scrum-master by borghei/claude-skills
npx skills add https://github.com/borghei/claude-skills --skill scrum-master该智能体扮演数据驱动的 Scrum Master,结合冲刺分析、行为科学和持续改进方法。它分析速率趋势,从 6 个维度评估冲刺健康状况,识别回顾会议模式,并推荐针对特定阶段的辅导干预措施。
智能体收集冲刺数据并建立基线:
python scripts/velocity_analyzer.py sprint_data.json --format json > velocity_baseline.json
python scripts/sprint_health_scorer.py sprint_data.json --format text
python scripts/retrospective_analyzer.py sprint_data.json --format text
验证检查点: 确认至少存在 3 个冲刺的数据(建议 6 个以上以获得统计显著性)。
智能体从 6 个加权维度对团队进行评分:
| 维度 | 权重 | 衡量内容 |
|---|---|---|
| 承诺可靠性 | 25% | 冲刺目标达成的一致性 |
| 范围稳定性 | 20% | 冲刺中期范围变更频率 |
| 阻碍解决 | 15% | 解决障碍的平均时间 |
| 仪式参与度 |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 15% |
| 参与度和有效性 |
| 用户故事完成分布 | 15% | 已完成与部分完成故事的比例 |
| 速率可预测性 | 10% | 交付一致性(变异系数目标:<20%) |
输出:总体健康分数(0-100)及等级、各维度细分、趋势分析和干预优先级矩阵。
智能体对历史速率数据运行蒙特卡洛模拟:
python scripts/velocity_analyzer.py sprint_data.json --format text
输出包括:
验证检查点: 如果变异系数 > 30%,将团队标记为“高波动性”,并建议在使用预测进行规划前进行根本原因调查。
python scripts/sprint_capacity_calculator.py team_data.json --format text
计算器考虑以下因素:
验证检查点: 如果任何团队成员带薪休假 >40% 或分配 <50%,工具会发出警告。
智能体利用回顾分析器的洞察来引导讨论:
python scripts/retrospective_analyzer.py sprint_data.json --format text
分析包括:
验证检查点: 将新的行动项数量限制在团队历史完成率范围内。如果团队完成了 50% 的行动项,则每次回顾会议最多新增 2-3 个行动项。
智能体将团队行为映射到塔克曼阶段并推荐干预措施:
| 阶段 | 行为指标 | 辅导方法 |
|---|---|---|
| 形成期 | 礼貌、试探、依赖 Scrum Master | 提供结构、流程教育、建立关系 |
| 震荡期 | 冲突、抵触、挫败感 | 促进冲突解决、维护安全环境、灵活调整流程 |
| 规范期 | 协作开始出现、共享规范 | 建立自主性、转移所有权、发展技能 |
| 成熟期 | 高生产力、自组织 | 引入挑战、支持创新、扩大影响范围 |
心理安全感评估使用埃德蒙森的 7 分量表。跟踪发言频率、讨论错误的开放度和寻求帮助的行为。
给定 6 个冲刺的速率数据 [18, 22, 20, 19, 23, 21]:
$ python scripts/velocity_analyzer.py sprint_data.json --format text
速率分析
=================
平均值:20.5 点
趋势:稳定(斜率:+0.3/冲刺)
波动性:低(变异系数:8.7%)
蒙特卡洛预测(下一个冲刺):
50% 置信区间:19-22 点
85% 置信区间:17-24 点
95% 置信区间:16-25 点
建议:承诺 19-20 点以确保可靠交付。
仅在团队无带薪休假且无已知阻碍时使用 22 点。
然后,智能体将此结果与容量计算器输出和健康分数进行交叉参考,以推荐可持续的承诺水平。
所有工具都接受遵循 assets/sample_sprint_data.json 的 JSON:
{
"team_info": { "name": "string", "size": "number", "scrum_master": "string" },
"sprints": [
{
"sprint_number": "number",
"planned_points": "number",
"completed_points": "number",
"stories": [],
"blockers": [],
"ceremonies": {}
}
],
"retrospectives": [
{
"sprint_number": "number",
"went_well": ["string"],
"to_improve": ["string"],
"action_items": []
}
]
}
| 工具 | 用途 | 命令 |
|---|---|---|
velocity_analyzer.py | 速率趋势、蒙特卡洛预测 | python scripts/velocity_analyzer.py sprint_data.json --format text |
sprint_health_scorer.py | 6 维度健康评分 | python scripts/sprint_health_scorer.py sprint_data.json --format text |
retrospective_analyzer.py | 回顾模式分析、行动跟踪 | python scripts/retrospective_analyzer.py sprint_data.json --format text |
sprint_capacity_calculator.py | 考虑仪式开销的容量规划 | python scripts/sprint_capacity_calculator.py team_data.json --format text |
assets/sprint_report_template.md -- 包含健康等级、速率趋势、质量指标的冲刺报告assets/team_health_check_template.md -- Spotify 小队健康检查适配版(9 个维度)assets/sample_sprint_data.json -- 用于测试工具的 6 个冲刺数据集assets/expected_output.json -- 参考输出(速率平均值 20.2,健康分数 78.3/100)assets/user_story_template.md -- 包含 INVEST 标准的经典和 Job Story 格式assets/sprint_plan_template.md -- 包含容量、承诺、风险的冲刺计划references/velocity-forecasting-guide.md -- 蒙特卡洛实现、置信区间、季节性调整references/team-dynamics-framework.md -- 塔克曼阶段、心理安全感建设、冲突解决references/sprint-planning-guide.md -- 计划前检查清单、SMART 目标、容量方法| 指标 | 目标 | 测量方式 |
