Unit Computation with Pint

SkillAI & models

Lets your agent convert units and do calculations that track units, like meters to feet.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Unit Computation with Pint skill

About this capability

Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic

What this skill tells your AI

The instructions your AI receives, as published by parcadei/continuous-claude-v3 in .claude/skills/pint-compute/SKILL.md and read by ahel’s review.

Cognitive prosthetics for unit-aware computation. Use Pint for converting between units, performing unit arithmetic, checking dimensional compatibility, and simplifying compound units.

When to Use

  • Converting between units (meters to feet, kg to pounds)
  • Unit-aware arithmetic (velocity x time = distance)
  • Dimensional analysis (is force = mass x acceleration?)
  • Simplifying compound units to base or named units
  • Parsing and analyzing quantities with units

Quick Reference

I want to...CommandExample
Convert unitsconvertconvert "5 meters" --to feet
Unit mathcalccalc "10 m/s * 5 s"
Check dimensionscheckcheck newton --against "kg * m / s^2"
Parse quantityparseparse "100 km/h"
Simplify unitssimplifysimplify "1 kg*m/s^2"

Commands

parse

Parse a quantity string into magnitude, units, and dimensionality.

uv run python -m runtime.harness scripts/pint_compute.py \
    parse "100 km/h"

uv run python -m runtime.harness scripts/pint_compute.py \
    parse "9.8 m/s^2"

convert

Convert a quantity to different units.

uv run python -m runtime.harness scripts/pint_compute.py \
    convert "5 meters" --to feet

uv run python -m runtime.harness scripts/pint_compute.py \
    convert "100 km/h" --to mph

uv run python -m runtime.harness scripts/pint_compute.py \
    convert "1 atmosphere" --to pascal

calc

Perform unit-aware arithmetic. Operators must be space-separated.

uv run python -m runtime.harness scripts/pint_compute.py \
    calc "5 m * 3 s"

uv run python -m runtime.harness scripts/pint_compute.py \
    calc "10 m / 2 s"

uv run python -m runtime.harness scripts/pint_compute.py \
    calc "5 meters + 300 cm"

check

Check if two units have compatible dimensions.

uv run python -m runtime.harness scripts/pint_compute.py \
    check newton --against "kg * m / s^2"

uv run python -m runtime.harness scripts/pint_compute.py \
    check joule --against "kg * m^2 / s^2"

simplify

Simplify compound units to base or compact form.

uv run python -m runtime.harness scripts/pint_compute.py \
    simplify "1 kg*m/s^2"

uv run python -m runtime.harness scripts/pint_compute.py \
    simplify "1000 m"

Common Unit Domains

DomainExamples
Lengthmeter, foot, inch, mile, km, yard
Timesecond, minute, hour, day, year
Masskg, gram, pound, ounce, ton
Velocitym/s, km/h, mph, knot
Energyjoule, calorie, eV, kWh, BTU
Forcenewton, pound_force, dyne
Temperaturekelvin, celsius, fahrenheit
Pressurepascal, bar, atmosphere, psi
Powerwatt, horsepower

Output Format

All commands return JSON with relevant fields:

{
  "result": "16.4042 foot",
  "magnitude": 16.4042,
  "units": "foot",
  "dimensionality": "[length]",
  "latex": "16.4042\\,\\mathrm{ft}"
}

Error Handling

Dimensionality errors are caught and reported:

# This will error - incompatible dimensions
uv run python -m runtime.harness scripts/pint_compute.py \
    convert "5 meters" --to kg
# Error: Cannot convert '[length]' to '[mass]'

Related Skills

  • /math-mode - Full math orchestration (SymPy + Z3)
  • /sympy-compute - Symbolic computation

Signals

GitHub stars
4k
Forks
300
Last commit
Jan 2026
Advanced
Catalog kind
skill
Gateway key
pint-compute
Source
github.com/parcadei/continuous-claude-v3