Tooluniverse Chemical Compound Retrieval

This handles the messy reality of looking up chemical compounds where "aspirin" maps cleanly but "Vitamin D" splits into multiple forms. It cross-references PubChem and ChEMBL to resolve names to actual identifiers (CIDs, ChEMBL IDs, SMILES), fetches molecular properties and bioactivity data, and grades evidence quality based on whether databases agree. The workflow is explicit about disambiguation first, then retrieval, which matters when stereochemistry or salt forms create ambiguity. Useful when you need reliable compound data without manually checking if two databases are talking about the same molecule. It won't guess at properties and includes SMILES verification to catch malformed inputs early.

skills.sh installs: 419
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Chemical Compound Information Retrieval

Retrieve comprehensive chemical compound data with proper disambiguation and cross-database validation.

LOOK UP DON'T GUESS: Never assume a CID, ChEMBL ID, or molecular property value. Always retrieve from PubChem/ChEMBL.

English-first: Always use English compound names in tool calls. Respond in user's language.

Domain Reasoning: Disambiguation

"Aspirin" = one compound. "Vitamin D" = multiple forms (D2/D3/active metabolite). For generic class names (steroids, vitamins, acids), present candidates and confirm before proceeding.

Workflow

Phase 0: Clarify (only if highly ambiguous -- skip for unambiguous names or specific IDs)
Phase 1: Disambiguate → resolve PubChem CID + ChEMBL ID
Phase 2: Retrieve data (silent)
Phase 3: Report compound profile