Token导航 LogoToken导航TokenDH.com
前端设计敏感数据github未标认证来源可访问clear审计通过

task-planning任务规划

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

276,624

周安装

11,308

GitHub Stars

88

下载量

88,592
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

3

许可证

MIT

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:task-planning(任务规划)
来源仓库:https://github.com/supercent-io/skills-template
仓库路径:skills/task-planning
安装命令:
npx skills add https://github.com/supercent-io/skills-template --skill task-planning
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/supercent-io/skills-template --skill task-planning

简介

为敏捷团队提供包含用户故事、冲刺组织和待办事项优先级的结构化任务规划。

  • 提供用于编写符合 INVEST 标准的用户故事的模板,其中包含验收标准、技术说明、估计和依赖项
  • 包括史诗般的分解模式,将功能分解为故事和带有时间估计的细粒度任务
  • 支持 MoSCoW 优先级排序(必须/应该/可以/不会)和冲刺计划,包括容量规划和完成清单定义
  • 强制约束:故事必须有明确的接受标准、点估计和已确定的依赖关系;超过 13 点的故事必须拆分

SKILL.md

Task Planning

When to use this skill

  • Feature development: Break down a new feature into small tasks
  • Sprint Planning: Select work to include in the sprint
  • Backlog Grooming: Clean up the backlog and set priorities

Instructions

Step 1: Write User Stories (INVEST)

INVEST principles:

  • Independent: Independent
  • Negotiable: Negotiable
  • Valuable: Valuable
  • Estimable: Estimable
  • Small: Small
  • Testable: Testable

Template:

## User Story: [title]

**As a** [user type]
**I want** [feature]
**So that** [value/reason]

### Acceptance Criteria
- [ ] Given [context] When [action] Then [outcome]
- [ ] Given [context] When [action] Then [outcome]
- [ ] Given [context] When [action] Then [outcome]

### Technical Notes
- API endpoint: POST /api/users
- Database: users table
- Frontend: React component

### Estimation
- Story Points: 5
- T-Shirt: M

### Dependencies
- User authentication must be completed first

### Priority
- MoSCoW: Must Have
- Business Value: High

Example:

## User Story: User Registration

**As a** new visitor
**I want** to create an account
**So that** I can access personalized features

### Acceptance Criteria
- [ ] Given valid email and password When user submits form Then account is created
- [ ] Given duplicate email When user submits Then error message is shown
- [ ] Given weak password When user submits Then validation error is shown
- [ ] Given successful registration When account created Then welcome email is sent

### Technical Notes
- Hash password with bcrypt
- Validate email format
- Send welcome email via SendGrid
- Store user in PostgreSQL

### Estimation
- Story Points: 5

### Dependencies
- Email service integration (#123)

### Priority
- MoSCoW: Must Have

Step 2: Decompose Epic → Story → Task

## Epic: User Management System

### Story 1: User Registration
- **Points**: 5
- Tasks:
  - [ ] Design registration form UI (2h)
  - [ ] Create POST /api/users endpoint (3h)
  - [ ] Implement email validation (1h)
  - [ ] Add password strength checker (2h)
  - [ ] Write unit tests (2h)
  - [ ] Integration testing (2h)

### Story 2: User Login
- **Points**: 3
- Tasks:
  - [ ] Design login form (2h)
  - [ ] Create POST /api/auth/login endpoint (2h)
  - [ ] Implement JWT token generation (2h)
  - [ ] Add "Remember Me" functionality (1h)
  - [ ] Write tests (2h)

### Story 3: Password Reset
- **Points**: 5
- Tasks:
  - [ ] "Forgot Password" UI (2h)
  - [ ] Generate reset token (2h)
  - [ ] Send reset email (1h)
  - [ ] Reset password form (2h)
  - [ ] Update password API (2h)
  - [ ] Tests (2h)

Step 3: MoSCoW prioritization

## Feature Prioritization (MoSCoW)

### Must Have (Sprint 1)
- User Registration
- User Login
- Basic Profile Page

### Should Have (Sprint 2)
- Password Reset
- Email Verification
- Profile Picture Upload

### Could Have (Sprint 3)
- Two-Factor Authentication
- Social Login (Google, GitHub)
- Account Deletion

### Won't Have (This Release)
- Biometric Authentication
- Multiple Sessions Management

Step 4: Sprint Planning

## Sprint 10 Planning

**Sprint Goal**: Complete user authentication system

**Duration**: 2 weeks
**Team Capacity**: 40 hours × 4 people = 160 hours
**Estimated Velocity**: 30 story points

### Selected Stories
1. User Registration (5 points) - Must Have
2. User Login (3 points) - Must Have
3. Password Reset (5 points) - Must Have
4. Email Verification (3 points) - Should Have
5. Profile Edit (5 points) - Should Have
6. JWT Refresh Token (3 points) - Should Have
7. Rate Limiting (2 points) - Should Have
8. Security Audit (4 points) - Must Have

**Total**: 30 points

### Sprint Backlog
- [ ] User Registration (#101)
- [ ] User Login (#102)
- [ ] Password Reset (#103)
- [ ] Email Verification (#104)
- [ ] Profile Edit (#105)
- [ ] JWT Refresh Token (#106)
- [ ] Rate Limiting (#107)
- [ ] Security Audit (#108)

### Definition of Done
- [ ] Code written and reviewed
- [ ] Unit tests passing (80%+ coverage)
- [ ] Integration tests passing
- [ ] Documentation updated
- [ ] Deployed to staging
- [ ] QA approved

Output format

Task board structure

Backlog → To Do → In Progress → Review → Done

Backlog:
- Sorted by priority
- Groomed stories

To Do:
- Work selected for the sprint
- Owner assigned

In Progress:
- WIP Limit: 2 per person
- Work in progress

Review:
- Waiting for code review
- In QA testing

Done:
- Meets DoD
- Deployed

Constraints

Required rules (MUST)

  1. Clear AC: Acceptance Criteria required
  2. Estimation done: Assign points to every story
  3. Dependencies identified: Specify prerequisite work

Prohibited (MUST NOT)

  1. Stories too large: Split anything 13+ points
  2. Vague requirements: Avoid "improve" and "optimize"

Best practices

  1. INVEST: Write good user stories
  2. Definition of Ready: Ready before sprint start
  3. Definition of Done: Clear completion criteria

References

Metadata

Version

  • Current version: 1.0.0
  • Last updated: 2025-01-01
  • Compatible platforms: Claude, ChatGPT, Gemini

Tags

#task-planning #user-stories #backlog #sprint-planning #agile #project-management

Examples

Example 1: Basic usage

Example 2: Advanced usage

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

30.88%
按下载量换算27,357

OpenCode

21.94%
按下载量换算19,437

Antigravity

18.8%
按下载量换算16,655

Codex

11.9%
按下载量换算10,542

Gemini CLI

8.55%
按下载量换算7,575

Cursor

3.24%
按下载量换算2,870

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。

来源信息

继续浏览同类 Skills