Skip to main content
skill CX Codex

second-order-odes — Claude Code skill: what it does, how to install

second-order-odes guides Claude Code through analytical and numerical workflows for solving second-order ordinary differential equations.

MIT ★ 3,951 updated 2026-01-26

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add parcadei/Continuous-Claude-v3 --skill second-order-odes -a claude-code
Open on GitHub

What second-order-odes does

This skill provides a decision tree for second-order ODEs. It first classifies the equation into constant coefficients, variable coefficients, or Cauchy-Euler form. For homogeneous cases, it finds characteristic roots, while non-homogeneous equations are tackled using undetermined coefficients or variation of parameters.

When analytical steps fall short, the workflow converts the second-order equation into a first-order system for numerical integration via SciPy solve_ivp. Boundary value problems are handled using scipy.integrate.solve_bvp or the shooting method.

Computation commands rely on uv run, requiring Python with scipy and sympy along with the repository scripts/sympy_compute.py. Without these tools in the environment, automated script execution will fail.

What it helps with

  • classify second-order ODEs by coefficient type and linearity
  • calculate characteristic roots for homogeneous equations
  • solve non-homogeneous ODEs using variation of parameters
  • convert a second-order ODE into a first-order system for SciPy solve_ivp
  • configure boundary value problem solving with solve_bvp

Example prompts for the agent

  • Solve the ODE y'' + 4y' + 4y = 0 with initial conditions y(0) = 1 and y'(0) = 0
  • Find a particular solution for y'' + y = sin(x) using variation of parameters
  • Integrate y'' = -y numerically on [0, 10] using solve_ivp

How to install second-order-odes

1Skills CLI (Vercel)

npx skills add parcadei/Continuous-Claude-v3 --skill second-order-odes -a claude-code

2Manually: put the files in place

~/.claude/skills/second-order-odes/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/second-order-odes/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about second-order-odes

How to install second-order-odes in Claude Code?

Run npx skills add parcadei/Continuous-Claude-v3 --skill second-order-odes -a claude-code or place the specification file at ~/.claude/skills/second-order-odes/SKILL.md.

What does second-order-odes do?

It outlines step-by-step mathematical strategies and shell commands to solve second-order differential equations symbolically and numerically.

What dependencies are needed to run the solver commands?

You need uv, a Python environment with scipy and sympy, and access to scripts/sympy_compute.py.

Source text

SKILL.md · MIT
---
name: second-order-odes
description: "Problem-solving strategies for second order odes in odes pdes"
allowed-tools: [Bash, Read]
---

# Second Order Odes

## When to Use

Use this skill when working on second-order-odes problems in odes pdes.

## Decision Tree


1. **Classify the ODE**
   - Constant coefficients: ay'' + by' + cy = f(x)?
   - Variable coefficients: y'' + P(x)y' + Q(x)y = R(x)?
   - Cauchy-Euler: x^2 y'' + bxy' + cy = 0?

2. **Homogeneous with Constant Coefficients**
   - Characteristic equation: ar^2 + br + c = 0
   - Distinct real roots: y = c1*e^{r1*x} + c2*e^{r2*x}
   - Repeated root: y = (c1 + c2*x)e^{r*x}
   - Complex roots a +/- bi: y = e^{ax}(c1*cos(bx) + c2*sin(bx))
   - `sympy_compute.py solve "a*r**2 + b*r + c" --var r`

3. **Particular Solution (Non-homogeneous)**
   - Undetermined coefficients: guess based on f(x)
   - Variation of parameters: y_p = u1*y1 + u2*y2
   - `sympy_compute.py dsolve "y'' + y = sin(x)"`

4. **Numerical Solution**
   - Convert to first-order system: let v = y', then v' = y''
   - `solve_ivp(system, [t0, tf], [y0, v0])`

5. **Boundary Value Problems**
   - Shooting method: guess initial slope, iterate
   - `scipy.integrate.solve_bvp(ode, bc, x, y_init)`


