chemistry-query
Chemistry agent skill for PubChem API queries (compound info/properties, structures/SMILES/images, synthesis routes/references) + RDKit cheminformatics (SMILES to molecule props/logP/TPSA, 2D PNG/SVG viz, Morgan fingerprints, retrosynthesis/BRICS disconnects, multi-step synth planning). Use for chemistry tasks involving compounds, molecules, structures, PubChem data, RDKit analysis, SMILES processing, synthesis routes, retrosynthesis, reaction simulation. Triggers on chemistry, compounds, molecules, chemical data/properties, PubChem, RDKit, SMILES, structures, synthesis, reactions, retrosynthesis, synth plan/route.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/cheminem/chemistry-queryWhat This Skill Does
The Chemistry Query Agent (v1.4.0) is a comprehensive cheminformatics suite integrated into the OpenClaw ecosystem. It bridges the gap between massive public molecular databases and local high-precision analysis tools. By leveraging the PubChem REST API, it allows users to perform instantaneous lookups of chemical entities by name or identifier. Beyond simple retrieval, the skill utilizes RDKit—a powerful open-source library—to perform structural calculations, molecular property predictions (such as Lipinski's Rule of Five parameters), and advanced chemical operations. Users can generate 2D visualizations, calculate Morgan fingerprints, identify substructures, and execute complex retrosynthetic pathways to determine how a molecule might be built from simpler components.
Installation
To integrate this skill into your local environment, use the OpenClaw package manager:
clawhub install openclaw/skills/skills/cheminem/chemistry-query
Ensure that you have an internet connection for PubChem API calls and that your environment supports RDKit dependencies, as the script execution engine requires a compatible Python 3.x environment.
Use Cases
This skill is designed for medicinal chemists, students, and materials scientists. Use it to verify molecular properties before synthesis, screen compounds based on structural similarity, or perform automated retrosynthesis planning. Whether you are identifying the logP value of a lead compound, generating a visual representation for a lab report, or simulating a multi-step organic reaction, this skill provides structured, machine-readable outputs.
Example Prompts
- "Look up the IUPAC name and molecular weight for caffeine, then generate a PNG structure image."
- "Perform a retrosynthesis analysis for the molecule 'aspirin' using a depth of 2 and return the disconnection results."
- "Compare the Tanimoto similarity between the following two SMILES: 'CC(=O)Oc1ccccc1C(=O)O' and 'CC(=O)Oc1ccccc1C(=O)OC'."
Tips & Limitations
When working with synthesis planning, note that retrosynthetic routes are purely theoretical based on BRICS fragments and SMARTS templates; always cross-reference with established chemical literature. For large datasets, chain the scripts/chain_entry.py to minimize redundant network requests. Be mindful that complex 3D XYZ coordinate optimization using MMFF requires more computation time than property extraction. If an API call times out, the script will return an error code; ensure your SMILES strings are valid, canonical representations for the best accuracy in similarity searches.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-cheminem-chemistry-query": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, code-execution, external-api
Related Skills
pharmaclaw-pharmacology-agent
Pharmacology agent for ADME/PK profiling of drug candidates from SMILES. Computes drug-likeness (Lipinski Ro5, Veber rules), QED, SA Score, ADME predictions (BBB permeability, aqueous solubility, GI absorption, CYP3A4 inhibition, P-gp substrate, plasma protein binding), and PAINS alerts. Chains from chemistry-query for SMILES input. Triggers on pharmacology, ADME, PK/PD, drug likeness, Lipinski, absorption, distribution, metabolism, excretion, BBB, solubility, bioavailability, lead optimization, drug profiling.
pharmaclaw-catalyst-design
Organometallic catalyst recommendation and novel ligand design for drug synthesis reactions. Recommends catalysts (Pd, Ru, Rh, Ir, Ni, Cu, Zr, Fe) for reaction types (Suzuki, Heck, Buchwald-Hartwig, metathesis, hydrogenation, click, etc.) from curated database with scoring. Designs novel ligand variants via RDKit (steric, electronic, bioisosteric modifications). Chains from chemistry-query/retrosynthesis (receives reaction type + substrate) and feeds into IP Expansion (novel ligands as patentable inventions). Triggers on catalyst, ligand, organometallic, cross-coupling catalyst, reaction conditions, catalyst selection, ligand design, cone angle, bite angle, phosphine, NHC, palladium catalyst, ruthenium catalyst.
Drug Team
Skill by cheminem
pharmaclaw-market-intel-agent
Fetches and analyzes FAERS (FDA Adverse Event Reporting System) data from openFDA API. Supports drug names and SMILES (resolves via PubChem). Generates: events list, yearly trends (counts), top reactions/outcomes as JSON + matplotlib bar chart PNGs.
pharma-pharmacology-agent
Pharmacology agent for ADME/PK profiling of drug candidates from SMILES. Computes drug-likeness (Lipinski Ro5, Veber rules), QED, SA Score, ADME predictions (BBB permeability, aqueous solubility, GI absorption, CYP3A4 inhibition, P-gp substrate, plasma protein binding), and PAINS alerts. Chains from chemistry-query for SMILES input. Triggers on pharmacology, ADME, PK/PD, drug likeness, Lipinski, absorption, distribution, metabolism, excretion, BBB, solubility, bioavailability, lead optimization, drug profiling.