Token导航 LogoToken导航

Agent Skill · 研究检索

user-story-fundamentals(用户故事基础)

user-story-fundamentals 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。

user-story-fundamentals 是研究检索类 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;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 53,392。

总安装 535周安装 23GitHub Stars 239下载 188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:user-story-fundamentals(用户故事基础)
来源仓库:https://github.com/flpbalada/my-opencode-config
仓库路径:skills/user-story-fundamentals
安装命令:
npx skills add https://github.com/flpbalada/my-opencode-config --skill user-story-fundamentals
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/flpbalada/my-opencode-config --skill user-story-fundamentals

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于根据关键词、任务场景或来源线索进行信息检索的场景。通过 npx skills add 命令从指定 GitHub 仓库安装使用。安装前需确认权限范围和维护状态,注意是否触发联网或文件读写操作。

user-story-fundamentals 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/user-story-fundamentals

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/flpbalada/my-opencode-config --skill user-stor…;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

user-story-fundamentals 怎么安装?

在终端执行 npx skills add https://github.com/flpbalada/my-opencode-config --skill user-story-fundamen…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

user-story-fundamentals 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。

user-story-fundamentals 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。

user-story-fundamentals 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。

user-story-fundamentals 用的人多吗?

公开数据是累计安装 535 次,近一周安装 23 次,下载 188 次,GitHub 239 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。

user-story-fundamentals 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。
  • 需要处理研究检索类任务、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。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
user-story-fundamentals

用户故事基础 · 本页

535239需要联网未明确通过

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

User Story Fundamentals - Capturing User-Centered Requirements

A structured framework for capturing product requirements from the user's perspective. User stories help teams understand who needs a feature, what they want to accomplish, and why it matters.

When to Use This Skill

  • Writing backlog items
  • Defining feature requirements
  • Prioritizing development work
  • Communicating with development teams
  • Breaking down epics into actionable work
  • Ensuring user focus in product decisions

User Story Format

THE STANDARD TEMPLATE

"As a [type of user],
 I want [some goal],
 so that [some reason/benefit]."

Components:
┌─────────────────────────────────────────────────────┐
│  WHO: The user persona or role                      │
│  WHAT: The desired functionality or goal            │
│  WHY: The business value or user benefit            │
└─────────────────────────────────────────────────────┘

This format shifts focus from WRITING about requirements
to TALKING about them, with users at the center.

Core Components

WHO - User Persona

Specificity Spectrum:

Generic (avoid):
├── "As a user..."
└── "As a customer..."

Better:
├── "As a first-time visitor..."
├── "As a returning customer..."
├── "As an admin user..."
└── "As a mobile user..."

Best (with job context):
├── "As a marketing manager who needs weekly reports..."
├── "As a parent shopping for school supplies..."
├── "As a developer debugging production issues..."
└── "As a sales rep preparing for a client meeting..."

WHAT - Desired Functionality

Focus on GOALS, not IMPLEMENTATION:

❌ "I want a blue button in the header"
   (prescriptive, limits solutions)

✓ "I want to quickly access my saved items"
   (goal-focused, enables creativity)

❌ "I want a REST API endpoint"
   (technical implementation)

✓ "I want to integrate my data with external tools"
   (user goal, flexible implementation)

WHY - Business Value

The "So That" Connection:

This part explains:
├── What pain it solves
├── What value it creates
├── Why this matters to the user
└── How it connects to business goals

Without "so that":
"As a user, I want to filter search results"
→ Why? What's the actual need?

With "so that":
"As a user, I want to filter search results
 so that I can find relevant items faster
 when browsing large catalogs"
→ Clear value, enables better solutions

INVEST Criteria

QUALITY CHECKLIST FOR USER STORIES

I - Independent
│   Can be developed and delivered separately
│   No tight coupling to other stories
│
N - Negotiable
│   Details open to discussion
│   Not a rigid contract
│
V - Valuable
│   Delivers real value to user or business
│   Not just technical tasks
│
E - Estimable
│   Team can estimate effort
│   Clear enough to size
│
S - Small
│   Fits within single sprint
│   If too big, split it
│
T - Testable
│   Has clear acceptance criteria
│   Can verify when complete

Acceptance Criteria

Definition

ACCEPTANCE CRITERIA (AC)

Purpose: Define what makes the story "done"
Format: Specific, testable conditions

Example Story:
"As a user, I want to reset my password via email
 so that I can regain access if I forget it"

Acceptance Criteria:
□ User can request reset from login page
□ Email sent within 60 seconds of request
□ Reset link expires after 24 hours
□ Link works only once
□ Password must meet security requirements
□ User receives confirmation after successful reset

Writing Good AC

CharacteristicExample
Specific"Within 60 seconds" not "quickly"
Testable"Email contains reset link" - can verify
Outcome-focused"User can access account" not "system sends"
CompleteCovers happy path AND edge cases

Prioritization Framework

RICE Scoring

RICE = (Reach × Impact × Confidence) / Effort

Reach: How many users affected per time period?
       (100 users/month, 1000 users/quarter)

Impact: How much will it move the needle?
        3 = Massive, 2 = High, 1 = Medium, 0.5 = Low, 0.25 = Minimal

Confidence: How sure are we about estimates?
            100% = High, 80% = Medium, 50% = Low

Effort: Person-months of work
        (0.5, 1, 2, 3...)

