Token导航 LogoToken导航

Agent Skill · 研究检索

sprint-planning-assistant(冲刺计划助理)

用于处理 Jira 项目、任务、缺陷、Sprint、负责人和状态流转。它适合让 Agent 辅助查询工单、汇总迭代进展、创建任务或整理需求和缺陷信息。使用时要确认项目权限、字段配置和工作流规则,不同团队的 Issue 类型、状态和必填字段可能不同;涉及批量改状态、改负责人或创建工单时,应先预览变更内容再执行。

sprint-planning-assistant 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,权限为只读;许可证为 MIT,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 27,129。

总安装 3,444周安装 170GitHub Stars 公开资料未说明下载 1,800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:sprint-planning-assistant(冲刺计划助理)
来源仓库:https://github.com/sethdford/claude-plugins
仓库路径:skills/sprint-planning-assistant
安装命令:
npx skills add sethdford/claude-plugins --skill "sprint-planning-assistant"
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。

AgentSkills.tonpx skills
npx skills add sethdford/claude-plugins --skill "sprint-planning-assistant"

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。

sprint-planning-assistant 用于 Jira 冲刺计划辅助,可查询 backlog、估算故事点或拆分用户故事。它帮助 Agent 整理需求优先级、识别阻塞项或协调跨团队依赖。

安装方式:npx skills add sethdford/claude-plugins --skill "sprint-planning-assistant",需具备对应项目的读写权限。创建任务时应检查必填字段(如描述、预估工时),避免因格式错误被系统拒绝。涉及跨项目引用时需显式声明链接关系,防止信息孤岛形成。

来源仓库内路径:skills/sprint-planning-assistant

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 sethdford/claude-plugins --skill "sprint-planning-assistant";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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

sprint-planning-assistant 怎么安装?

在终端执行 npx skills add sethdford/claude-plugins --skill "sprint-planning-assistant"。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

sprint-planning-assistant 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。

sprint-planning-assistant 需要什么权限?

权限级别是只读。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。

sprint-planning-assistant 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。

sprint-planning-assistant 用的人多吗?

公开数据是累计安装 3,444 次,近一周安装 170 次,下载 1,800 次。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。

sprint-planning-assistant 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

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。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 要求有安全扫描结论才肯安装的团队。
  • 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
sprint-planning-assistant

冲刺计划助理 · 本页

3,444—只读MIT未收录

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

Sprint Planning Assistant

Expert assistance for planning sprints, estimating work, and managing team capacity.

When to Use This Skill

  • Planning a new sprint
  • Grooming/refining the backlog
  • Estimating story points
  • Calculating team capacity
  • Analyzing sprint velocity
  • Organizing work priorities
  • User mentions: sprint, velocity, capacity, estimation, story points

Sprint Planning Process

1. Pre-Planning Preparation

Review Previous Sprint
sprint = "Sprint 42" ORDER BY updated DESC

Analyze:

  • What was completed?
  • What carried over?
  • What was the velocity?
  • Any blockers or issues?
Check Backlog Health
project = PROJ AND sprint IS EMPTY AND status = "To Do" ORDER BY priority DESC

Verify:

  • Stories have descriptions
  • Acceptance criteria defined
  • Dependencies identified
  • Estimates added

2. Sprint Planning Meeting

Step 1: Set Sprint Goal
  • What is the primary objective?
  • What value will we deliver?
  • How does it align with roadmap?

Example Goals:

  • "Complete user authentication system"
  • "Improve page load performance by 50%"
  • "Launch payment integration MVP"
Step 2: Calculate Capacity

Formula:

Capacity = (Team Size × Work Days × Hours per Day) - (Meetings + PTO + Buffer)

Example:

Team: 5 developers
Sprint: 10 work days
Work: 6 hours/day (accounting for meetings)
PTO: 2 days (one person out)
Buffer: 20% (for unexpected work)

Capacity = (5 × 10 × 6) - (2 × 6) - (20% of 288)
        = 300 - 12 - 58
        = 230 hours

Or in story points (if velocity is 40):
Capacity ≈ 40 story points
Step 3: Select Stories

Criteria:

  1. Aligns with sprint goal
  2. Has clear acceptance criteria
  3. Team has necessary skills
  4. No blocking dependencies
  5. Fits within capacity

Query for candidates:

project = PROJ
AND status = "To Do"
AND sprint IS EMPTY
AND "Story Points" IS NOT EMPTY
ORDER BY priority DESC, rank ASC
Step 4: Review and Commit
  • Total points within capacity?
  • Dependencies manageable?
  • Risks identified?
  • Team agreement on scope?

Story Point Estimation

What Are Story Points?

Story points measure relative effort/complexity, not time:

  • Effort: How much work?
  • Complexity: How hard is it?
  • Uncertainty: How much is unknown?

