CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tooluniverse-admet-prediction in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 well-structured, highly actionable workflow skill with clear sequencing, fallbacks, and a verification checklist. The main weaknesses are minor verbosity (a repeated description sentence) and a large monolithic body that could split reference detail into separate files.

Suggestions

Remove the line 13 sentence ('Comprehensive pharmacokinetic and toxicity profiling...') which duplicates the frontmatter description, and tighten the intro 'ADMET reasoning' paragraph.

Move the detailed per-tool interpretation tables (property ideal-range table, toxicity-endpoint reference) into a separate reference file (e.g. references/INTERPRETATION.md) and link one level deep from the phases to reduce SKILL.md length.

Add at least one fully realized example call using the provided ibuprofen SMILES in place of <SMILES> placeholders to make the common-case path copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient; the domain-significance notes are genuine value-add rather than filler, but line 13 re-states the description and the intro 'ADMET reasoning' paragraph is a touch long.

4 / 5

Actionability

Concrete, executable tool signatures with explicit param names and list-vs-string type rules, plus a real example SMILES; held back from 5 only by <SMILES> placeholders rather than fully realized example calls.

4 / 5

Workflow Clarity

Clear 5-phase sequence with per-phase goals/steps, error-recovery fallbacks (ADMETAI fail -> SwissADME), and a mandatory completeness checklist as a verification checkpoint.

5 / 5

Progressive Disclosure

Well-organized with clear section headers and workflow-coupled inline tool detail, but it is a full ~300-line manual with no one-level-deep reference split rather than an overview pointing to separate files.

4 / 5

Total

17

/

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 excellent description: specific, comprehensive, third-person, and clearly distinguishes what the skill does from when to invoke it with natural trigger phrases. It occupies a distinct niche with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — profiling plus integration of six named data sources (ADMET-AI, SwissADME, PubChemTox, ChEMBL, Lipinski, CYP) — with comprehensive coverage and no gaps.

5 / 5

Completeness

Explicitly answers both 'what' (ADMET profiling integrating six named sources) and 'when' (a 'Use for...' clause with concrete trigger phrases) with no vagueness.

5 / 5

Trigger Term Quality

Comprehensive set of natural domain terms a medicinal chemist would actually say: ADMET, drug-likeness, BBB penetration, bioavailability, hepatotoxicity, ADME/PK, screening compound libraries.

5 / 5

Distinctiveness Conflict Risk

ADMET prediction is a tight niche with distinct, specialized triggers (BBB penetration, CYP interactions, hepatotoxicity) unlikely to fire for unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.