tooluniverse-systems-biology

Systems biology and pathway analysis integrating Reactome, KEGG, WikiPathways, BioCarta, NCI-Nature Pathway Interaction Database. Multi-database pathway enrichment, protein-pathway relationships, network reasoning. Use for pathway analysis on a gene list, multi-source pathway concordance, and systems-level interpretation across databases.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-systems-biology/SKILL.md

Quality

Content

63%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 pathway-analysis core is well-organized and actionable with strong tool/parameter guidance, but the skill is inflated by a large inlined enzyme-kinetics tangent that assumes Claude lacks basic biochemistry knowledge and inflates the file past an overview's scope.

Suggestions

Move the 'Enzyme Kinetics & Metabolic Analysis' and metabolic-flux sections into a separate reference file (or the cross-referenced computational-biophysics skill) and link to them one level deep, keeping SKILL.md a concise pathway-analysis overview.

Add a short inline Python example for the 'COMPUTE, DON'T DESCRIBE' step (e.g., sorting Enrichr/Reactome results by adjusted p-value) so the compute directive is executable rather than merely stated.

Trim explanations of textbook concepts (Michaelis-Menten, Hill cooperativity, inhibition types) to one-line reminders, since Claude already knows them; keep only the tool-specific lookup guidance.

Dimension	Reasoning	Score
Conciseness	The core pathway workflow is efficient, but a large inline enzyme-kinetics/metabolic-flux section (~70 lines of Michaelis-Menten, Hill equations, inhibition tables, and an 8-point troubleshooting list) explains textbook biochemistry Claude already knows and dilutes token budget.	3 / 5
Actionability	Concrete tool tables with exact parameter names, input formats, response-shape notes, and a 'Common Mistake' column give mostly executable guidance, though no inline Python is provided despite the 'COMPUTE, DON'T DESCRIBE' directive.	4 / 5
Workflow Clarity	The four-phase pipeline is clearly sequenced with per-phase decision logic, fallback chains, and explicit empty-result handling; operations are read-only so the destructive-validation cap does not apply, but no validate->fix->retry loop is present.	4 / 5
Progressive Disclosure	Headers and phases provide structure, but no bundle files exist and the enzyme-kinetics tangent (which belongs in the cross-referenced computational-biophysics skill or a separate reference) is inlined into a single ~265-line monolith.	3 / 5
	Total	14 / 20 Passed

Description

87%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.

A strong, specific description that clearly conveys the skill's purpose and when to use it, with concrete database names and trigger cases. Minor gains are possible by tightening action verbs and adding a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('pathway enrichment', 'protein-pathway relationships', 'network reasoning', 'multi-source pathway concordance', 'systems-level interpretation') with named databases, but the phrasing is somewhat abstract compared to the most action-rich anchor.	4 / 5
Completeness	Explicitly states both the 'what' (multi-database pathway enrichment and protein-pathway mapping) and the 'when' via a 'Use for...' clause with concrete trigger cases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'pathway analysis on a gene list' and 'systems-level interpretation' alongside database names; good coverage but a few common synonyms (e.g., 'enrichment', 'gene set') are lightly represented.	4 / 5
Distinctiveness Conflict Risk	The multi-database pathway-integration niche is clearly distinguished from generic bioinformatics, though it risks minor overlap with a sibling computational-biophysics skill it cross-references.	4 / 5
	Total	17 / 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: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-systems-biology/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.