uncertainty-and-units

SUMMARY

What it does

This Agent Skill provides procedural knowledge for tracking physical units and propagating measurement uncertainty in scientific calculations, using the Python libraries pint and uncertainties. It covers unit conversion and dimensional checking, GUM uncertainty budgets, Type A and Type B evaluation, coverage factors and expanded uncertainty, Monte Carlo propagation, significant-figure and plus-minus reporting, error propagation through curve fits, CODATA constants, auditing Python code for stripped units or broken uncertainty propagation, and order-of-magnitude plausibility checks using dimensionless groups (Reynolds, Peclet, Damkohler, Knudsen, Biot, Womersley), characteristic scales such as diffusion time or Debye length, and observed magnitude ranges. It triggers on phrases like "is this number physically reasonable", "sanity check these units", "what regime is this flow in", or a result that looks off by orders of magnitude. The skill bundles local command-line tools that run offline and require Python 3.12+ with pint, uncertainties, NumPy, and SciPy for numeric operations; the static auditor is standard-library only. The skill is part of the Scientific Agent Skills library by K-Dense-AI and is distributed under the MIT license.