Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Deterministic mathematical computation using SymPy. Use for ANY math operation requiring exact/verified results - basic arithmetic, algebra (simplify, expand, factor, solve equations), calculus (derivatives, integrals, limits, series), linear algebra (matrices, determinants, eigenvalues), trigonometry, number theory (primes, GCD/LCM, factorization), and statistics. Ensures mathematical accuracy by using symbolic computation rather than LLM estimation.
.claude/skills/foryourhealth111-pixel-math-tools/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-20 | ✓→✓ | = Same ✓ | 105% | 0% |
| case-21 | ✓→✓ | = Same ✓ | 58% | 0% |
Deterministic mathematical computation engine using SymPy. All calculations use symbolic math - no LLM estimation.
Use this skill whenever mathematical accuracy matters:
Run the calculator script with operation and arguments:
bashpython scripts/math_calculator.py <operation> <args...>
All results return JSON with result, latex, and numeric fields.
bashpython scripts/math_calculator.py add 5 3 2 # 10 python scripts/math_calculator.py multiply 2 3 4 # 24 python scripts/math_calculator.py divide 10 4 # 5/2 (exact) python scripts/math_calculator.py sqrt 8 # 2*sqrt(2) python scripts/math_calculator.py factorial 10 # 3628800
bash# Simplify python scripts/math_calculator.py simplify "(x**2 - 1)/(x - 1)" # → x + 1 # Expand python scripts/math_calculator.py expand "(x + 1)**3" # → x**3 + 3*x**2 + 3*x + 1 # Factor python scripts/math_calculator.py factor "x**3 - 8" # → (x - 2)*(x**2 + 2*x + 4) # Solve equations python scripts/math_calculator.py solve "x**2 - 5*x + 6" x # → [2, 3] python scripts/math_calculator.py solve "2*x + 3 = 7" x # → [2]
bash# Derivative python scripts/math_calculator.py derivative "x**3 + sin(x)" x # → 3*x**2 + cos(x) # Second derivative python scripts/math_calculator.py derivative "x**4" x 2 # → 12*x**2 # Indefinite integral python scripts/math_calculator.py integrate "x**2" x # → x**3/3 # Definite integral python scripts/math_calculator.py integrate "x**2" x 0 1 # → 1/3 # Limit python scripts/math_calculator.py limit "sin(x)/x" x 0 # → 1 # Limit at infinity python scripts/math_calculator.py limit "(x**2 + 1)/(x**2 - 1)" x oo # → 1 # Taylor series python scripts/math_calculator.py series "exp(x)" x 0 5 # → 1 + x + x**2/2 + x**3/6 + x**4/24 + O(x**5)
bash# Determinant python scripts/math_calculator.py det '[[1,2],[3,4]]' # → -2 # Inverse python scripts/math_calculator.py inverse '[[1,2],[3,4]]' # Eigenvalues python scripts/math_calculator.py eigenvalues '[[4,2],[1,3]]' # → {5: 1, 2: 1} # RREF python scripts/math_calculator.py rref '[[1,2,3],[4,5,6]]'
bashpython scripts/math_calculator.py gcd 24 36 48 # 12 python scripts/math_calculator.py lcm 4 6 8 # 24 python scripts/math_calculator.py prime_factors 360 # 2^3 × 3^2 × 5 python scripts/math_calculator.py is_prime 17 # true python scripts/math_calculator.py nth_prime 100 # 541 python scripts/math_calculator.py binomial 10 3 # 120
bashpython scripts/math_calculator.py mean '[1,2,3,4,5]' # 3 python scripts/math_calculator.py variance '[1,2,3,4,5]' # 2 python scripts/math_calculator.py std_dev '[1,2,3,4,5]' # sqrt(2)
