multi-objective-optimization

Pareto-aware molecular design balancing multiple ADMET properties simultaneously. Based on MultiMol (Yu 2025) and MOLLM (Ran 2025).

Quality

65%

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/multi-objective-optimization/SKILL.md

Quality

Content

80%

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

The content is concise and highly actionable with executable workflows, but it lacks validation checkpoints for batch optimization operations and references a bundle script that is absent. Adding verification steps and the missing radar script would lift the weakest dimensions.

Suggestions

Add explicit validation/verification checkpoints to the workflows (e.g., confirm generated SMILES are valid, sanity-check the Pareto front, inspect objective gaps before reporting).

Provide the missing scripts/property_radar.py referenced in workflow 3 and the Script Reference table, or remove the reference.

Add a brief note on interpreting results and error recovery if RDKit fails to parse a candidate molecule.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient: terse bullets, one-line installs, and copy-paste workflows, with no padding explaining concepts Claude already knows.	3 / 3
Actionability	Workflows are fully executable commands with real flags, a reference SMILES, an objectives string, and output paths, plus a script-to-outputs reference table.	3 / 3
Workflow Clarity	The three workflows are clearly numbered and sequenced, but batch generation/ranking operations lack any validation or verification checkpoints, capping clarity at 2.	2 / 3
Progressive Disclosure	Sections are well organized with one-level-deep script references, but the referenced scripts/property_radar.py does not exist in the scripts/ bundle, slightly undermining navigation.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 states a clear domain and core action but omits explicit trigger guidance and multiple concrete actions, leaving it at the mid-level across all dimensions. Adding a 'Use when...' clause and listing specific actions would raise it.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., optimizing potency vs. hERG safety, balancing LogP and solubility, Pareto analysis of candidates).

Enumerate multiple concrete actions (generate candidates, rank by Pareto dominance, plot property radar) instead of the single 'balancing' phrase.

Include common natural phrasings ('drug design', 'lead optimization', 'ADMET profiling') alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Pareto-aware molecular design') and a concrete action ('balancing multiple ADMET properties simultaneously') but does not enumerate multiple specific concrete actions.	2 / 3
Completeness	Clearly states what the skill does but provides no explicit 'Use when...' trigger clause, capping completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant keywords ('Pareto-aware', 'ADMET properties', 'molecular design') but lacks common natural phrasings a user would say such as 'drug design' or 'lead optimization'.	2 / 3
Distinctiveness Conflict Risk	The Pareto/ADMET niche is fairly specific but could still overlap with related skills like molecular-optimization given the absence of distinct triggers.	2 / 3
	Total	8 / 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
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

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

Reviewed: 5 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.