Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/rowan
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API.
Passed 20 of 20 test cases with the skill, and 3 of 20 without it.
and 35 more in the full report
19 fixed3 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
Write a Python snippet to submit a protein-ligand docking workflow using Rowan for ligand 'CCO', protein object `protein`, and pocket dict `pocket`, enabling both pose refinement and conformer search flags.
| Checked | Without skill | With skill |
|---|---|---|
| Calls rowan.submit_docking_workflow | Missed | Passed |
| Passes do_pose_refinement=True | Missed | Passed |
| Passes do_conformer_search=True | Missed | Passed |
The instructions your model reads when the skill loads.
----|----------------|-------------------|-------| | Descriptors | <1 min | 0.5–2 | Lightweight, good for triage | | pKa (single transition) | 2–5 min | 2–5 | Depends on molecule size | | MacropKa (pH 0–14) | 5–15 min | 5–15 | Broader sampling, higher cost | | Conformer search | 3–10 min | 3–10 | Ensemble quality matters | | Tautomer search | 2–5 min | 2–5 | Heterocyclic systems | | Docking (single ligand) | 5–20 min | 5–20 | Depends on pocket size, refinement | | Analogue docking series (10–50 ligands) | 30–120 min | 30–100+ | Shared reference frame | | MSA generation | 5–30 min | 5–30 | Sequence length dependent | | Protein-ligand cofolding | 15–60 min | 20–50+ | AI structure prediction, GPU-heavy |
uv pip install rowan-python
import rowan
rowan.api_key = "your_api_key_here" # or set ROWAN_API_KEY env var
# Submit a descriptors workflow — completes in under a minute
wf = rowan.submit_descriptors_workflow("CC(=O)Oc1ccccc1C(=O)O", name="aspirin")
result = wf.result()
print(result.descriptors['MW']) # 180.16
print(result.descriptors['SLogP']) # 1.19
print(result.descriptors['TPSA']) # 59.44
If that prints without error, you're set up correctly.
uv pip install rowan-python
# or: pip install rowan-python
test cases passed, vs 3 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.