tooluniverse-network-pharmacology

Construct and analyze compound-target-disease networks for drug repurposing, polypharmacology discovery, and systems pharmacology. Builds multi-layer networks from ChEMBL, OpenTargets, STRING, DrugBank, Reactome, FAERS, and 60+ other ToolUniverse tools. Calculates Network Pharmacology Scores (0-100), identifies repurposing candidates, predicts mechanisms, and analyzes polypharmacology. Use when users ask about drug repurposing via network analysis, multi-target drug effects, compound-target-disease networks, systems pharmacology, or polypharmacology.

Quality

88%

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

77%

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

A highly actionable, well-sequenced multi-tool pipeline with executable calls, a completeness checklist, and troubleshooting recovery, but it is a monolithic ~1300-line document with notable duplication between the inline walkthroughs and the appended reference/fallback tables. Splitting the API reference and report template into separate reference files would improve both conciseness and progressive disclosure.

Suggestions

Move the 'Tool Parameter Reference' tables and 'Response Format Notes' into a dedicated reference file (e.g. references/tool_reference.md) and link to it from each phase to eliminate duplication with the inline code blocks and reduce the main file's length.

Extract the full Phase 8 markdown report template into references/report_template.md, keeping only a short structure summary inline, to improve progressive disclosure and reduce token cost on load.

Consolidate the 'Fallback Strategies' table with the per-phase tool calls (or move it alongside the tool reference) so each tool's primary/fallback options live in one place instead of being repeated across sections.

Dimension	Reasoning	Score
Conciseness	The ~1300-line body duplicates tool calls across the inline phase walkthroughs, the 'Tool Parameter Reference' tables, the 'Response Format Notes', and the 'Fallback Strategies' table, so it could be meaningfully tightened. Not level 1 because most content is tool-specific API knowledge Claude does not already have rather than generic concept explanation, but not level 3 due to the repetition and length.	2 / 3
Actionability	Provides extensive executable `tu.tools.X(...)` calls with explicit parameter names, return-value shapes, and a copy-paste-ready report template. Not level 2 because the code is concrete and complete rather than pseudocode or abstract direction.	3 / 3
Workflow Clarity	Nine phases (0-8) are clearly sequenced, with 'report file FIRST' and 'Entity disambiguation FIRST' as upfront checkpoints, a mandatory end-of-report Completeness Checklist, and a Troubleshooting section giving error-recovery feedback loops. Not level 2 because validation checkpoints and recovery paths are explicit rather than implicit.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets are empty) and the skill is a single monolithic ~1300-line file, with the ~90-line API reference tables and ~150-line report template inlined as content that should be split into reference files. Not level 1 because sections are well organized with clear headings, but not level 3 because large reference-style blocks remain inline instead of being moved to one-level-deep files.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, third-person description that states concrete capabilities, names the underlying databases, and provides an explicit 'Use when...' trigger clause with natural user phrasing. It clearly answers both what the skill does and when to invoke it, with low conflict risk against sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (construct/analyze C-T-D networks, build multi-layer networks from named databases, calculate Network Pharmacology Scores 0-100, identify repurposing candidates, predict mechanisms, analyze polypharmacology), matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (construct/analyze networks, calculate scores, identify candidates) and 'when' via a clear 'Use when...' trigger clause. Not level 2 because the when-guidance is explicit rather than merely implied.	3 / 3
Trigger Term Quality	The 'Use when users ask about drug repurposing via network analysis, multi-target drug effects, compound-target-disease networks, systems pharmacology, or polypharmacology' clause covers natural phrasing a domain user would actually say. Not level 2 because common variations are well covered rather than partial.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear network-pharmacology niche with distinct triggers (network analysis, polypharmacology, systems pharmacology) that are unlikely to fire for the sibling repurposing/target-validation skills. Not level 2 because the scope is sharply narrowed to network-based analysis.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1313 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 5 suspicious	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/tooluniverse-network-pharmacology/SKILL.md
Commit: df37802

Reviewed: 2 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.