Math
Route math problems to the right tool—compute, solve, explain
What You Can Do
Solve algebraic and transcendental equations, compute derivatives and integrals, perform matrix operations, simplify expressions, compute limits and series expansions, solve differential equations, and convert units. Claude automatically selects the best computational engine for your problem—SymPy for symbolic math, Z3 for logical proofs, Pint for unit conversion—so you get fast, verified answers without manual tool selection.
Features
symbolic and numerical solutions for polynomials, transcendental, and systems of equations
derivatives, indefinite/definite integrals, limits, Taylor series, and Laplace transforms
eigenvalues, eigenvectors, determinants, inverses, rank, row echelon form, and transpose
solve ODEs and systems with initial conditions using symbolic methods
algebraic, trigonometric, and logarithmic simplification with step-by-step reduction
convert between physical units (distance, mass, temperature, etc.) with automatic scaling
route to /prove for machine-verified formal proofs in Lean 4 or category theory
Claude explains mathematical concepts, theorems, and results in plain English
Example Output
Example 1: Solve a differential equation
Input: "Solve y'' + y = cos(x)"
Output:
General solution: y(x) = C₁·sin(x) + C₂·cos(x) + (x/2)·sin(x)
Explanation: The homogeneous solution is C₁·sin(x) + C₂·cos(x). The particular solution uses the method of undetermined coefficients, yielding (x/2)·sin(x).
Example 2: Eigenvalues of a matrix
Input: "Find eigenvalues and eigenvectors of [[2, 1], [1, 2]]"
Output:
Eigenvalues: λ₁ = 3, λ₂ = 1
Eigenvector for λ = 3: [1, 1]
Eigenvector for λ = 1: [1, -1]
Example 3: Unit conversion
Input: "Convert 5 miles per hour to meters per second"
Output: 5 mi/h = 2.24 m/s
What's Included
- SKILL.md: Core skill definition with triggers and tool routing logic
- SymPy computation scripts: Pre-built Python modules for solve, integrate, diff, simplify, limit, series, dsolve, Laplace, and matrix operations
- Z3 integration: Logical proof engine for inequality verification and boolean satisfiability
- Pint unit conversion module: Comprehensive unit database with automatic dimensional analysis
- Quick reference table: Command syntax and examples for all 20+ math operations
Who It's For
- Engineers — solve systems of equations, compute eigenvalues, verify design constraints
- Research scientists — symbolic integration, differential equation solving, dimensional analysis
- Mathematics tutors — explain concepts, verify student solutions, generate worked examples
- Physics students — Laplace transforms, ODE solving, unit conversion for problem sets
- Data scientists — matrix algebra, eigenvalue decomposition, symbolic variable handling
Best For
- Solving algebraic and transcendental equations with symbolic verification
- Calculus operations (derivatives, integrals, limits) with step-by-step breakdowns
- Linear algebra tasks (eigenvalues, matrix rank, inversion) for ML and scientific computing
- Differential equation solving (ODEs and systems) for physics and engineering
- Unit conversion and dimensional analysis across engineering and scientific domains
- Expression simplification and mathematical proof assistance
You might also like
You can deploy this agent to execute specific implementation tasks within a larger development plan. It operates independently with fresh context, follows test-driven development principles for every code change, and creates comprehensive handoff documentation that captures progress, decisions, and learnings for the next task executor. This ensures consistent code quality, prevents rework, and maintains continuity across distributed implementation efforts.
by parcadei
This skill maps construction claims as interdependent probability states rather than isolated analyses, allowing you to evaluate how changes in one contractual interpretation cascade through damages calculations, delay causation, and liability allocation. You can simultaneously model competing scenarios—concurrent causation, ambiguous change order triggers, insurance coverage dependencies—and identify which settlement positions minimize exposure across all correlated outcomes, not just single interpretations.
by parcadei
You can formally verify mathematical proofs by translating theorems into Lean 4 code, leveraging Mathlib's extensive library of formalized mathematics. The skill guides you through researching existing lemmas, designing proof strategies, testing approaches, implementing formal proofs, and verifying correctness—turning informal mathematical claims into machine-checked theorems without requiring deep Lean syntax expertise.
by parcadei
You can confidently navigate complex statistical analyses by working through structured workflows that match your research question and data type to the right test. The skill guides you through assumption validation, helps you interpret results accurately without common pitfalls, and walks you through regression diagnostics with full transparency about what your findings actually mean.
by moonwell-fi
You can systematically analyze construction estimates by breaking down components, validating labor and material pricing against market data, identifying embedded errors or outdated assumptions, and applying data-driven contingency allocation. Claude helps you produce risk-adjusted cost projections that are defensible to stakeholders and competitive in bid scenarios, reducing estimate variance and catching pricing gaps before client submission.
by parcadei
You can rapidly process multiple subcontractor bid responses—from trade contractors, material suppliers, and specialty vendors—into a cohesive, auditable estimate structure. Claude extracts key bid components, identifies pricing inconsistencies against benchmarks or prior projects, flags scope gaps and exclusions, and organizes everything by CSI division for seamless estimate assembly. This eliminates manual spreadsheet comparison and reduces the risk of overlooked scope omissions or pricing anomalies when managing 15+ concurrent bids.
by parcadei
You'll follow the strict TDD workflow: write a failing test that defines expected behavior, verify it fails, write minimal production code to pass the test, then refactor for quality. This approach ensures complete test coverage, catches bugs early, and produces well-designed code backed by comprehensive test suites. Claude guides you through each phase with examples and enforces TDD principles to prevent shortcuts.
by parcadei
You can create reusable slash commands that execute instantly in Claude Code conversations. Commands support bash execution, file references, arguments, and tool permissions. Use built-in commands like /cost, /review, /memory, and /clear, or define custom project and personal commands stored in .claude/commands/ or ~/.claude/commands/.
by parcadei