Skip to main content
skill CX Codex

analytic-functions — Claude Code skill: complex analysis

analytic-functions is a Claude Code skill for checking analyticity, verifying Cauchy-Riemann equations, and computing power series and analytic continuations. It activates for theory of functions questions.

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 analytic-functions -a claude-code
Open on GitHub

What analytic-functions does

The skill provides a systematic framework for analyzing analytic functions. It includes a decision tree to determine whether a function is analytic at a point and which computational tool to apply. For Cauchy-Riemann verification, sympy_compute.py diff computes partial derivatives of u and v. Power series expansion uses sympy_compute.py series with a specified center. The z3_solve.py prove command automates condition verification.

The skill requires Bash and file read access. SymPy and Z3 are built into the environment. When you need to check analytic continuation or apply the identity theorem, the decision tree guides you through the correct sequence of steps.

What it helps with

  • verify whether a function is analytic at a given point
  • check Cauchy-Riemann equations
  • find the radius of convergence for a power series
  • construct an analytic continuation of a function beyond its original domain

Example prompts for the agent

  • Check if f(z) = exp(z) is analytic at the origin using Cauchy-Riemann equations
  • Compute the power series for sin(z) centered at zero and determine its radius of convergence
  • Verify that partial derivatives u and v satisfy du/dx = dv/dy and du/dy = -dv/dx

How to install analytic-functions

1Skills CLI (Vercel)

npx skills add parcadei/Continuous-Claude-v3 --skill analytic-functions -a claude-code

2Manually: put the files in place

~/.claude/skills/analytic-functions/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/analytic-functions/

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

Questions about analytic-functions

How do I install analytic-functions in Claude Code?

Run npx skills add parcadei/Continuous-Claude-v3 --skill analytic-functions -a claude-code, then view the documentation at ~/.claude/skills/analytic-functions/SKILL.md.

What does the analytic-functions skill do?

It provides a step-by-step decision tree for analyzing analytic functions: verifies Cauchy-Riemann conditions, computes power series, finds convergence radii, and constructs analytic continuations.

What tools are included in this skill?

The skill uses SymPy for symbolic computation of derivatives and series, and Z3 for automated verification of analyticity conditions. It works through Bash commands.

Source text

SKILL.md · MIT
---
name: analytic-functions
description: "Problem-solving strategies for analytic functions in complex analysis"
allowed-tools: [Bash, Read]
---

# Analytic Functions

## When to Use

Use this skill when working on analytic-functions problems in complex analysis.

## Decision Tree


1. **Is f analytic at z0?**
   - Check Cauchy-Riemann equations: du/dx = dv/dy, du/dy = -dv/dx
   - Check if f has power series expansion around z0
   - Check if f is differentiable in neighborhood of z0
   - `sympy_compute.py diff "u" --var x` and `sympy_compute.py diff "v" --var y`

2. **Cauchy-Riemann Verification**
   - Write f(z) = u(x,y) + iv(x,y)
   - Compute partial derivatives
   - Verify: du/dx = dv/dy AND du/dy = -dv/dx
   - `z3_solve.py prove "cauchy_riemann"`

3. **Power Series**
   - f(z) = sum_{n=0}^{inf} a_n (z - z0)^n
   - Radius of convergence: R = 1/limsup |a_n|^(1/n)
   - `sympy_compute.py series "f(z)" --var z --at z0`

4. **Analytic Continuation**
   - Extend f beyond original domain via power series
   - Identity theorem: if f = g on set with limit point, then f = g everywhere


## Tool Commands

### Sympy_Diff_U
```bash
uv run python -m runtime.harness scripts/sympy_compute.py diff "u(x,y)" --var x
```

### Sympy_Diff_V
```bash
uv run python -m runtime.harness scripts/sympy_compute.py diff "v(x,y)" --var y
```

### Sympy_Series
```bash
uv run python -m runtime.harness scripts/sympy_compute.py series "exp(z)" --var z --at 0
```

### Z3_Cauchy_Riemann
```bash
uv run python -m runtime.harness scripts/z3_solve.py prove "diff(u,x) == diff(v,y)"
```

## Key Techniques

*From indexed textbooks:*

- [Complex Analysis (Elias M. Stein, Ram... (Z-Library)] A deep theorem which we prove in the next chapter says that the converse is true: every holomorphic function is analytic. For that reason, we use the terms holomorphic and analytic interchangeably. PRELIMINARIES TO COMPLEX ANALYSIS Corollary 2.
- [Complex Analysis (Elias M. Stein, Ram... (Z-Library)] Cauchy, 1826 There is a general principle in the theory, already implicit in Riemann’s work, which states that analytic functions are in an essential way charac- terized by their singularities. That is to say, globally analytic functions are “eectively” determined by their zeros, and meromorphic functions by their zeros and poles. While these assertions cannot be formulated as precise general theorems, there are nevertheless signicant instances where this principle applies.
- [Complex analysis  an introduction to... (Z-Library)] EXERCISES If f(z) is analytic in the whole plane and real on the real axis, purely imaginary on the imaginary axis, show that f{z) is odd. COMPLEX INTEGRATION In the same situation, if v is the imaginary part of an analytic function f(z) in 12+, then f(z) has an analytic extension which satisfies f(z) = f(z). For the proof we construct the function V(z) which is equal to v(z) respect to this disk formed with the boundary values V.
- [Complex analysis  an introduction to... (Z-Library)] E is compact it can be covered by a finite number of the smaller disks, and we find that the p(/nJ are bounded on E, contrary to assumption. EXERCISES Prove that in any region 0 the family of analytic functions with positive real part is normal. Under what added condition is it locally bounded?
- [Complex Analysis (Elias M. Stein, Ram... (Z-Library)] Notice that the radius of convergence of the above series is 1. Show that f cannot be continued analytically past the unit disc. Hint: Suppose θ = 2πp/2k, where p and k are positive integers.

## 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 AI and ML →

From the same set161

The whole set →
contour-integrals contour-integrals — a Claude Code skill for solving contour integral problems in complex analysis. It guides you through choosing the right contour, locating poles, and applying the residue theorem to evaluate definite integrals. CX Codex +1 ★ 3,951repo stars arbiter arbiter runs unit and integration tests, investigates failures, and checks an implementation against acceptance criteria. Saves its report in the project. CX Codex ★ 3,951repo stars convex-optimization Skill for tackling convex optimization problems. Includes convexity verification, problem classification, and solution methods based on KKT conditions. CX Codex +1 ★ 3,951repo stars connectedness A skill for Claude Code with strategies for connectedness problems in topology. CX Codex +1 ★ 3,951repo stars math-intuition-builder math-intuition-builder develops mathematical understanding by guiding you through concrete examples, diagrams, and analogies before diving into calculation. Useful when you need solid intuition before solving a problem. CX Codex +1 ★ 3,951repo stars constrained-optimization Guides Claude Code through constrained optimization problems. It classifies constraints, formulates Lagrangians, and checks KKT optimality conditions. CX Codex +1 ★ 3,951repo stars integration-theory integration-theory — a Claude Code skill for solving measure-theoretic integration problems. Covers simple functions, monotone and dominated convergence, Fatou's lemma, and Fubini—Tonelli via sympy_compute.py and z3_solve.py commands. CX Codex +1 ★ 3,951repo stars math-progress-monitor math-progress-monitor — a skill that evaluates whether you're on the right track while solving a math problem and helps decide whether to keep going or switch strategies. Activates on phrases like "I'm stuck" or "is this approach working". CX Codex +1 ★ 3,951repo stars

Project sponsors

Companies that keep this analytics open