Name: tooluniverse-drug-mechanism-research
Rating: 65.60000000000001 (1 reviews)
Author: mims-harvard

tooluniverse-drug-mechanism-research

Trace drug mechanism of action — primary target → downstream signaling → pathway perturbation → tissue/organ effect → clinical outcome. Uses DrugBank, ChEMBL, KEGG, Reactome, STRING. Use for understanding how a drug works, identifying off-target effects, mechanism-based combination therapy design, and writing mechanism sections of reports.

Quality

79%

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 ./plugins/tooluniverse/skills/tooluniverse-drug-mechanism-research/SKILL.md

The canonical home for this skill is tooluniverse-drug-mechanism-research in mims-harvard/ToolUniverse

Quality

Content

75%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 highly actionable, well-sequenced research workflow with concrete executable tool calls and strong fallback guidance. The main weakness is conciseness — several step openings restate pharmacology basics Claude already knows — and the absence of any progressive-disclosure split for the larger reference-style sections.

Suggestions

Trim the concept-explanation openings of Steps 3-7 ('Most drugs bind more than one target…', 'A drug target does not work in isolation…') to assume Claude's pharmacology knowledge.

Consider moving the full report-structure template and the drug-comparison guidance into a reference file to reduce SKILL.md length and improve progressive disclosure.

Add a brief verification checkpoint in Step 8 (e.g. confirm each report section has at least one sourced finding) to lift workflow clarity toward the top anchor.

Dimension	Reasoning	Score
Conciseness	The bulk is executable code and useful reasoning strategies, but several steps open with pharmacology concepts Claude already knows ('Most drugs bind more than one target', 'A drug target does not work in isolation', 'Drug labels describe WHAT the drug does').	3 / 5
Actionability	Copy-paste-ready tu.tools.* calls with real identifiers (CHEMBL1431, metformin, PRKAA1), a fallback strategies table, and a report template fully cover the common investigation cases.	5 / 5
Workflow Clarity	A clear 8-step sequence with fallbacks, 'Known issue' notes, and an evidence hierarchy; read-only research so the destructive/batch cap does not apply, but explicit verification checkpoints are absent.	4 / 5
Progressive Disclosure	Single ~280-line file with well-organized section headers and no bundle files to reference; the report template and comparison guidance are reasonably inline for a cohesive workflow, with only minor organization gaps.	4 / 5
	Total	16 / 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 defines both what the skill does and when to use it, anchored by a concrete mechanism chain and named data sources. Minor gaps in natural-term synonyms and a small overlap risk with related drug skills keep it just below the top anchor on two dimensions.

Suggestions

Add a couple of common synonyms (e.g. 'pharmacodynamics', 'side effects') to broaden natural trigger coverage.

Sharpen the action list toward discrete tool actions (e.g. 'Query DrugBank/ChEMBL for targets, map pathways in KEGG/Reactome') rather than framing everything as use-cases.

Dimension	Reasoning	Score
Specificity	Lists a concrete mechanism-tracing chain (target → downstream → pathway → organ → clinical outcome), names five databases, and enumerates four specific use cases, but several actions are phrased as use-cases rather than discrete tool actions.	4 / 5
Completeness	Clearly states the 'what' (trace the full MOA chain) and an explicit 'Use for…' clause with concrete trigger phrases, satisfying both halves comprehensively.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('mechanism of action', 'how a drug works', 'off-target effects') with good coverage, but a few common synonyms (e.g. pharmacodynamics, side effects) are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear drug-MOA niche and names specific databases, with only minor overlap risk against sibling pharmacology skills.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-drug-mechanism-research/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.