Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/pymoo
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
Passed 20 of 22 test cases with the skill, and 19 of 22 without it.
1 fixed19 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
When running my constrained optimization model in pymoo, the algorithm struggles to produce valid candidate solutions because the feasible region is very small. Could you provide a structured troubleshooting solution and Python code snippet that explains how constraints should be mathematically aligned with pymoo conventions, along with recommended algorithmic strategies or constraint handling methods for heavy constraint conditions?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends SRES or ISRES for heavily constrained problems with small feasible regions. | Missed | Passed |
| Explains that inequality constraints in pymoo must be formulated such that g(x) <= 0 represents feasibility. | Passed | Passed |
The instructions your model reads when the skill loads.
-----|----------|--------------| | GA | General-purpose | Flexible, customizable operators | | DE | Continuous optimization | Good global search | | PSO | Smooth landscapes | Fast convergence | | CMA-ES | Difficult/noisy problems | Self-adapting |
| Algorithm | Best For | Key Features |
|---|---|---|
| NSGA-II | Standard benchmark | Fast, reliable, well-tested |
| R-NSGA-II | Preference regions | Reference point guidance |
| MOEA/D | Decomposable problems | Scalarization approach |
| Algorithm | Best For | Key Features |
|---|---|---|
| NSGA-III | 4-15 objectives | Reference direction-based |
| RVEA | Adaptive search | Reference vector evolution |
| AGE-MOEA | Complex landscapes | Adaptive geometry |
| Approach | Algorithm | When to Use |
|---|---|---|
| Feasibility-first | Any algorithm | Large feasible region |
| Specialized | SRES, ISRES | Heavy constraints |
| Penalty | GA + penalty | Algorithm compatibility |
See: references/algorithms.md for comprehensive algorithm reference
from pymoo.problems import get_problem
# Single-objective
problem = get_problem("rastrigin", n_var=10)
test cases passed, vs 19 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.