pymoo

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/pymoo/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with strong progressive disclosure, concrete executable snippets, and clear workflow/selection guidance. The main drag is mild over-explanation of basic optimization concepts Claude already knows and a placeholder in the flagship example.

Suggestions

Trim or remove the basic 'Problem Types' definitions (e.g., what single- vs multi-objective means) since Claude already knows these; keep only pymoo-specific distinctions.

Make the flagship minimize() example fully self-contained by defining a concrete problem and algorithm inline, so it is copy-paste runnable end-to-end.

Avoid repeating the frontmatter description verbatim in the Overview; have the Overview add new context instead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material, but includes unnecessary explanation of concepts Claude already knows (e.g., 'Single-objective: One objective to minimize/maximize', 'Multi-objective: 2-3 conflicting objectives') and an Overview that repeats the frontmatter description.	3 / 5
Actionability	Provides multiple concrete, copy-paste-ready snippets (get_problem examples, GA with SBX/PM operator config, run commands), but the central minimize() example uses placeholder problem/algorithm objects rather than a fully self-contained runnable example.	4 / 5
Workflow Clarity	A numbered 9-workflow table plus algorithm-selection decision tables give a clear sequenced path, and the troubleshooting section offers problem-to-solution recovery guidance; minor validation/checkpoint gaps exist but optimization is not inherently destructive.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview pointing to seven real one-level-deep reference files (verified to exist, no nested references) and five executable scripts, with well-signaled 'See: references/X.md' navigation throughout.	5 / 5
	Total	16 / 20 Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive, naming concrete algorithms and benchmarks that clearly demarcate the skill's niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the invocation guidance only weakly implied.

Suggestions

Add an explicit 'Use when...' clause listing concrete triggers (e.g., 'Use when solving multi-objective or constrained optimization, computing Pareto fronts, or benchmarking evolutionary algorithms').

Include natural synonyms users might say, such as 'evolutionary algorithms', 'genetic algorithms', or 'trade-off analysis', to broaden trigger coverage.

Consider leading with action verbs (e.g., 'Solves', 'Computes', 'Benchmarks') to frame capabilities as concrete actions rather than a list of named features.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete, specific capabilities ('NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ)'), though these are named techniques/features rather than explicit action verbs.	4 / 5
Completeness	Has a clear 'what' (multi-objective optimization framework with named algorithms), but the 'when' is only weakly implied via 'for engineering design and optimization problems' with no explicit 'Use when...' clause, which caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('multi-objective optimization', 'Pareto fronts', 'NSGA-II', 'constraint handling', 'optimization problems') with good coverage; a few common synonyms like 'evolutionary algorithms' or 'trade-offs' are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (multi-objective optimization) anchored by distinctive named algorithms (NSGA-II/III, MOEA/D, Pareto fronts), giving it minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/pymoo/SKILL.md
Commit: 1e5eeff

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.