Drug Team
Skill by cheminem
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/cheminem/drug-teamWhat This Skill Does
The Drug Team skill is a sophisticated meta-agent designed to streamline the complex lifecycle of drug discovery. By orchestrating a specialized ensemble of sub-agents, it bridges the gap between theoretical molecular design and practical laboratory synthesis. The system architecture coordinates multiple specialized domains including cheminformatics (ADMET prediction), computational chemistry (molecular docking and scaffold generation), supply chain logistics (lab inventory management), and intellectual property analysis (patent scouting).
When a user initiates a request, the skill orchestrates the following workflow:
- Scaffold generation and synthesis route planning.
- In-silico evaluation of molecular properties (ADMET) such as LogP, TPSA, and pKa.
- Toxicological screening for common medicinal chemistry alerts (PAINS, Brenk, Ames).
- Automated checking of reagent availability and cost via Lab Inventory integration.
- Patent landscape analysis to ensure novelty and freedom to operate.
The final output provides a refined selection of the top three molecular candidates, accompanied by visual representations, optimized synthesis routes, and comprehensive scoring metrics covering feasibility, safety, and intellectual property standing.
Installation
To integrate this agent into your workflow, ensure your environment satisfies all dependencies, including RDKit, Matplotlib, and the required sub-skills (chemistry-query, synth-notebook, and lab-inventory). Run the following command in your terminal:
clawhub install openclaw/skills/skills/cheminem/drug-team
Use Cases
This skill is ideal for medicinal chemists, academic researchers, and pharmaceutical start-ups who need to accelerate early-stage drug discovery. Use it to rapidly prototype lead compounds that are not only biologically active but also synthetically accessible and patentable. It is particularly effective for filtering out non-viable candidates early in the design phase, thereby saving significant time and laboratory resources.
Example Prompts
- "Design a novel pain relief molecule with a LogP under 3 and check if we have the necessary reagents in stock."
- "Perform a drug synthesis design for a JAK inhibitor and include a patent novelty check."
- "Design a low-toxicity cardiovascular lead compound and provide a synthesis route with yield optimization."
Tips & Limitations
- Quality of Data: The efficacy of ADMET predictions and docking results relies heavily on the underlying ML models; verify these results with experimental data before synthesis.
- Inventory Synchronization: Ensure your
lab-inventoryskill is updated regularly to provide accurate cost and availability data. - Patent Scope: The patent scouting tool provides an initial indicator of novelty; always consult with a professional patent attorney for a definitive freedom-to-operate opinion.
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-drug-team": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-read, file-write, external-api, code-execution
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.
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.
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.