## Tool Commands

### Scipy_Solve_Ivp_System
```bash
uv run python -c "from scipy.integrate import solve_ivp; sol = solve_ivp(lambda t, Y: [Y[1], -Y[0]], [0, 10], [1, 0]); print('y(10) =', sol.y[0][-1])"
```

### Sympy_Charpoly
```bash
uv run python -m runtime.harness scripts/sympy_compute.py solve "r**2 + r + 1" --var r
```

### Sympy_Dsolve_2Nd
```bash
uv run python -m runtime.harness scripts/sympy_compute.py dsolve "Derivative(y,x,2) + y"
```

## Key Techniques

*From indexed textbooks:*

- [An Introduction to Numerical Analysis... (Z-Library)] Modern Numerical Methods for Ordinary Wiley, New York. User's guide for DVERK: A subroutine for solving non-stiff ODEs. Keller (1966), Analysis of Numerical Methods.
- [Elementary Differential Equations and... (Z-Library)] Riccati equation and that y1(t) = 1 is one solution. Use the transformation suggested in Problem 33, and nd the linear equation satised by v(t). Find v(t) in the case that x(t) = at, where a is a constant.
- [An Introduction to Numerical Analysis... (Z-Library)] Test results on initial value methods for non-stiff ordinary differential equations, SIAM J. Comparing numerical methods for Fehlberg, E. Klassische Runge-Kutta-Formeln vierter und niedrigerer Ordnumg mit Schrittweiten-Kontrolle und ihre Anwendung auf Warme leitungsprobleme, Computing 6, 61-71.
- [Elementary Differential Equations and... (Z-Library)] Two papers by Robert May cited in the text are R. May,“Biological Populations with Nonoverlapping Generations: Stable Points, Stable Cycles, and Chaos,” Science 186 (1974), pp. Biological Populations Obeying Difference Equations: Stable Points, Stable Cycles, and Chaos,” Journal of Theoretical Biology 51 (1975), pp.
- [An Introduction to Numerical Analysis... (Z-Library)] COLSYS: collocation software for boundary-value ODEs, ACM Trans. Numerical Solutions of Boundary Value Problems for Ordinary Differential Equations. Elementary Differential Equations and Boundary Value Problems, 4th ed.

## Cognitive Tools Reference

See `.claude/skills/math-mode/SKILL.md` for full tool documentation.

© parcadei · MIT · parcadei/Continuous-Claude-v3

Similar skills

All skills for Science and research →

From the same set161

The whole set →
sleuth sleuth — a subagent that systematically debugs issues by forming diagnostic questions, tracing code paths, analyzing logs, and documenting findings in a structured report. CX Codex ★ 3,951repo stars scribe scribe — a Claude Code subagent for tracking progress across sessions. It logs decisions, completed steps, and file lists into markdown handoffs and ledgers. CX Codex ★ 3,951repo stars parallel-agents The parallel-agents skill lays out a background-run and file-based workflow for coordinating agents. Use it to track parallel tasks without pulling each agent’s full response into context. CX Codex +1 ★ 3,951repo stars lebesgue-measure A skill for measure theory tasks focused on Lebesgue measure. Provides decision trees and computational tools to work through outer measure construction, the Carathéodory criterion, and properties of measurable sets. CX Codex +1 ★ 3,951repo stars math-model-selector The math-model-selector skill helps identify a mathematical framework when you have a problem but aren’t sure how to formalize it. Use it to choose a direction before working through the calculations. CX Codex +1 ★ 3,951repo stars first-order-odes first-order-odes — a skill for classifying and solving first-order differential equations. Guides you through equation type detection, selects a solution method, and provides commands for both analytical and numerical solving. CX Codex +1 ★ 3,951repo stars operator-theory operator-theory — a skill for Claude Code with strategies for functional analysis: bounded operator verification, spectral theory, compact operators. Runs Z3 and SymPy for proofs and computations. CX Codex +1 ★ 3,951repo stars root-finding root-finding is a Claude Code skill that selects a numerical method for finding equation or system roots based on available derivatives and a known interval. CX Codex +1 ★ 3,951repo stars

Project sponsors

Companies that keep this analytics open