tooluniverse-small-molecule-discovery

Small molecule identification, characterization, and procurement — PubChem, ChEMBL, BindingDB, ADMET-AI, SwissADME, eMolecules, Enamine. Covers compound name to structure to activity to ADMET properties to commercial sourcing. Use for chemical biology, lead identification, probe selection, and the full small-molecule discovery pipeline.

Quality

88%

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

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 tool skill with concrete examples and good error-recovery guidance. Its main weaknesses are token redundancy (duplicate tool tables, Claude-known concept explanations) and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Collapse the 'Key Tools' and 'Tool Parameter Reference' tables into a single table to remove redundant tokens.

Trim or remove the 'Domain Reasoning' explanation of Lipinski's Rule of 5, which Claude already knows, keeping only the skill-specific guidance.

Move the detailed tool parameter reference and/or common-pattern catalog into a separate referenced file (e.g. references/TOOLS.md) and signal it from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and tool-specific, but the 'Domain Reasoning' section re-explains Lipinski's Rule of 5 (which Claude knows) and the 'Key Tools' and 'Tool Parameter Reference' tables overlap heavily, adding redundant tokens.	2 / 3
Actionability	Concrete, executable tool calls with real parameters appear throughout (e.g. ChEMBL_search_activities with pchembl_value__gte=6), and the workflow code blocks are copy-paste ready.	3 / 3
Workflow Clarity	Six numbered phases give a clear sequence, and the Fallback Chains table plus per-tool timeout notes provide explicit error-recovery guidance for fragile external APIs.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a monolithic ~340-line document; the full tool reference tables and pattern catalog are inline where they could be split into referenced 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 clearly states capabilities, names specific tools and pipeline stages, and provides an explicit 'Use for' trigger clause. It is concise without fluff or over-claims.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete actions — 'identification, characterization, and procurement' and 'compound name to structure to activity to ADMET properties to commercial sourcing' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It states both what the skill does (the identification-to-sourcing pipeline) and when to use it via an explicit 'Use for chemical biology, lead identification, probe selection...' clause.	3 / 3
Trigger Term Quality	It surfaces natural domain terms a user would say ('ADMET properties', 'commercial sourcing', 'lead identification', 'probe selection', 'small-molecule discovery') alongside tool names like PubChem and ChEMBL, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The small-molecule discovery niche and named chemistry tools make it clearly distinguishable and unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 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: plugin/skills/tooluniverse-small-molecule-discovery/SKILL.md
Commit: 089eb8e

Reviewed: about 9 hours 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.