable decisions that apply across all phases:

  • Routes:...
  • Schema:...
  • Key models:...
  • (add/remove sections as appropriate)

Phase 1:

User stories:

What to build

  1. First task — describe the first deliverable for this slice
  2. Second task — describe the next deliverable
  3. Third task — describe the next deliverable

Acceptance criteria

  • Criterion 1
  • Criterion 2
  • Criterion 3

Phase 2:

User stories:

What to build

  1. First task —...
  2. Second task —...

Acceptance criteria

  • ...

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

35.82%
按下载量换算207

Claude

31.18%
按下载量换算180

Cursor

19.84%
按下载量换算114

Gemini CLI

11.04%
按下载量换算64

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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