Token导航 LogoToken导航

Agent Skill · AI 工具

requirements-engineering(需求工程)

requirements-engineering 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。

requirements-engineering 是AI 工具类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描已通过,按安装量在AI 工具类的 2,536 个 Skill 里排第 1,999。

总安装 367周安装 15GitHub Stars 21下载 119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
MIT

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:requirements-engineering(需求工程)
来源仓库:https://github.com/thapaliyabikendra/ai-artifacts
仓库路径:skills/requirements-engineering
安装命令:
npx skills add https://github.com/thapaliyabikendra/ai-artifacts --skill requirements-engineering
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/thapaliyabikendra/ai-artifacts --skill requirements-engineering

这个 Skill 是做什么的

AI 工具类 Skill 用来扩展助手本身的能力,例如接模型、接检索、接外部服务。

requirements-engineering 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。适用于代码变更追踪、Issue 管理和协作流程梳理等场景。

通过安装命令 npx skills add https://github.com/thapaliyabikendra/ai-artifacts --skill requirements-engineering 从 GitHub 仓库安装使用。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。

来源仓库内路径:skills/requirements-engineering

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/thapaliyabikendra/ai-artifacts --skill require…;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

    它需要需要联网,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

requirements-engineering 怎么安装?

在终端执行 npx skills add https://github.com/thapaliyabikendra/ai-artifacts --skill requirements-engi…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

requirements-engineering 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。

requirements-engineering 需要什么权限?

权限级别是需要联网。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。

requirements-engineering 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

requirements-engineering 用的人多吗?

公开数据是累计安装 367 次,近一周安装 15 次,下载 119 次,GitHub 21 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。

requirements-engineering 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 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

  • 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AI 工具类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

AI 工具类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
executing-plans

执行计划 · Codex、Claude

1,515,336173,110只读MIT通过
verification-before-completion

完成前的验证 · Codex、Claude

1,319,472173,121权限未标注MIT通过
subagent-driven-development

子 Agent 驱动开发 · Codex、Claude

1,312,416173,138只读MIT通过
copy-editing

复制编辑 · Codex、Claude

1,209,57625,632只读MIT通过
paywall-upgrade-cro

付费专区升级 cro · Codex、Claude

1,030,17625,617只读MIT通过
requirements-engineering

需求工程 · 本页

36721需要联网MIT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

Requirements Engineering

Transform raw requirements into structured, testable specifications that guide development teams.

When to Use

  • Creating feature requirements documents
  • Writing user stories with acceptance criteria
  • Defining business rules and constraints
  • Documenting process flows
  • Prioritizing features (MoSCoW, RICE)
  • Analyzing stakeholder needs

Requirements Document Structure

A complete requirements document includes:

  1. Feature Overview - Business context and success metrics
  2. User Stories - Who, what, why format
  3. Acceptance Criteria - Given/When/Then scenarios
  4. Data Model - Fields, types, constraints
  5. Business Rules - BR-XXX format
  6. Permission Requirements - Role-based access
  7. Open Questions - Items needing clarification

Core Templates

User Story Format

**US-[XXX]: [Title]**

As a [role],
I want to [action],
So that [benefit].

**Acceptance Criteria:**
- [ ] Given [context], when [action], then [expected result]
- [ ] Given [context], when [action], then [expected result]
- [ ] Given [context], when [action], then [expected result]

**Priority**: Must Have | Should Have | Could Have | Won't Have
**Effort**: S (1-2 days) | M (3-5 days) | L (1-2 weeks) | XL (2+ weeks)
**Dependencies**: [List any dependent stories]

Acceptance Criteria Patterns

Happy Path:

Given a logged-in [role]
When they [perform action] with valid [inputs]
Then [expected success outcome]
And [side effects if any]

Validation Error:

Given a logged-in [role]
When they [perform action] with invalid [input type]
Then the system displays "[error message]"
And [the operation is not completed]

Authorization:

Given a user without [permission]
When they attempt to [perform action]
Then the system returns 403 Forbidden
And [logs the unauthorized attempt]

Edge Case:

Given [edge condition exists]
When [action is performed]
Then [graceful handling occurs]

Business Rule Format

Full format: See domain-modeling skill for detailed patterns and categories.

Quick format for requirements:

IDRuleEnforcementImpact
BR-{CAT}-001[Rule description][Create/Update/Delete][Reject with error]

Data Model Template

Full entity modeling: See domain-modeling skill for complete entity definitions with relationships, state transitions, and API access.

Quick format for requirements:

FieldTypeRequiredConstraintsDescription
IdGuidYesPKUnique identifier
NamestringYesMax 100 charsDisplay name
EmailstringYesValid email, UniqueContact email
StatusenumYesActive/InactiveCurrent state

Process Flow Template

## Process: [Process Name]

### Actors
| Actor | Role | Responsibility |
|-------|------|----------------|
| [Role 1] | [Title] | [What they do] |
| [Role 2] | [Title] | [What they do] |

### Flow
1. **[Actor]** initiates [action]
2. **System** validates [criteria]
3. If valid:
   a. [Success step 1]
   b. [Success step 2]
   c. [Notification/confirmation]
4. If invalid:
   a. [Error handling]
   b. [User feedback]

### Business Rules Applied
- BR-001: [Rule applied at step X]
- BR-002: [Rule applied at step Y]

Prioritization Methods

MoSCoW Method

PriorityMeaningGuideline
Must HaveCritical for launch~60% of effort
Should HaveImportant but not critical~20% of effort
Could HaveNice to have~20% of effort
Won't HaveOut of scope for this releaseDocument for future

RICE Scoring

RICE Score = (Reach × Impact × Confidence) / Effort

Reach: How many users affected per quarter (number)
Impact: Effect on each user (3=massive, 2=high, 1=medium, 0.5=low, 0.25=minimal)
Confidence: How sure are we (100%=high, 80%=medium, 50%=low)
Effort: Person-months to complete (number)

Quality Checklist

Before finalizing requirements:

  • At least 3 user stories defined
  • Each story has 2+ acceptance criteria
  • Acceptance criteria are testable (Given/When/Then)
  • Data model includes all fields with types
  • Business rules are numbered and documented
  • Permissions align with existing roles
  • Open questions are captured
  • Priority assigned to each story
  • Dependencies identified

Integration with Domain Modeling

When creating requirements, always consider domain impact:

  1. Before writing requirements: Review existing domain in docs/domain/
  2. During analysis: Identify new/modified entities, rules, permissions
  3. After requirements: Create impact analysis using domain-modeling skill

The business-analyst agent combines requirements-engineering with domain-modeling for complete analysis.

References

平台分布

Cursor

32.01%
按下载量换算38

Claude Code

22.2%
按下载量换算26

github-copilot

17.28%
按下载量换算21

mcpjam

12.68%
按下载量换算15

crush

8.24%
按下载量换算10

cline

3.91%
按下载量换算5

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。

继续浏览同类 Skills