pymoo
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
86
83%
Does it follow best practices?
Impact
93%
2.06xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, technically precise description that clearly identifies its domain and lists specific algorithms and benchmarks. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms are excellent for the target audience of engineers and optimization practitioners.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about multi-objective optimization, evolutionary algorithms, Pareto-optimal solutions, or trade-off analysis in engineering design.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and algorithms: NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, and specific benchmarks (ZDT, DTLZ). These are concrete, identifiable techniques rather than vague language. | 3 / 3 |
Completeness | The 'what' is well-covered (multi-objective optimization framework with specific algorithms and benchmarks), and the domain is mentioned ('engineering design and optimization problems'), but there is no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural keywords a user working in this domain would use: 'multi-objective optimization', 'NSGA-II', 'NSGA-III', 'MOEA/D', 'Pareto fronts', 'constraint handling', 'ZDT', 'DTLZ', 'engineering design', 'optimization problems'. These are the exact terms practitioners would mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific algorithm names (NSGA-II, NSGA-III, MOEA/D) and benchmark suites (ZDT, DTLZ) that clearly carve out a niche. Unlikely to conflict with general optimization or single-objective optimization skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability and progressive disclosure. Every workflow includes executable code and clear references to deeper documentation. The main weakness is verbosity - sections like 'When to Use This Skill', basic concept explanations, and generic troubleshooting tips add tokens without proportional value for Claude.
Suggestions
Remove the 'When to Use This Skill' section entirely - Claude can infer applicability from the overview and workflows
Trim 'Core Concepts > Problem Types' definitions (single-objective, multi-objective, etc.) as these are basic optimization concepts Claude already knows
Condense the 'Performance and Troubleshooting' section to just the non-obvious tips, or move it to a reference file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary sections like 'When to Use This Skill' (Claude can infer this), 'Core Concepts' explaining what single/multi/many-objective means, and verbose 'Performance and Troubleshooting' tips that are largely general knowledge. The algorithm selection tables and workflow examples are valuable but the overall document is longer than needed. | 2 / 3 |
Actionability | Excellent actionable content throughout - every workflow includes complete, executable Python code examples with proper imports. Custom problem definitions show both constrained and unconstrained variants with concrete class implementations. Constraint formulation rules are specific and practical. | 3 / 3 |
Workflow Clarity | Workflows are clearly numbered and sequenced with explicit steps. Each workflow specifies when to use it, what algorithm to choose, and includes complete code. Constraint handling workflow includes feasibility checking (result.CV), and decision making workflow includes normalization validation. The multi-step processes are well-structured with clear progression. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear main document containing quick-start workflows and concise examples, with well-signaled one-level-deep references to detailed docs (references/algorithms.md, references/problems.md, etc.) and executable scripts. The 'See:' links are consistently placed after each workflow section. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (570 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- Reviewed
Table of Contents
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.