pymoo · davila7 — Claude Code skill: optimization and installation
Use this skill to work through Python optimization problems, from a single objective to competing goals. It helps when you need to compare trade-offs or account for constraints.
npx claude-code-templates@latest --skill scientific/pymooWhat pymoo does
The skill guides Claude Code through setting up optimization tasks with pymoo in Python. For a single objective, it covers options such as genetic algorithms, differential evolution, and PSO. For competing objectives, it discusses NSGA-II and MOEA/D, with results that include decision variables, objective values, and constraint violations when constraints are part of the problem.
For multi-objective tasks, pymoo can produce a Pareto front for comparing candidate solutions. The many-objective example uses NSGA-III and requires reference directions; those must be supplied when configuring the algorithm. The skill also explains how to define a custom problem with ElementwiseProblem, variable bounds, objectives, and constraints.
It covers continuous, discrete, and mixed-variable problems, plus ZDT and DTLZ benchmarks. Python and pymoo are needed. Without reference directions, the described NSGA-III setup cannot run as shown.
What it helps with
- optimize a function with one objective
- compare trade-offs across competing goals
- encode constraints in an optimization problem
- benchmark algorithms on ZDT or DTLZ
- plot a Pareto front
Example prompts for the agent
- Help me define a Python optimization problem with two objectives and constraints.
- Choose a pymoo algorithm for five objectives and show how to provide its reference directions.
- Compare the Pareto solutions for the ZDT1 problem.
How to install pymoo
1claude-code-templates
npx claude-code-templates@latest --skill scientific/pymoo2Skills CLI (Vercel)
npx skills add davila7/claude-code-templates --skill pymoo -a claude-code3Manually: put the files in place
~/.claude/skills/pymoo/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pymoo/
Manually: put the files in place
.agents/skills/pymoo/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/pymoo/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davila7/claude-code-templates pymoo2Manually: put the files in place
.github/skills/pymoo/SKILL.mdPlatform CLI
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/scientific/pymooManually: put the files in place
.devin/skills/pymoo/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pymoo
How do I install pymoo in Claude Code?
Run npx claude-code-templates@latest --skill scientific/pymoo.
What does the pymoo skill do?
It helps configure Python optimization tasks, select algorithms, and inspect trade-offs between objectives.
What must I provide when using NSGA-III?
The setup requires reference directions, which you pass into the algorithm configuration.
Similar skills
All skills for Science and research →pymoo by other authors comes first.