Estimation Scales

Fibonacci Scale (Recommended)
1  - Trivial: Simple change, < 1 hour
2  - Easy: Small feature, well understood
3  - Moderate: Standard feature, clear path
5  - Average: Typical feature, some complexity
8  - Complex: Significant feature, multiple components
13 - Very Complex: Large feature, high uncertainty
21 - Epic: Too large, should be split
T-Shirt Sizes (Alternative)
XS = 1 point
S  = 2 points
M  = 3 points
L  = 5 points
XL = 8 points

Estimation Techniques

Planning Poker
  1. Product owner explains story
  2. Team asks clarifying questions
  3. Each person picks estimate (secretly)
  4. Everyone reveals simultaneously
  5. Discuss differences
  6. Re-estimate until consensus
Reference Stories

Compare to previously completed work:

  • "This is about the same as the login feature (5 points)"
  • "This is simpler than the payment integration (8 points)"
  • "This is more complex than adding a button (2 points)"
Three-Point Estimation
Estimate = (Optimistic + (4 × Most Likely) + Pessimistic) / 6

Example:
Best case: 3 points
Most likely: 5 points
Worst case: 13 points

Estimate = (3 + (4 × 5) + 13) / 6 = 36 / 6 = 6 points

Factors Affecting Estimates

Increase Estimate For:
  • New technology/unfamiliar domain
  • External dependencies
  • Unclear requirements
  • Complex business logic
  • Integration with many systems
  • High risk/uncertainty
Keep Estimate Lower For:
  • Familiar technology
  • Clear requirements
  • Similar to past work
  • Self-contained changes
  • Good test coverage exists

Backlog Grooming

When to Groom

  • Regular sessions (e.g., mid-sprint)
  • Before sprint planning
  • When new priorities emerge

Grooming Activities

1. Refinement
  • Clarify requirements
  • Add acceptance criteria
  • Identify dependencies
  • Break down epics
  • Add technical notes
2. Estimation
  • Add story points
  • Validate existing estimates
  • Re-estimate if scope changed
3. Prioritization
  • Order by business value
  • Consider dependencies
  • Balance quick wins vs. strategic work
4. Cleanup
  • Close duplicates
  • Archive obsolete issues
  • Update stale information

Grooming Checklist

For each story:

  • Clear title and description
  • User story format (if applicable)
  • Acceptance criteria defined
  • Story points estimated
  • Priority set
  • Labels added
  • Dependencies identified
  • Assignee (if known)
  • Sprint ready

Capacity Management

Team Capacity Factors

Available Hours
Base Hours = Team Size × Sprint Days × Hours/Day
Actual Hours = Base - (PTO + Meetings + Support + Buffer)
Focus Factor

Percentage of time spent on sprint work:

Typical: 60-70%
High performing: 70-80%
New team: 50-60%
Velocity

Average story points completed per sprint:

Velocity = Average(Last 3-5 Sprints)

Capacity Planning Example

Team Details:

  • 6 developers
  • 2-week sprint (10 work days)
  • Historical velocity: 45 points

Commitments:

  • 1 developer on PTO for 3 days
  • 2 developers in training for 2 days
  • On-call rotation (1 person, 20% capacity)

Calculation:

Base capacity: 45 points (historical velocity)

Adjustments:
- PTO: -3 days of 1 person = -3 points
- Training: -2 days of 2 people = -4 points
- On-call: -20% of 1 person = -2 points
- Buffer (10%): -4 points

Sprint capacity: 45 - 3 - 4 - 2 - 4 = 32 points

Sprint Anti-Patterns to Avoid

❌ Overcommitment

Loading 60 points when velocity is 40.

Fix: Use historical velocity as guide, add buffer

❌ Under-commitment

Loading 20 points when velocity is 40, to "guarantee" completion.

Fix: Commit to realistic amount, have stretch goals ready

❌ No Sprint Goal

Just a collection of random stories.

Fix: Define clear, valuable objective for the sprint

❌ Splitting Mid-Sprint

Constantly splitting stories after sprint starts.

Fix: Better grooming and estimation up front

❌ Ignoring Dependencies

Starting work that's blocked by external factors.

Fix: Identify dependencies during planning

❌ Gold Plating

Adding unplanned features during implementation.

