Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Rowan Molecular Modeling Workflows

Teaches Claude to build and run cloud molecular-modeling pipelines — pKa, conformers, docking, cofolding — through Rowan's Python API.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Rowan is a cloud-native platform for molecular simulation and structure-based drug design. This skill gives Claude a working knowledge of the rowan-python client so it can generate and run:

  • Descriptor, microscopic pKa and macropKa predictions
  • Conformer and tautomer ensemble generation
  • Single-ligand docking, analogue docking, pose refinement
  • Protein–ligand cofolding, MSA generation, MD, permeability workflows
  • Project/folder organization, batch submission, webhook-driven async pipelines

It documents a consistent submit → result()/stream_result() → typed result pattern plus decision tables for picking the right workflow (e.g. macropKa when multiple ionizable groups couple).

Who it's for

  • Medicinal chemists, computational chemists and drug-discovery teams
  • Groups screening compound libraries in batches
  • Labs that can't maintain their own HPC/GPU infrastructure
  • Anyone who already holds a Rowan API key with available credits

Examples

  1. "Compute MW, SLogP and TPSA for these 50 SMILES and give me a table" → batch descriptor workflows plus aggregated output.
  2. "Find the dominant tautomer of this heterocycle, then generate conformers from it" → chained tautomer search → conformer search code.
  3. "Pull PDB 1M17 and run analogue docking on 20 related compounds, ranked by score" → protein upload, project creation, docking submission and pose collection.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/rowan folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/rowan/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/rowan ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Copy the skill into your Claude Code skills directory: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/rowan ~/.claude/skills/
  3. Install the Python client (Python 3.12+ required): uv pip install rowan-python (or pip install rowan-python).
  4. Get an API key from your Rowan account and export it: export ROWAN_API_KEY="your_key_here" — add it to your shell profile to persist.
  5. Verify auth by running python -c "import rowan; print(rowan.whoami().email)"; a printed email means you're ready.
  6. Restart Claude Code and try a prompt such as "Use Rowan to predict the pKa of aspirin."
View source on GitHub ↗License: MIT