Higher RICE score = Higher priority

MoSCoW Method

CATEGORIZATION FOR RELEASE PLANNING

MUST Have (Non-negotiable)
├── Critical for release
├── Legal/compliance requirements
└── Core value proposition

SHOULD Have (Important)
├── High value but not critical
├── Workarounds exist
└── Strong user demand

COULD Have (Nice to have)
├── Desired but not necessary
├── Easy wins if time permits
└── Lower user impact

WON'T Have (Not this time)
├── Explicitly out of scope
├── Future consideration
└── Documented for later

Story Splitting Techniques

When to Split

SPLIT IF:
├── Can't complete in one sprint
├── Story points > 13 (or team max)
├── Multiple distinct user values
├── Contains "and" connecting features
└── Too many acceptance criteria

Splitting Methods

1. BY WORKFLOW STEPS
   Original: "User can complete purchase"
   Split:
   ├── User can add items to cart
   ├── User can enter shipping info
   ├── User can enter payment info
   └── User can confirm and place order

2. BY USER TYPE
   Original: "User can view dashboard"
   Split:
   ├── Admin can view full dashboard
   ├── Manager can view team metrics
   └── User can view personal stats

3. BY OPERATIONS (CRUD)
   Original: "User can manage contacts"
   Split:
   ├── User can create contact
   ├── User can view contact details
   ├── User can edit contact
   └── User can delete contact

4. BY DATA VARIATIONS
   Original: "User can import data"
   Split:
   ├── User can import CSV files
   ├── User can import Excel files
   └── User can import from API

5. BY ACCEPTANCE CRITERIA
   Original: "User can search products"
   Split:
   ├── User can basic keyword search
   ├── User can filter by category
   ├── User can sort results
   └── User can save search

Definition of Done vs. Acceptance Criteria

DEFINITION OF DONE (DoD)        ACCEPTANCE CRITERIA (AC)
────────────────────────        ────────────────────────
Universal checklist             Story-specific conditions
Same for all stories            Unique per story
Quality standard                Functional requirements

DoD Examples:                   AC Examples:
□ Code reviewed                 □ User can X
□ Tests written                 □ System does Y
□ Documentation updated         □ Data validates as Z
□ No critical bugs              □ Performance meets N

Story Template

## User Story

**ID:** [PROJ-123] **Title:** [Brief descriptive title]

### Story

As a [specific user type], I want [goal/desire], so that [benefit/value].

### Acceptance Criteria

- [ ] [Specific, testable condition 1]
- [ ] [Specific, testable condition 2]
- [ ] [Specific, testable condition 3]

### Notes

- [Additional context]
- [Technical considerations]
- [Dependencies]

### Attachments

- [Link to designs]
- [Link to research]

### Estimation

- **Story Points:** [X]
- **Priority:** [High/Medium/Low]
- **Sprint:** [Sprint N]

Real-World Examples

E-commerce

Story: Password-less Login

As a returning customer,
I want to login using a magic link sent to my email,
so that I can access my account without remembering passwords.

Acceptance Criteria:
□ User enters email on login page
□ "Send magic link" option available
□ Email received within 30 seconds
□ Link valid for 15 minutes
□ One-click login from email
□ User lands on their dashboard after login
□ Link cannot be reused after login

SaaS Product

Story: Team Invitation

As an account admin,
I want to invite team members via email,
so that I can onboard my team without manual account creation.

Acceptance Criteria:
□ Admin can enter multiple email addresses
□ Invitation email clearly explains next steps
□ Invited user can set their own password
□ Admin can see pending invitations
□ Admin can revoke pending invitations
□ Duplicate email addresses are prevented
□ Admin can set role during invitation

Common Mistakes

ANTI-PATTERNS TO AVOID

❌ Implementation as story
   "Create database table for users"
   → Not user value, technical task

❌ Missing "so that"
   "As a user, I want to search"
   → Why? What problem does this solve?

❌ Too vague
   "As a user, I want a better experience"
   → What specifically? Not actionable

❌ Too large
   "As a user, I want full account management"
   → Multiple features, needs splitting

❌ Solution prescribed
   "As a user, I want a dropdown menu"
   → Describes UI, not user goal

Integration with Other Methods

MethodCombined Use
Theme-Epic-StoryStories fit within epic hierarchy
Jobs to Be DoneStories address user jobs
Five WhysFind root cause behind story need
Hypothesis TreeStories as hypotheses to test
KanbanStories flow through board stages

Quick Reference

STORY WRITING CHECKLIST

Format:
□ Follows "As a... I want... so that..." format
□ User type is specific and meaningful
□ Goal is user-focused, not technical
□ Benefit clearly stated

Quality (INVEST):
□ Independent - can be built alone
□ Negotiable - details discussable
□ Valuable - delivers real value
□ Estimable - team can size it
□ Small - fits in single sprint
□ Testable - has clear AC

Acceptance Criteria:
□ Specific and measurable
□ Testable (can verify pass/fail)
□ Covers main scenarios
□ Includes edge cases
□ Outcome-focused

Resources

平台分布

Codex

35.08%
按下载量换算66

Claude

31.86%
按下载量换算60

Cursor

19.49%
按下载量换算37

Gemini CLI

9.44%
按下载量换算18

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。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