bash# Numerical evaluation with precision python scripts/math_calculator.py evaluate "pi" 50 # LaTeX output python scripts/math_calculator.py latex "x**2 + 1/x" # → x^{2} + \frac{1}{x} # Compare expressions python scripts/math_calculator.py compare "(x+1)**2" "x**2 + 2*x + 1" # → equal: true
x**2 or x^22*x or 2x (implicit)sin(x), cos(x), exp(x), log(x), sqrt(x)pi, E, I (imaginary), oo (infinity)For operations requiring structured input:
bash# Solve system of equations python scripts/math_calculator.py solve_system \ '{"equations": ["x + y = 10", "x - y = 2"], "variables": ["x", "y"]}' # Substitute values python scripts/math_calculator.py substitute \ '{"expr_str": "x**2 + y", "substitutions": {"x": 3, "y": 2}}' # Matrix multiplication python scripts/math_calculator.py matrix_mult \ '{"matrix_a": [[1,2],[3,4]], "matrix_b": [[5,6],[7,8]]}'
See references/api_reference.md for complete documentation of all operations, including:
Requires SymPy:
bashpip install sympy
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,738 | 5,175 | -33% | 1 | 1 | 0% | 1,679 | 1,791 | +7% | 0 | 0 | — |
case-02 | fail→fail | 2,970 | 5,361 | +81% | 1 | 1 | 0% | 563 | 1,796 | +219% | 0 | 0 | — |
case-03 | fail→fail | 9,656 | 16,387 | +70% | 1 | 1 | 0% | 2,318 | 1,801 | -22% | 0 | 0 | — |
case-04 | fail→pass | 5,149 | 1,774 | -66% | 1 | 1 | 0% | 1,049 | 1,761 | +68% | 0 | 0 | — |
case-05 | fail→pass | 6,888 | 3,123 | -55% | 1 | 1 | 0% | 1,191 | 1,989 | +67% | 0 | 0 | — |
case-06 | fail→pass | 6,272 | 2,515 | -60% | 1 | 1 | 0% | 1,098 | 1,888 | +72% | 0 | 0 | — |
case-07 | fail→fail | 3,972 | 6,858 | +73% | 1 | 1 | 0% | 811 | 1,828 | +125% | 0 | 0 | — |
case-08 | fail→fail | 4,164 | 5,463 | +31% | 1 | 1 | 0% | 794 | 1,713 | +116% | 0 | 0 | — |
case-09 | fail→fail | 4,455 | 1,539 | -65% | 1 | 1 | 0% | 689 | 1,777 | +158% | 0 | 0 | — |
case-10 | fail→fail | 7,930 | 5,087 | -36% | 1 | 1 | 0% | 1,464 | 1,659 | +13% | 0 | 0 | — |
case-11 | fail→fail | 4,099 | 3,880 | -5% | 1 | 1 | 0% | 640 | 1,652 | +158% | 0 | 0 | — |
case-12 | fail→fail | 5,798 | 5,100 | -12% | 1 | 1 | 0% | 1,001 | 1,698 | +70% | 0 | 0 | — |
case-13 | fail→fail | 10,953 | 4,444 | -59% | 1 | 1 | 0% | 2,130 | 1,662 | -22% | 0 | 0 | — |
case-14 | fail→fail | 4,966 | 7,643 | +54% | 1 | 1 | 0% | 772 | 2,164 | +180% | 0 | 0 | — |
case-15 | fail→fail | 6,243 | 3,918 | -37% | 1 | 1 | 0% | 1,342 | 1,679 | +25% | 0 | 0 | — |
case-16 | fail→fail | 2,008 | 4,295 | +114% | 1 | 1 | 0% | 305 | 1,638 | +437% | 0 | 0 | — |
case-17 | fail→fail | 6,446 | 4,859 | -25% | 1 | 1 | 0% | 1,273 | 1,695 | +33% | 0 | 0 | — |
case-18 | fail→fail | 4,989 | 6,288 | +26% | 1 | 1 | 0% | 810 | 1,673 | +107% | 0 | 0 | — |
case-19 | fail→fail | 3,515 | 4,683 | +33% | 1 | 1 | 0% | 578 | 1,678 | +190% | 0 | 0 | — |
case-20 | pass→pass | 8,719 | 14,552 | +67% | 1 | 1 | 0% | 1,421 | 2,918 | +105% | 0 | 0 | — |
case-21 | pass→pass | 13,110 | 10,651 | -19% | 1 | 1 | 0% | 2,267 | 3,571 | +58% | 0 | 0 | — |
case-22 | pass→pass | 5,185 | 4,890 | -6% | 1 | 1 | 0% | 1,195 | 2,558 | +114% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 7 counted toward the lift figure. The other 15 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +14 percentage points is the difference between those two pass rates over the 7 comparable cases. 12 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.