Scrum Master

What Is Scrum Master?

The "Scrum Master" skill is a specialized, data-driven assistant designed for Scrum teams and agile practitioners seeking advanced insights into their development process. It enables in-depth analysis and coaching for agile teams by leveraging Python-based analytics tailored for key Scrum ceremonies and metrics. Unlike generic project management tools, this skill focuses on actionable, evidence-based insights by processing sprint data exports (commonly from Jira or similar tools). By automating analysis of velocity, team health, and retrospective outcomes, it empowers Scrum Masters and agile coaches to drive continuous improvement and foster high-performing teams.

Why Use Scrum Master?

Scrum teams continually seek to optimize their delivery, improve predictability, and enhance collaboration. The Scrum Master skill addresses these needs by providing:

• Objective Analytics: Move beyond anecdotal feedback with quantitative analysis of team performance.
• Forecasting: Employ Monte Carlo simulations for sprint planning and capacity forecasting, improving commitment confidence.
• Health Diagnostics: Assess multidimensional team health across collaboration, throughput, and process adherence.
• Retrospective Insights: Track action item completion and recurring themes to ensure retrospectives drive measurable improvement.
• Actionable Reporting: Generate concise, data-rich reports and forecasts to inform sprint planning, standups, and reviews.

These capabilities help Scrum teams avoid common pitfalls such as overcommitment, undetected process issues, and stagnating improvement efforts.

How to Get Started

Prerequisites

• Python environment (3.7+ recommended)
• Access to sprint JSON exports from Jira or a similar agile tracking tool

Installation

Clone the repository and install any required dependencies:

git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills/project-management/scrum-master
pip install -r requirements.txt

Data Preparation

Export your sprint data from your agile tool in JSON format. Typical exports include completed stories, story points, action items, blockers, and retrospective notes.

Running Analyses

Three main Python scripts are included:

1. velocity_analyzer.py
   For forecasting sprint outcomes using Monte Carlo simulations.
2. sprint_health_scorer.py
   For scoring team health across multiple dimensions.
3. retrospective_analyzer.py
   For extracting and tracking action items and improvement themes from retrospectives.

Example:

Velocity Forecast

python velocity_analyzer.py --input sprint_data.json --sprints 5

This command analyzes the last five sprints and produces a confidence interval forecast for the next sprint’s velocity.

Example:

Team Health Scoring

python sprint_health_scorer.py --input sprint_data.json

Outputs a health report with scores for collaboration, throughput, and blocker resolution.

Example:

Retrospective Analysis

python retrospective_analyzer.py --input retrospectives.json

Generates a report of recurring themes and tracks action item follow-through rates.

Key Features

1. Velocity

Analyzer

Utilizes Monte Carlo simulation to forecast potential sprint outcomes, taking into account historical velocity variance. This is invaluable for sprint planning and commitment discussions.

Sample output:

Sprint 21 velocity forecast: 38-52 story points (80% confidence interval)

2. Sprint Health

Scorer

Applies a scoring model across several dimensions (e.g., delivery consistency, collaboration, blocker management) to surface strengths and areas for improvement. The model is customizable to fit team context.

Sample output:

Team Health: B+
- Delivery Consistency: A
- Collaboration: B
- Blocker Management: C

3. Retrospective

Analyzer

Extracts action items and recurring improvement themes from retrospective notes or exports. Tracks historical follow-up rate, helping teams close the feedback loop on improvement items.

Sample output:

Retrospective Themes:
- Communication (3 occurrences)
- Definition of Done gaps (2 occurrences)
Action Item Completion Rate: 85%

4. Automated, Data-Driven Reporting

Each script produces concise reports suitable for sharing in sprint reviews, retrospectives, or standups. Outputs can be further customized or exported to other formats for wider visibility.

Best Practices

• Regular Data Exports: Automate or schedule regular sprint data exports from your tracking tool to ensure up-to-date analysis.
• Integrate with Ceremonies: Review reports during sprint planning, retrospectives, and standups to provide a factual basis for discussions.
• Customize Scoring: Adjust health scoring parameters to reflect your team’s unique goals and working agreements.
• Track Improvement Over Time: Use retrospective analysis to maintain accountability on improvement actions and detect persistent issues.
• Iterate Workflows: Continuously refine how you use insights from the tool, fostering a culture of data-driven improvement.

Important Notes

• The skill relies on the accuracy and completeness of your sprint data exports; incomplete data can yield misleading results.
• Customization may be required to adapt the JSON export format from different agile tools.
• The health scoring and forecasting models are configurable; review and calibrate them periodically to ensure alignment with team context.
• Reports are intended to support—not replace—human judgment. Use them as a starting point for deeper team discussions.
• The skill is open-source (MIT licensed) and welcomes contributions for additional analysis dimensions or integrations.

By embedding the Scrum Master skill into your agile process, teams can unlock deeper insights, predictability, and continuous improvement, all grounded in robust, reproducible analytics.