tooluniverse-network-pharmacology

Compound-target-disease network construction and analysis for drug repurposing, polypharmacology discovery, and multi-target drug design. Uses STRING, BioGRID, ChEMBL, DGIdb, OMIM, OpenTargets. Use for off-target effect prediction, network-based drug repurposing, and identifying molecules with desired multi-target profile.

Quality

87%

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

Quality

Content

82%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.

A lean, highly actionable, well-sequenced network-pharmacology workflow with strong progressive-disclosure signaling. Main weaknesses are deferred inline code examples and a bundle where several referenced reference files are missing.

Suggestions

Add one minimal copy-paste code block inline (e.g., a Phase 3 Network_proximity call) so the common case is executable without opening ANALYSIS_PROCEDURES.md.

Add an explicit validation gate after Phase 0 (e.g., 'Do not proceed until every entity has ChEMBL/DrugBank/Disease IDs resolved') to strengthen the workflow's feedback loop.

Create the missing referenced files (ANALYSIS_PROCEDURES.md, REPORT_TEMPLATE.md, SCORING_REFERENCE.md, TOOL_REFERENCE.md, USE_PATTERNS.md, QUICK_START.md) so the progressive-disclosure structure is complete, or remove links to any not yet authored.

Dimension	Reasoning	Score
Conciseness	Dense, tool-action-oriented content with no padding and no explanation of concepts Claude already knows; every section (principles, scoring, phases, parameter notes, fallbacks) earns its tokens.	5 / 5
Actionability	Concrete per-phase tool lists, exact required parameters (e.g., DrugBank's four required params) and response-structure notes, plus a tested Network_proximity edge-mapping path; minor gap is that copy-paste code examples are deferred to ANALYSIS_PROCEDURES.md rather than included inline.	4 / 5
Workflow Clarity	Phases 0-8 are explicitly sequenced with per-phase tools, fallback chains as error-recovery loops, and a Phase 8 completeness checklist; minor gap is the absence of an explicit gate verifying ID resolution before proceeding to network construction.	4 / 5
Progressive Disclosure	Overview body points to well-signaled one-level-deep references (SCORING_REFERENCE, ANALYSIS_PROCEDURES, REPORT_TEMPLATE, TOOL_REFERENCE, USE_PATTERNS, QUICK_START) plus the verified scripts/network_proximity.py; however several referenced .md files are not actually present in the bundle, so structure is good but incomplete.	4 / 5
	Total	17 / 20 Passed

Description

92%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 states capabilities and usage triggers with concrete network-pharmacology terms. Only minor weakness is a slight reliance on technical phrasing over the most colloquial user synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Compound-target-disease network construction and analysis,' 'drug repurposing, polypharmacology discovery,' 'off-target effect prediction,' 'identifying molecules with desired multi-target profile' — covering the domain comprehensively rather than 1-2 actions.	5 / 5
Completeness	Explicitly answers both 'what' (network construction and analysis for repurposing/polypharmacology) and 'when' via the 'Use for off-target effect prediction, network-based drug repurposing, and identifying molecules with desired multi-target profile' clause.	5 / 5
Trigger Term Quality	Good coverage of natural terms ('off-target effect prediction,' 'network-based drug repurposing,' 'polypharmacology,' 'multi-target profile'), but leans technical and omits common synonyms such as 'drug repositioning.'	4 / 5
Distinctiveness Conflict Risk	Clear network-pharmacology niche with distinct C-T-D triggers and minimal overlap risk; the body further delegates non-network cases to sibling skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 10 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-network-pharmacology/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.