Tooluniverse Chemical Safety

This is a comprehensive chemical safety assessment framework that pulls from multiple databases to build toxicity profiles. It combines AI predictions (ADMET-AI for LD50, carcinogenicity, liver toxicity), experimental data (PubChemTox for GHS classifications and dose-response), toxicogenomics (CTD for gene interactions and disease associations), and regulatory data (FDA labels for drugs). The workflow is structured as eight research phases, from compound disambiguation through integrated risk assessment, with mandatory evidence grading (T1-T4) so you know whether you're looking at a clinical finding or a computational prediction. It explicitly separates drug toxicity from environmental chemical toxicity and forces you to compute results rather than describe them. Best for hazard identification, occupational exposure assessment, and understanding whether a compound is acutely toxic versus a long-term carcinogen.

skills.sh installs: 398
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-chemical-safety --agent claude-code

Installs into .claude/skills of the current project.

Files

Chemical Safety & Toxicology Assessment

Toxicity assessment: identify the chemical, check known hazards (GHS, IARC), then look for ADMET predictions. Dose makes the poison — always consider exposure level, as a compound that is toxic at high doses may be safe at relevant exposures. Distinguish between acute toxicity (LD50, GHS category) and chronic hazards (carcinogenicity, endocrine disruption) — they require different risk management approaches. Computational predictions (ADMETAI) are T3 evidence and must be anchored by experimental data from PubChemTox or FDA labels wherever available. When evidence conflicts between prediction and experiment, always defer to the experimental finding.

LOOK UP DON'T GUESS: never assume GHS categories, IARC classification, or CTD disease links — always call PubChemTox and CTD tools to retrieve current classifications before reporting.

Comprehensive chemical safety analysis integrating predictive AI models, curated toxicogenomics databases, regulatory safety data, and chemical-biological interaction networks.

When to Use This Skill

SKILL.md on GitHub

Details

Repository: github.com/mims-harvard/tooluniverse
First seen: Jun 3, 2026