Scrum Master Expert

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.

Workflow

1. Assess Current State

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).

2. Analyze Sprint Health

The agent scores the team across 6 weighted dimensions:

Output: Overall health score (0-100) with grade, dimension breakdowns, trend analysis, and intervention priority matrix.

3. Forecast Velocity

The agent runs Monte Carlo simulation on historical velocity data:

python scripts/velocity_analyzer.py sprint_data.json --format text

Output includes:

• Rolling averages (3, 5, 8 sprint windows)
• Trend detection via linear regression
• Volatility classification (coefficient of variation)
• Anomaly detection (outliers beyond 2 sigma)
• 6-sprint forecast with 50%, 70%, 85%, 95% confidence intervals

Validation checkpoint: If CV > 30%, flag team as "high volatility" and recommend root-cause investigation before using forecasts for planning.

4. Plan Sprint Capacity

python scripts/sprint_capacity_calculator.py team_data.json --format text

The calculator accounts for:

• Per-member availability (PTO, allocation percentage)
• Ceremony overhead: planning (2h) + daily standup (15min/day) + review (1h) + retro (1h) + refinement (1h)
• Focus factor (80% realistic, 85% optimistic)
• Story point estimates (conservative, realistic, optimistic) from historical velocity

Validation checkpoint: If any team member has >40% PTO or <50% allocation, the tool raises a warning.

5. Facilitate Retrospective

The agent uses retrospective analyzer insights to guide discussion:

python scripts/retrospective_analyzer.py sprint_data.json --format text

Analysis includes:

• Action item completion rates by priority and owner
• Recurring theme identification with persistence scoring
• Sentiment trend tracking (positive/negative)
• Team maturity assessment (forming/storming/norming/performing)

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.

6. Coach Team Development

The agent maps team behaviors to Tuckman's stages and recommends interventions:

Psychological safety assessment uses Edmondson's 7-point scale. Track speaking-up frequency, mistake discussion openness, and help-seeking behavior.

Example: Sprint Planning with Forecast

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.

Input Schema

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": []
    }
  ]
}

Tools

velocity_analyzer.py

python scripts/velocity_analyzer.py sprint_data.json --format text

sprint_health_scorer.py

python scripts/sprint_health_scorer.py sprint_data.json --format text

retrospective_analyzer.py

python scripts/retrospective_analyzer.py sprint_data.json --format text

sprint_capacity_calculator.py

python scripts/sprint_capacity_calculator.py team_data.json --format text

Templates & Assets

• assets/sprint_report_template.md

  -- Sprint report with health grade, velocity trends, quality metrics

• assets/team_health_check_template.md

  -- Spotify Squad Health Check adaptation (9 dimensions)

• assets/sample_sprint_data.json

  -- 6-sprint dataset for testing tools

• assets/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 criteria

• assets/sprint_plan_template.md

  -- Sprint plan with capacity, commitments, risks

References

• references/velocity-forecasting-guide.md

  -- Monte Carlo implementation, confidence intervals, seasonality adjustment

• references/team-dynamics-framework.md

  -- Tuckman's stages, psychological safety building, conflict resolution

• references/sprint-planning-guide.md

  -- Pre-planning checklist, SMART goals, capacity methodology

Key Metrics & Targets

Troubleshooting

sprint_health_scorer.py

velocity_analyzer.py

retrospective_analyzer.py

retrospective_analyzer.py

Success Criteria

• Sprint health score consistently above 80/100 across 6-dimension assessment
• Velocity coefficient of variation (CV) maintained below 20% over rolling 6-sprint window
• Sprint commitment reliability exceeds 85% (completed vs. planned points)
• Action item completion rate from retrospectives exceeds 70% by next retro
• Blocker average resolution time under 3 working days
• Team maturity advances at least one Tuckman stage within 3-6 months of coaching
• Psychological safety score on Edmondson scale exceeds 4.0/5.0

Scope & Limitations

In Scope:

• Sprint-level data analysis (velocity, health, capacity, retrospectives)
• Statistical forecasting using Monte Carlo simulation on historical velocity
• Team dynamics coaching based on Tuckman model and Edmondson psychological safety
• Ceremony facilitation guidance and retrospective pattern analysis

Out of Scope:

• Portfolio-level project management (see

  senior-pm/

  skill)
• Product backlog prioritization and roadmap decisions (see

  execution/prioritization-frameworks/

  )
• Individual performance evaluation -- this skill measures team-level metrics only
• Real-time Jira/Confluence integration (see

  jira-expert/

  and

  confluence-expert/

  skills)
• SAFe-specific PI planning or cross-team dependency management (see

  program-manager/

  )

Important Caveats:

• The Scrum Guide 2020 removed the term "velocity" as a required artifact; this skill treats velocity as a diagnostic tool, not a performance measure. Flow metrics (cycle time, throughput, WIP) complement velocity for delivery forecasting. Use both -- velocity for sprint planning, flow metrics for process improvement.
• Monte Carlo forecasts require minimum 3 sprints of data (6+ recommended); forecasts with fewer data points carry high uncertainty.
• Health scores are heuristics, not absolute measures. Calibrate dimension weights to your team context.

Integration Points

senior-pm/

sprint-retrospective/

execution/brainstorm-okrs/

execution/prioritization-frameworks/

discovery/pre-mortem/

Tool Reference

velocity_analyzer.py

Analyzes sprint velocity data with trend detection, Monte Carlo forecasting, and anomaly identification.

data_file

--format

text

text

json

sprint_health_scorer.py

Scores sprint health across 6 weighted dimensions with composite grading and recommendations.

data_file

--format

text

text

json

retrospective_analyzer.py

Processes retrospective data to track action item completion, identify recurring themes, and assess team maturity.

data_file

--format

text

text

json

sprint_capacity_calculator.py

Calculates sprint capacity accounting for ceremony overhead, PTO, allocation percentages, and focus factor.

data_file

--format

text

text

json

--demo