tooluniverse-admet-prediction

Comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) profiling for drug candidates. Integrates ADMET-AI predictions, SwissADME drug-likeness, PubChemTox experimental toxicity, ChEMBL clinical data, Lipinski rule-of-five, and CYP interaction data. Use for drug-likeness assessment, BBB penetration, bioavailability, hepatotoxicity prediction, ADME/PK profiling, or screening compound libraries before lab testing.

Quality

94%

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

88%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 strong, highly actionable skill body with a well-sequenced 5-phase workflow, explicit validation checklist, and concrete tool-call examples. The main weaknesses are minor over-explanation of concepts Claude already knows and a monolithic structure with no progressive disclosure of detail into reference files.

Suggestions

Trim inferable explanations (e.g. the 'Why CYP matters' paragraph, 'BBB+ = can cross', per-property 'Why It Matters' rationales) to tighten token efficiency.

Move the long reference tables (per-property ideal ranges, evidence-grading tier table) into a separate references/ file and link from SKILL.md to improve progressive disclosure.

Reduce the multi-line ASCII workflow diagram to a concise one-line phase summary, since the per-phase sections already enumerate each step.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes domain competence, but carries minor over-explanation Claude could infer (e.g. '~75% of drugs are metabolized by CYP enzymes', 'BBB+ = compound can cross; BBB- = cannot', the 'Why CYP matters' paragraph and per-property 'Why It Matters' rationales).	4 / 5
Actionability	Concrete, copy-paste-ready tool-call signatures throughout with exact parameter shapes (list vs string), return values, and explicit pass/warn/fail verdict thresholds — e.g. 'ADMETAI_predict_physicochemical_properties(smiles=["<SMILES>"])' and the parallel PubChemTox call block.	5 / 5
Workflow Clarity	Clear 5-phase numbered sequence with per-phase goals, explicit fallback paths (ADMETAI import fails -> SwissADME; PubChem fails -> user provides SMILES), and a MANDATORY pre-report completeness checklist acting as the validation gate.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a coherent phased structure, but it is a ~310-line monolith with no bundle files and substantial inline reference-style tables (per-property ideal ranges, evidence tiers) that could live in separate reference files.	4 / 5
	Total	18 / 20 Passed

Description

100%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.

An exemplary description: it states what the skill does, enumerates the concrete data sources it integrates, and lists the natural trigger phrases that map to its use. No fluff, no over-claims, third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities and data sources — 'Integrates ADMET-AI predictions, SwissADME drug-likeness, PubChemTox experimental toxicity, ChEMBL clinical data, Lipinski rule-of-five, and CYP interaction data' — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both 'what' (Comprehensive ADMET profiling integrating six named sources) and 'when' ('Use for drug-likeness assessment, BBB penetration, bioavailability, hepatotoxicity prediction, ADME/PK profiling, or screening compound libraries') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases a user would actually say: 'drug-likeness assessment', 'BBB penetration', 'bioavailability', 'hepatotoxicity prediction', 'ADME/PK profiling', 'screening compound libraries before lab testing'.	5 / 5
Distinctiveness Conflict Risk	The 'ADMET' niche and named tools (ADMET-AI, SwissADME, PubChemTox, ChEMBL) carve a clear, distinct trigger space with minimal overlap risk against other skills.	5 / 5
	Total	20 / 20 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-admet-prediction/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.