Rdkit

What it does

When your agent uses it

• Tasks that involve Drug discovery and cheminformatics

Example prompts

• “/rdkit”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires RDKit Python package (conda install -c conda-forge rdkit or pip install rdkit).

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Forgetting AddHs — RDKit molecules from SMILES have implicit H. Call Chem.AddHs() before 3D embedding.
2. 2Embedding failure — EmbedMolecule returns -1 on failure. Check return value; retry with useRandomCoords=True.
3. 3MMFF94 unsupported atoms — MMFF94 does not cover all elements. Use UFF for organometallics.
4. 4Stereo loss — ensure SMILES include stereochemistry (/, \, @, @@) if relevant.
5. 5Large flexible molecules — conformer generation for molecules with >10 rotatable bonds needs many conformers (200+).
6. 6Sanitization errors — invalid SMILES cause MolFromSmiles to return None. Always check for None.

What it can do on your machine

Read from SKILL.md and the folder at commit fd6291b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires RDKit Python package (conda install -c conda-forge rdkit or pip install rdkit).

  From compatibility in the SKILL.md frontmatter.

Context cost

Rdkit loads about 1.1k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 201 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~40

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Hello-QM/catgo-LRG at commit fd6291b, republished under its AGPL-3.0 licence (© Hello-QM). 201 words, ~1,140 tokens.

name

rdkit

description

Use RDKit for molecular conformer generation, SMILES/InChI handling, molecular descriptors, fingerprints, and substructure searching. Python-based toolkit.

compatibility

Requires RDKit Python package (conda install -c conda-forge rdkit or pip install rdkit).

catalog-hidden

true

catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "shell",
  "name": "rdkit_conf",
  "command": "python gen_conformers.py",
  "input_files": {
    "gen_conformers.py": "<script content>"
  },
  "system_name": "caffeine_conformers"
})

from rdkit import Chem
from rdkit.Chem import AllChem, rdMolDescriptors

smiles = "CN1C=NC2=C1C(=O)N(C(=O)N2C)C"  # caffeine
mol = Chem.MolFromSmiles(smiles)
mol = Chem.AddHs(mol)

# Generate conformers
params = AllChem.ETKDGv3()
params.numThreads = 0  # use all cores
params.pruneRmsThresh = 0.5  # Angstrom RMSD pruning

cids = AllChem.EmbedMultipleConfs(mol, numConfs=50, params=params)
print(f"Generated {len(cids)} conformers")

# Optimize with MMFF94
results = AllChem.MMFFOptimizeMoleculeConfs(mol, numThreads=0)

# Sort by energy and write
energies = [(cid, res[1]) for cid, res in zip(cids, results) if res[0] == 0]
energies.sort(key=lambda x: x[1])

writer = Chem.SDWriter("conformers.sdf")
for cid, energy in energies[:20]:  # top 20 lowest energy
    mol.SetProp("Energy_kcal/mol", f"{energy:.2f}")
    writer.write(mol, confId=cid)
writer.close()

from rdkit import Chem
from rdkit.Chem import Descriptors, rdMolDescriptors

mol = Chem.MolFromSmiles("CCO")

print(f"MW:       {Descriptors.MolWt(mol):.2f}")
print(f"LogP:     {Descriptors.MolLogP(mol):.2f}")
print(f"HBD:      {rdMolDescriptors.CalcNumHBD(mol)}")
print(f"HBA:      {rdMolDescriptors.CalcNumHBA(mol)}")
print(f"TPSA:     {Descriptors.TPSA(mol):.2f}")
print(f"RotBonds: {Descriptors.NumRotatableBonds(mol)}")

from rdkit import Chem, DataStructs
from rdkit.Chem import AllChem

mol1 = Chem.MolFromSmiles("c1ccccc1")  # benzene
mol2 = Chem.MolFromSmiles("c1ccncc1")  # pyridine

fp1 = AllChem.GetMorganFingerprintAsBitVect(mol1, radius=2, nBits=2048)
fp2 = AllChem.GetMorganFingerprintAsBitVect(mol2, radius=2, nBits=2048)

tanimoto = DataStructs.TanimotoSimilarity(fp1, fp2)
print(f"Tanimoto similarity: {tanimoto:.3f}")

from rdkit import Chem
from rdkit.Chem import AllChem

mol = Chem.MolFromSmiles("CCO")
mol = Chem.AddHs(mol)
AllChem.EmbedMolecule(mol, AllChem.ETKDGv3())
AllChem.MMFFOptimizeMolecule(mol)

# Write XYZ
conf = mol.GetConformer()
symbols = [a.GetSymbol() for a in mol.GetAtoms()]
coords = conf.GetPositions()

with open("molecule.xyz", "w") as f:
    f.write(f"{len(symbols)}\n")
    f.write("Generated by RDKit\n")
    for sym, (x, y, z) in zip(symbols, coords):
        f.write(f"{sym} {x:.6f} {y:.6f} {z:.6f}\n")

© Hello-QM, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/rdkit of Hello-QM/catgo-LRG.

Open the folder on GitHubat commit fd6291b