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

78%

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 ./plugin/skills/tooluniverse-network-pharmacology/SKILL.md

Quality

Content

73%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 body is a well-architected, actionable multi-phase workflow with clear sequencing, validation checkpoints, and fallback feedback loops. Its main defect is progressive disclosure: most referenced reference files are missing from the bundle, so the carefully signaled navigation leads to dead ends.

Suggestions

Add the missing referenced files to the bundle (ANALYSIS_PROCEDURES.md, REPORT_TEMPLATE.md, SCORING_REFERENCE.md, TOOL_REFERENCE.md, USE_PATTERNS.md, QUICK_START.md) or remove their links so signaled references resolve to real content.

Inline a minimal executable code example for the core computation (e.g., building the C-T-D network and calling Network_proximity) so the skill is copy-paste actionable even if ANALYSIS_PROCEDURES.md is absent.

Tighten the Polypharmacology Reasoning prose into a compact decision rule to reduce token load without losing the desired-vs-promiscuous distinction.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with terse imperative headers and bullet lists and no basic-concept padding; the Polypharmacology Reasoning block and detailed Network_proximity parameter notes are domain-specific and justified but could be trimmed slightly.	4 / 5
Actionability	Concrete, actionable guidance via specific tool names, required parameters (DrugBank 4 params, FAERS operation/medicinalproduct, species='homo_sapiens'), Z-score thresholds, and a point-valued scoring formula, though no copy-paste executable code is inlined (deferred to reference files).	4 / 5
Workflow Clarity	A clear 8-phase sequence with per-phase tools, explicit validation checkpoints (entity disambiguation FIRST, report-first, 'No data is data', completeness checklist), and feedback loops via the Fallback Strategies section.	5 / 5
Progressive Disclosure	References are well-signaled and one level deep, but scored against the actual bundle 6 of 7 referenced paths (ANALYSIS_PROCEDURES.md, REPORT_TEMPLATE.md, SCORING_REFERENCE.md, TOOL_REFERENCE.md, USE_PATTERNS.md, QUICK_START.md) do not exist — only scripts/network_proximity.py is present — so navigation is largely broken.	2 / 5
	Total	15 / 20 Passed

Description

83%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 both capabilities and explicit trigger conditions in third person, with good keyword coverage and a well-defined niche. Minor redundancy and slight overlap with a sibling repurposing skill keep it just short of top marks on specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('network construction and analysis', 'polypharmacology discovery', 'multi-target drug design', 'off-target effect prediction') but 'construction and analysis' is slightly generic and 'drug repurposing' repeats, leaving minor coverage gaps rather than full comprehensiveness.	4 / 5
Completeness	Explicitly answers both 'what' (C-T-D network construction/analysis for repurposing, polypharmacology, multi-target design) and 'when' via a concrete 'Use for ...' trigger clause, satisfying the anchor for clear what-and-when with concrete triggers.	5 / 5
Trigger Term Quality	Good coverage of natural domain terms users would say ('drug repurposing', 'polypharmacology', 'multi-target drug design', 'off-target effect prediction') with synonyms, though a few common variations are absent and 'network pharmacology' appears only in the name.	4 / 5
Distinctiveness Conflict Risk	Clear C-T-D network pharmacology niche, but 'drug repurposing' overlaps with the sibling tooluniverse-drug-repurposing skill; the 'network-based' qualifier keeps it mostly distinct with only minor overlap risk.	4 / 5
	Total	17 / 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: plugin/skills/tooluniverse-network-pharmacology/SKILL.md
Commit: 7a0ceb2

Reviewed: 3 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.