Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

pymoo Multi-Objective Optimization

A pymoo expert skill that guides Claude through NSGA-II/III, MOEA/D and other evolutionary algorithms to compute Pareto fronts.

Data & AnalyticsIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Turns Claude into a competent pymoo user for single-, multi-, and many-objective optimization in Python. It ships algorithm selection tables (GA, DE, PSO, CMA-ES for single objective; NSGA-II, SPEA2, MOEA/D for 2–3 objectives; NSGA-III, RVEA, AGE-MOEA for 4+), the unified minimize() interface, three problem-definition styles (Problem, ElementwiseProblem, FunctionalProblem), constraint handling, genetic operator customization, Pareto-front visualization, MCDM decision making, and parallel evaluation. Nine runnable workflows, benchmark suites (ZDT, DTLZ, WFG) and a troubleshooting checklist are referenced from bundled docs and example scripts.

Who it's for

  • Design engineers balancing conflicting goals (cost vs performance, weight vs strength)
  • Researchers and grad students benchmarking evolutionary algorithms
  • Data scientists tackling mixed-variable (continuous/integer/binary/categorical) problems
  • Decision analysts who must pick one solution out of a Pareto set

Examples

  1. "Minimize part weight and manufacturing cost simultaneously with NSGA-II" → generates a custom ElementwiseProblem plus a Pareto scatter plot.
  2. "I have six objectives — which algorithm?" → recommends NSGA-III and shows how to build reference directions.
  3. "Almost no feasible solutions appear" → walks through g(x) ≤ 0 formulation, repair operators, and SRES/ISRES alternatives.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/pymoo folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/pymoo/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/pymoo ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Terminal on macOS/Linux, Git Bash on Windows).
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/pymoo ~/.claude/skills/
  5. Install the Python dependencies: uv pip install "pymoo==0.6.1.6" matplotlib (plain pip install works too).
  6. Restart Claude Code and ask something like "Use pymoo to solve this two-objective design problem."
  7. Sanity-check the bundled example: python3 ~/.claude/skills/pymoo/scripts/multi_objective_example.py
View source on GitHub ↗License: MIT