Fix: Stick to acceptance criteria, capture new ideas as separate stories

Sprint Queries

Stories Ready for Sprint

project = PROJ
AND type = Story
AND status = "To Do"
AND sprint IS EMPTY
AND "Story Points" IS NOT EMPTY
AND description IS NOT EMPTY
ORDER BY priority DESC

Current Sprint Progress

sprint in openSprints()
ORDER BY status ASC, priority DESC

Unestimated Stories

project = PROJ
AND type IN (Story, Task)
AND "Story Points" IS EMPTY
AND status != Done
ORDER BY priority DESC

Sprint Burndown Data

sprint = "Sprint 42"
AND status IN ("In Progress", "To Do")

Carry-Over from Previous Sprint

sprint = "Sprint 42"
AND sprint = "Sprint 43"
AND resolution IS EMPTY

Velocity Tracking

Calculate Velocity

Method 1: Average of Last 3 Sprints

Sprint 40: 38 points
Sprint 41: 42 points
Sprint 42: 44 points

Velocity = (38 + 42 + 44) / 3 = 41 points

Method 2: Weighted Average

Recent sprints count more:
Velocity = (Sprint N × 3 + Sprint N-1 × 2 + Sprint N-2 × 1) / 6

Velocity Trends

Increasing Velocity
  • Team is maturing
  • Processes improving
  • Technical debt decreasing
Stable Velocity
  • Team is consistent
  • Good predictability
  • Sustainable pace
Decreasing Velocity
  • Investigate: technical debt? team changes? distractions?
  • Address root causes
  • May need to reduce commitments

Velocity vs. Capacity

Velocity: Historical output (story points completed) Capacity: Theoretical input (available hours/points)

Use velocity for sprint planning, not capacity.

Sprint Planning Template

1. Sprint Details

Sprint Number: 43
Duration: Jan 15 - Jan 28 (10 work days)
Sprint Goal: Complete user profile functionality
Team Velocity: 41 points (average last 3 sprints)

2. Team Capacity

Team Members: 6 developers
Availability:
- Alice: 10 days (full)
- Bob: 7 days (3 days PTO)
- Carol: 10 days (full)
- Dave: 10 days (full)
- Eve: 9 days (1 day training)
- Frank: 10 days (full, but on-call)

Adjusted Capacity: 36 points

3. Sprint Backlog

Committed Stories (36 points):
- PROJ-101: User profile page (8 pts)
- PROJ-102: Avatar upload (5 pts)
- PROJ-103: Profile editing (8 pts)
- PROJ-104: Privacy settings (5 pts)
- PROJ-105: Profile completion badge (3 pts)
- PROJ-106: Update navigation (2 pts)
- PROJ-107: Profile tests (5 pts)

Stretch Goals (13 points):
- PROJ-108: Social media links (5 pts)
- PROJ-109: Custom themes (8 pts)

4. Dependencies & Risks

Dependencies:
- PROJ-102 blocked until design review (due Jan 16)
- PROJ-104 requires security review

Risks:
- Avatar upload may need third-party service
- Privacy settings have regulatory requirements

Mitigation:
- Start PROJ-101, 103, 106 first
- Spike for avatar service options
- Consult legal team early on privacy

5. Sprint Success Criteria

Must Have:
- Users can view and edit their profiles
- Avatar upload working
- Privacy controls functional

Nice to Have:
- Profile completion indicators
- Social media integration

Definition of Done:
- Code reviewed
- Tests passing (>80% coverage)
- Deployed to staging
- Acceptance criteria met
- Documentation updated

How I'll Help

When you need sprint planning assistance, I will:

  1. Analyze backlog: Review stories and readiness
  2. Calculate capacity: Based on team size, availability, velocity
  3. Suggest stories: Prioritized candidates for the sprint
  4. Estimate work: Help with story point estimation
  5. Identify risks: Dependencies, blockers, unknowns
  6. Track progress: Monitor sprint health
  7. Provide queries: JQL for sprint management

Example Interaction

You: "Help me plan Sprint 45. Team of 5, one person out for 2 days, velocity is usually around 35 points"

Me: "I'll help plan Sprint 45.

Capacity Calculation:

  • Base velocity: 35 points
  • Adjustment for PTO: -1.5 points (2 days of 1 person ≈ 10%)
  • Buffer (10%): -3.5 points
  • Sprint capacity: 30 points

Let me search for ready stories:

[Uses /jira-search with refinement query]

Recommended Sprint Backlog (30 points):

  1. PROJ-501: Payment gateway integration (13 pts) - HIGH PRIORITY
  2. PROJ-502: Transaction history UI (8 pts)
  3. PROJ-503: Receipt email templates (5 pts)
  4. PROJ-504: Payment error handling (4 pts)

Sprint Goal: Complete basic payment processing flow

Stretch Goals (if time allows):

  • PROJ-505: Refund functionality (8 pts)

Should I create these issues or adjust the selection?"

平台分布

Claude Code

27.33%
按下载量换算492

windsurf

22.28%
按下载量换算401

trae

19.42%
按下载量换算350

OpenCode

13.24%
按下载量换算238

Codex

7.2%
按下载量换算130

Antigravity

3.29%
按下载量换算59

安全审计

暂无安全审计结果可展示。

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。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