|---|---|---|
| 健康分数 | >80/100 | 冲刺级别,6 个维度 |
| 速率可预测性(变异系数) | <20% | 滚动 6 个冲刺窗口 |
| 承诺可靠性 | >85% | 已达成冲刺目标 / 尝试冲刺目标 |
| 范围稳定性 | <15% 变更 | 冲刺中期范围变更 |
| 阻碍解决 | <3 天平均值 | 从提出到解决的时间 |
| 行动项完成率 | >70% | 下次回顾会议前完成的回顾项目 |
| 仪式参与度 | >90% | 出勤率 + 参与质量 |
| 心理安全感 | >4.0/5.0 | 月度脉冲调查 |
每周安装次数
77
代码仓库
GitHub 星标数
35
首次出现
Jan 24, 2026
安全审计
安装于
claude-code60
opencode54
gemini-cli52
codex50
cursor50
github-copilot46
The agent acts as a data-driven Scrum Master combining sprint analytics, behavioral science, and continuous improvement methodologies. It analyzes velocity trends, scores sprint health across 6 dimensions, identifies retrospective patterns, and recommends stage-specific coaching interventions.
The agent collects sprint data and establishes baselines:
python scripts/velocity_analyzer.py sprint_data.json --format json > velocity_baseline.json
python scripts/sprint_health_scorer.py sprint_data.json --format text
python scripts/retrospective_analyzer.py sprint_data.json --format text
Validation checkpoint: Confirm at least 3 sprints of data exist (6+ recommended for statistical significance).
The agent scores the team across 6 weighted dimensions:
| Dimension | Weight | What It Measures |
|---|---|---|
| Commitment Reliability | 25% | Sprint goal achievement consistency |
| Scope Stability | 20% | Mid-sprint scope change frequency |
| Blocker Resolution | 15% | Average time to resolve impediments |
| Ceremony Engagement | 15% | Participation and effectiveness |
| Story Completion Distribution | 15% | Completed vs. partial stories ratio |
| Velocity Predictability | 10% | Delivery consistency (CV target: <20%) |
Output: Overall health score (0-100) with grade, dimension breakdowns, trend analysis, and intervention priority matrix.
The agent runs Monte Carlo simulation on historical velocity data:
python scripts/velocity_analyzer.py sprint_data.json --format text
Output includes:
Validation checkpoint: If CV > 30%, flag team as "high volatility" and recommend root-cause investigation before using forecasts for planning.
python scripts/sprint_capacity_calculator.py team_data.json --format text
The calculator accounts for:
Validation checkpoint: If any team member has >40% PTO or <50% allocation, the tool raises a warning.
The agent uses retrospective analyzer insights to guide discussion:
python scripts/retrospective_analyzer.py sprint_data.json --format text
Analysis includes:
Validation checkpoint: Limit new action items to the team's historical completion rate. If the team completes 50% of action items, cap at 2-3 new items per retro.
The agent maps team behaviors to Tuckman's stages and recommends interventions:
| Stage | Behavioral Indicators | Coaching Approach |
|---|---|---|
| Forming | Polite, tentative, dependent on SM | Provide structure, educate on process, build relationships |
| Storming | Conflict, resistance, frustration | Facilitate conflict, maintain safety, flex process |
| Norming | Collaboration emerging, shared norms | Build autonomy, transfer ownership, develop skills |
| Performing | High productivity, self-organizing | Introduce challenges, support innovation, expand impact |
Psychological safety assessment uses Edmondson's 7-point scale. Track speaking-up frequency, mistake discussion openness, and help-seeking behavior.
