Math
Route natural-language math requests to SymPy, Z3, Pint, or explanation flows so your agent solves and explains without picking the wrong tool each time.
Overview
math is a journey-wide agent skill that routes computation and math explanation requests to SymPy, Z3, Pint, or explanatory flows—usable whenever a solo builder needs accurate symbolic or numeric work before committing.
Install
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill mathWhat is this skill?
- Single /math entry point routes requests to SymPy, Z3, Pint, or category-theory explanation
- SymPy script supports solve, integrate, diff, simplify, limit, and related commands via uv-run Python
- Trigger list covers calculate, compute, solve, integrate, eigenvalues, unit convert, and explain phrasing
- Explicit handoff: formal proofs should use /prove instead of this skill
- Allowed tools: Bash, Read, Write with high priority routing
- SymPy command surface includes solve, integrate, diff, simplify, and limit in the documented routing table
Adoption & trust: 661 installs on skills.sh; 3.8k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You ask your agent to solve or integrate an expression and it improvises hand-wavy algebra instead of calling the right symbolic or unit-conversion tool.
Who is it for?
Builders running agent projects with cc_math scripts who want consistent routing from plain-language math questions to SymPy, Z3, or Pint.
Skip if: Users who need publication-grade formal proofs without /prove, or teams forbidden from Bash execution in agent sessions.
When should I use this skill?
Triggers include calculate, compute, solve, integrate, derivative, eigenvalue, matrix, simplify, factor, limit, series, differential equation, unit convert, explain, what is, or how does.
What do I get? / Deliverables
Your request maps to a documented SymPy, Z3, or Pint command path with reproducible script invocation, or to structured explanation when you ask what is or how does.
- SymPy or Z3 computation output from scripted commands
- Unit conversion results via Pint
- Concise math explanations when routing to theory content
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Compute break-even units and margin formulas before you lock SaaS pricing.
Verify eigenvalues or integrals for algorithms your API will implement.
Generate symbolic expected results to cross-check unit tests for math helpers.
Simplify or solve lifecycle metric expressions when defining funnel equations.
Re-run limits or unit conversions while tuning production config thresholds.
How it compares
Unified math router skill for agents—not a standalone Wolfram Alpha MCP or a SymPy tutorial article.
Common Questions / FAQ
Who is math for?
Solo builders using continuous-claude-v3-style setups who want one /math skill to handle calculation, solving, integration, limits, linear algebra, units, and short explanations.
When should I use math?
Use it whenever triggers like calculate, compute, solve, integrate, eigenvalue, unit convert, or explain match—during Validate for model checks, Build for implementation math, Grow for metric formulas, or Operate when debugging numeric edge cases.
Is math safe to install?
It allows Bash and file writes to project scripts; review the Security Audits panel on this Prism page and restrict execution in untrusted repos.
SKILL.md
READMESKILL.md - Math
# /math - Unified Math Capabilities **One entry point for all computation and explanation.** I route to the right tool based on your request. For formal proofs, use `/prove` instead. --- ## Quick Examples | You Say | I Use | |---------|-------| | "Solve x² - 4 = 0" | SymPy solve | | "Integrate sin(x) from 0 to π" | SymPy integrate | | "Eigenvalues of [[1,2],[3,4]]" | SymPy eigenvalues | | "Is x² + 1 > 0 for all x?" | Z3 prove | | "Convert 5 miles to km" | Pint | | "Explain what a functor is" | Category theory skill | --- ## Computation Scripts ### SymPy (Symbolic Math) ```bash uv run python "$CLAUDE_PROJECT_DIR/.claude/scripts/cc_math/sympy_compute.py" <command> <args> ``` | Command | Description | Example | |---------|-------------|---------| | `solve` | Solve equations | `solve "x**2 - 4" --var x` | | `integrate` | Definite/indefinite integral | `integrate "sin(x)" --var x --lower 0 --upper pi` | | `diff` | Derivative | `diff "x**3" --var x` | | `simplify` | Simplify expression | `simplify "sin(x)**2 + cos(x)**2"` | | `limit` | Compute limit | `limit "sin(x)/x" --var x --point 0` | | `series` | Taylor expansion | `series "exp(x)" --var x --point 0 --n 5` | | `dsolve` | Solve ODE | `dsolve "f''(x) + f(x)" --func f --var x` | | `laplace` | Laplace transform | `laplace "sin(t)" --var t` | **Matrix Operations:** | Command | Description | |---------|-------------| | `det` | Determinant | | `eigenvalues` | Eigenvalues | | `eigenvectors` | Eigenvectors with multiplicities | | `inverse` | Matrix inverse | | `transpose` | Transpose | | `rref` | Row echelon form | | `rank` | Matrix rank | | `nullspace` | Null space basis | | `linsolve` | Linear system Ax=b | | `charpoly` | Characteristic polynomial | **Number Theory:** | Command | Description | |---------|-------------| | `factor` | Factor polynomial | | `factorint` | Prime factorization | | `isprime` | Primality test | | `gcd` | Greatest common divisor | | `lcm` | Least common multiple | | `modinverse` | Modular inverse | **Combinatorics:** | Command | Description | |---------|-------------| | `binomial` | C(n,k) | | `factorial` | n! | | `permutation` | P(n,k) | | `partition` | Integer partitions p(n) | | `catalan` | Catalan numbers | | `bell` | Bell numbers | --- ### Z3 (Constraint Solving) ```bash uv run python "$CLAUDE_PROJECT_DIR/.claude/scripts/cc_math/z3_solve.py" <command> <args> ``` | Command | Use Case | |---------|----------| | `sat` | Is this satisfiable? | | `prove` | Is this always true? | | `optimize` | Find min/max subject to constraints | --- ### Pint (Units) ```bash uv run python "$CLAUDE_PROJECT_DIR/.claude/scripts/cc_math/pint_compute.py" convert <value> <from_unit> <to_unit> ``` Example: `convert 5 miles kilometers` --- ### Math Router (Auto-Route) ```bash uv run python "$CLAUDE_PROJECT_DIR/.claude/scripts/cc_math/math_router.py" route "<natural language request>" ``` Returns the exact command to run. Use when unsure which script. --- ## Topic Skills (For Explanation) When the request is "explain X" or "what is X", I reference these: | Topic | Skill Location | Key Concepts | |-------|----------------|--------------| | **Abstract Algebra** | `math/abstract-algebra/` | Groups, rings, fields, homomorphisms | | **Category Theory** | `math/category-theory/` | Functors, natural transformations, limits | | **Complex Analysis** | `math/complex-analysis/` | Analytic functions, residues, contour integrals | | **Functional Analysis** | `math/functional-analysis/` | Banach spaces, operators, spectra | | **Linear Algebra** | `math/linear-algebra/` | Matrices, eigenspaces,