Pubchem Database

88TrustedShips scripts

Chemical data retrieval for molecular properties, hazard info, and structural research.

What it does

Installing Pubchem Database allows your assistant to interface directly with authoritative chemical records. It processes technical inquiries by fetching validated identifiers, computed physical constants, and standardized safety information rather than relying on generalized training data.

The skill provides a specialized wrapper to handle API interactions, ensuring queries remain within usage limits while parsing returned data into readable formats. It transforms the assistant from a general conversationalist into a tool capable of performing specific cheminformatics tasks like structure-based searching and pharmacology lookups.

When it earns its place

Reach for it when…

Use this when verifying exact chemical properties, looking up GHS hazard classifications, or identifying protein targets for a specific substance. It is appropriate for drafting research summaries, checking pharmacological mechanisms, or building lists of similar compounds based on structural SMILES strings.

Look elsewhere when…

This is not intended for high-throughput batch screening of millions of compounds or for complex molecular modeling simulations. Use a dedicated cheminformatics software suite if you require real-time 3D conformational analysis or quantum chemical calculations.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • What are the physical properties and hazard statements for caffeine?
  • Find compounds similar to this SMILES string
  • Identify the pharmacological targets of ibuprofen
  • Show me the 2D structure of this drug molecule

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/pubchem_database ~/.claude/skills/pubchem-database

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/pubchem_database .claude/skills/pubchem-database

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server