Given 6 sprints of velocity data [18, 22, 20, 19, 23, 21]:
$ python scripts/velocity_analyzer.py sprint_data.json --format text
Velocity Analysis
=================
Average: 20.5 points
Trend: Stable (slope: +0.3/sprint)
Volatility: Low (CV: 8.7%)
Monte Carlo Forecast (next sprint):
50% confidence: 19-22 points
85% confidence: 17-24 points
95% confidence: 16-25 points
Recommendation: Commit to 19-20 points for reliable delivery.
Use 22 points only if team has no PTO and no known blockers.
The agent then cross-references this with capacity calculator output and health scores to recommend a sustainable commitment level.
All tools accept JSON following assets/sample_sprint_data.json:
{
"team_info": { "name": "string", "size": "number", "scrum_master": "string" },
"sprints": [
{
"sprint_number": "number",
"planned_points": "number",
"completed_points": "number",
"stories": [],
"blockers": [],
"ceremonies": {}
}
],
"retrospectives": [
{
"sprint_number": "number",
"went_well": ["string"],
"to_improve": ["string"],
"action_items": []
}
]
}
| Tool | Purpose | Command |
|---|---|---|
velocity_analyzer.py | Velocity trends, Monte Carlo forecasting | python scripts/velocity_analyzer.py sprint_data.json --format text |
sprint_health_scorer.py | 6-dimension health scoring | python scripts/sprint_health_scorer.py sprint_data.json --format text |
retrospective_analyzer.py | Retro pattern analysis, action tracking | python scripts/retrospective_analyzer.py sprint_data.json --format text |
assets/sprint_report_template.md -- Sprint report with health grade, velocity trends, quality metricsassets/team_health_check_template.md -- Spotify Squad Health Check adaptation (9 dimensions)assets/sample_sprint_data.json -- 6-sprint dataset for testing toolsassets/expected_output.json -- Reference outputs (velocity avg 20.2, health 78.3/100)assets/user_story_template.md -- Classic and Job Story formats with INVEST criteriaassets/sprint_plan_template.md -- Sprint plan with capacity, commitments, risksreferences/velocity-forecasting-guide.md -- Monte Carlo implementation, confidence intervals, seasonality adjustmentreferences/team-dynamics-framework.md -- Tuckman's stages, psychological safety building, conflict resolutionreferences/sprint-planning-guide.md -- Pre-planning checklist, SMART goals, capacity methodology| Metric | Target | Measurement |
|---|---|---|
| Health Score | >80/100 | Sprint-level, 6 dimensions |
| Velocity Predictability (CV) | <20% | Rolling 6-sprint window |
| Commitment Reliability | >85% | Sprint goals achieved / attempted |
| Scope Stability | <15% change | Mid-sprint scope changes |
| Blocker Resolution | <3 days avg | Time from raised to resolved |
| Action Item Completion | >70% | Retro items done by next retro |
| Ceremony Engagement | >90% | Attendance + participation quality |
| Psychological Safety | >4.0/5.0 | Monthly pulse survey |
Weekly Installs
77
Repository
GitHub Stars
35
First Seen
Jan 24, 2026
Security Audits
Gen Agent Trust HubPassSocketFailSnykPass
Installed on
claude-code60
opencode54
gemini-cli52
codex50
cursor50
github-copilot46
Excel财务建模规范与xlsx文件处理指南:专业格式、零错误公式与数据分析
45,800 周安装
Linkerd 服务网格生产模式指南:Kubernetes 轻量级网格、mTLS、金丝雀部署、流量拆分
3,600 周安装
Hyperliquid 交易技能:在链上 DEX 交易永续合约与现货,AI 代理自动执行
3,600 周安装
App Store 截图生成器 - 用 Next.js 制作高转化率 iOS 应用商店广告截图
3,600 周安装
数据可视化指南:图表选择、Python代码与设计原则
3,600 周安装
Angular v20+ 测试指南:使用 Vitest 测试信号组件与最佳实践
3,500 周安装
SLO实施指南:SLI/SLO/错误预算框架,Prometheus监控与可靠性目标设定
3,600 周安装
sprint_capacity_calculator.py | Capacity planning with ceremony overhead | python scripts/sprint_capacity_calculator.py team_data.json --format text |