Reasoning & math
AuraScore 77/100

Process Capability Ratio and Tolerance Shift Assessment

Calculate Cp, Cpk, and projected defect rates to evaluate industrial machining process capability against design tolerances.

Use this template when setting up or validating precision manufacturing processes. It computes statistical capability indices from sample measurements and models the risk of out-of-spec production.

Template

Role: Chief Quality Assurance & Metrology Statistician with expertise in Six Sigma process validation and precision manufacturing controls.

Context

  • Manufacturing station: {{manufacturing_line_id}}
  • Critical quality characteristic: {{critical_dimension_feature}}
  • Upper Specification Limit (USL): {{upper_spec_limit_mm}} mm
  • Lower Specification Limit (LSL): {{lower_spec_limit_mm}} mm
  • Measured sample mean: {{sample_mean_measured}} mm
  • Sample standard deviation: {{sample_std_deviation}} mm

Task

Produce a statistical process capability analysis assessing centering, spread, Cp, Cpk, and estimated non-conformance PPM for the specified critical engineering dimension.

Method

  1. Calculate total design tolerance band (USL minus LSL).
  2. Compute potential process capability ratio (Cp) by dividing tolerance spread by six standard deviations.
  3. Calculate Upper Capability Index (Cpu) using {{upper_spec_limit_mm}}, {{sample_mean_measured}}, and {{sample_std_deviation}}.
  4. Calculate Lower Capability Index (Cpl) using {{lower_spec_limit_mm}}, {{sample_mean_measured}}, and {{sample_std_deviation}}.
  5. Determine minimum index Cpk and process centering factor (k).
  6. Derive theoretical parts-per-million (PPM) defect rates based on normal distribution Z-scores.
  7. Assess whether the process satisfies standard industrial acceptance thresholds (Cpk >= 1.33 and Cpk >= 1.67).
  8. Formulate physical tooling or parameter adjustment guidance to eliminate centering bias.

Constraints

  • Statistical derivations MUST include exact equations, intermediate Z-scores, and clear metric bounds.
  • Output MUST NOT extrapolate results beyond the assumed normal distribution behavior.
  • Clearly distinguish between potential capability (Cp) and realized capability (Cpk).
  • Limit tool and process tuning recommendations to physical manufacturing parameters.

Output format

  • Section 1: Statistical Index Matrix (Tolerance Band, Cp, Cpu, Cpl, Cpk, Centering Factor k)
  • Section 2: Defect Probability Model (Upper/Lower tail Z-scores and expected scrap PPM)
  • Section 3: Capability Classification (Pass/Fail vs. 1.33 benchmark and centering status)
  • Section 4: Process Centering Directives (3 engineering adjustment steps within 150 words)

Self-review

  • Verify that Cpk is mathematically less than or equal to Cp in all scenarios.
  • Confirm that Cpu and Cpl calculations reference the exact specified tolerance limits.
  • Ensure PPM estimates correctly map to calculated upper and lower tail probabilities.
AuraScore breakdown
77/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering8/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-reasoning-math
manufacturing-industrial
spc
quality-engineering
process-capability