
Six Sigma DMAIC Project Assistant
Structure DMAIC projects, analyze process data, and generate control plans
What You Can Do
This skill helps you structure end-to-end DMAIC projects by interpreting process data, explaining statistical test results to stakeholders, identifying root causes from multiple data sources, and designing control plans with monitoring strategies. You'll accelerate the narrative reasoning and documentation work that typically consumes 30-40% of Six Sigma project execution, while maintaining full control over methodology decisions and statistical validity.
Features
Clarify project scope, develop business cases, and establish Critical to Quality (CTQ) metrics with structured stakeholder alignment
Translate hypothesis test results, regression outputs, and Measurement System Analysis (MSA) data into actionable business insights
Connect findings across multiple data sources into coherent narratives that explain process variation and defects
Design monitoring strategies, set control limits, establish reaction plans, and define escalation triggers for sustained improvement
Generate charters, scorecards, dashboards, and executive summaries that track metric movements and project financial impact
Evaluate solution feasibility, structure DOE (Design of Experiments) approaches, and project improvement outcomes
Interpret process capability indices and establish measurement baselines for tracking improvement progress
Example Output
Example 1: Statistical Interpretation Input: "We ran a t-test on cycle time reduction: p-value = 0.032, mean difference = 2.3 hours, current capability index = 0.87" Output: The result is statistically significant at the 95% confidence level and indicates the process improvement is real, not random variation. Current capability (Cpk = 0.87) shows the process cannot consistently meet customer requirements—you need to achieve Cpk ≥ 1.33. The 2.3-hour reduction moves you in the right direction but further optimization is required.
Example 2: Control Plan Template Input: "We reduced defect rate by 30%. Now I need a control plan for the packaging station." Output: Control Plan summary including: Process variable (packaging pressure), Control method (automated gauge), Target/UCL/LCL values, Measurement frequency (every 500 units), Reaction plan (adjust if 2 points exceed control limit), Data recording method, and escalation procedure (notify supervisor if trend detected).
Example 3: Root Cause Narrative Input: "Defect rate spiked 3 weeks ago. Pareto chart shows 60% are labeling errors. Operator turnover increased 25%. Humidity in warehouse averaged 72%. Recent supplier change for adhesive." Output: Root cause analysis identifying operator inexperience as primary driver (60% weight) with environmental factor (humidity) as contributing factor, and supplier change as secondary contributor—structured narrative linking data points to actionable countermeasures.
What's Included
- SKILL.md instruction file with DMAIC methodology guidance and prompt templates:
- DMAIC Project Charter Template: Define phase structure with scope, business case, CTQ definition, and stakeholder identification
- Statistical Interpretation Framework: Decision trees and language patterns for explaining p-values, capability indices, and test results to non-technical stakeholders
- Control Plan Worksheet: Monitoring strategy template with control limits, reaction plans, escalation triggers, and measurement cadence
- Root Cause Analysis Synthesis Guide: Structure for connecting multiple data sources (Pareto, correlation, process data) into cohesive narratives
Who It's For
- Six Sigma Black Belts and Green Belts — Accelerate DMAIC execution and documentation for certification projects
- Process Improvement Managers — Structure and track multi-phase improvement initiatives with stakeholder alignment
- Operations Managers — Interpret process data and establish control systems for sustained performance gains
- Manufacturing/Quality Engineers — Synthesize statistical findings and design robust monitoring strategies
- Business Analysts — Build project scorecards and dashboards that explain variance and financial impact
Best For
- DMAIC phase structuring — Define charters, establish baselines, design improvement roadmaps
- Statistical data interpretation — Explain hypothesis tests, capability indices, and process measurements to business stakeholders
- Control plan development — Design monitoring systems, set control limits, and escalation procedures
- Root cause synthesis — Connect multiple data sources into unified narratives explaining defects or variation
- Project documentation — Generate executive summaries, dashboards, and formal project reports with financial impact calculations







