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.
npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-chemical-safety