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 ./backend/cli/skills/coding/pymoo/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

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

The skill body is highly actionable with executable examples and a clean progressive-disclosure structure pointing to real reference and script bundles. It loses points on conciseness (repetition and an undated version note) and on workflow clarity for lacking explicit validation checkpoints.

Suggestions

Tighten the Overview and 'When to Use' sections to avoid restating the description, and consolidate the inline 'See:' pointers with the Resources section to remove duplication.

Move or frame the 'pymoo 0.6.x' version note under a clearly labeled compatibility/deprecation section so time-sensitive information does not bloat the main content.

Add explicit validation checkpoints to optimization workflows, e.g., verify convergence/feasibility (result.CV, hypervolume, or n_eval) before declaring a result final.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with relevant executable code, but the Overview restates the frontmatter, the 'When to Use' section lists nine bullets, the Resources section re-lists references already signposted inline, and a version string ('pymoo 0.6.x') sits outside a deprecated/old-patterns section, all of which could be tightened.	2 / 3
Actionability	Each workflow provides fully executable, copy-paste-ready Python with concrete imports, parameters, and result extraction, plus tables giving specific algorithm choices — matching the anchor for executable, specific examples.	3 / 3
Workflow Clarity	Workflows are clearly numbered and sequenced with 'When', 'Steps', and 'Algorithm choice' labels, but they lack explicit validation/verification checkpoints (e.g., checking a convergence metric or feasibility before proceeding), leaving feedback loops implicit.	2 / 3
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references to real bundle files (verified: references/algorithms.md, references/problems.md, references/operators.md, references/visualization.md, references/constraints_mcdm.md and the five scripts/*_example.py all exist), with content appropriately split and easy 'See:' navigation.	3 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 benchmark suites in third-person voice. It is held back by the absence of an explicit 'Use when...' trigger clause and only partial coverage of natural user trigger terms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when solving multi-objective or constrained optimization problems, computing Pareto fronts, or benchmarking evolutionary algorithms.'

Broaden trigger terms to include lay phrasings users actually say, such as 'trade-offs', 'evolutionary algorithms', and 'optimization'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ)' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Clearly answers 'what' (a framework with named algorithms and benchmarks), but 'when' is only implied by the trailing 'for engineering design and optimization problems' with no explicit 'Use when...' trigger clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant domain keywords ('multi-objective optimization', 'Pareto fronts', 'constraint handling') but misses common natural variations a user might say such as 'trade-off', 'evolutionary algorithm', or 'optimization problem', so coverage is good but not exhaustive.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (multi-objective optimization with named evolutionary algorithms) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (571 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/pymoo/SKILL.md
Commit: dc00e07

Reviewed: 8 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.