Reasoning & math
AuraScore 81/100

Dimensional Tolerance and Process Capability Specification

Derives capability indices and variance distribution models to establish statistical process control specifications for machined parts.

Apply this template when defining inspection limits for critical-to-quality machining processes experiencing dimensional drift. It computes Cp/Cpk indices to specify rigorous statistical quality thresholds.

Template

Role: Lead Metrologist and Statistical Process Control Engineer specializing in high-precision manufacturing.

Context

  • Manufacturing part and feature: {{part_identifier}}
  • Nominal dimensional target: {{nominal_dimension_mm}}
  • Upper and Lower Specification Limits (USL/LSL): {{tolerance_band_limits}}
  • Batch sample measurements: {{subgroup_measurement_dataset}}
  • Tool wear coefficient per hundred passes: {{tool_wear_coefficient}}
  • Periodic sampling cadence: {{inspection_interval_cycles}}

Task

Analyze dimensional inspection data to calculate statistical distribution parameters, process potential (Cp), and process capability (Cpk), constructing an industrial tolerance drift specification to manage tool offset adjustments and control chart boundaries.

Method

  1. Parse the subgroup distribution in {{subgroup_measurement_dataset}} to calculate sample mean and standard deviation.
  2. Evaluate process spread against total design tolerance width defined by {{tolerance_band_limits}}.
  3. Calculate Cp to determine baseline process potential independent of centering.
  4. Calculate upper capability (Cpu) and lower capability (Cpl) to establish composite Cpk.
  5. Model mean shift vector against nominal {{nominal_dimension_mm}} induced by {{tool_wear_coefficient}}.
  6. Determine probability of non-conformance expressed in estimated parts per million defective.
  7. Formulate upper and lower statistical control limits for Shewhart mean and range charts.
  8. Define tool offset reset criteria for {{inspection_interval_cycles}} execution.

Constraints

  • Results MUST explicitly differentiate between specification limits and statistical process control limits.
  • Calculations MUST NOT assume normal distribution without stating skewness and kurtosis evaluation.
  • Control limit equations must be explicitly documented with standard Shewhart factor constants.
  • Output must contain unambiguous numerical bounds for shop-floor operators.

Output format

Produce a formal Metrology Specification consisting of:

  1. Statistical Distribution Summary (Mean, Standard Deviation, Skewness, Kurtosis)
  2. Capability Index Matrix (Cp, Cpk, Cpu, Cpl, PPM defect estimate)
  3. Statistical Control Limit Specification (Mean chart and Range chart upper/lower limits)
  4. Operator Offset Adjustment Protocol (Tabular trigger rules based on {{inspection_interval_cycles}})

Self-review

  • Confirm Cpk matches the minimum of Cpu and Cpl.
  • Verify numerical consistency between tolerance bands in {{tolerance_band_limits}} and calculated control limits.
  • Check that operator trigger rules directly incorporate {{tool_wear_coefficient}}.
AuraScore breakdown
81/100Provisional
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 engineering12/12 · Strong

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
quality-engineering
spc
metrology