sumit11402/knights-ae-02/chemistry-rdkit

Claude Code and agent skill by sumit11402/knights-ae-02

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Computational chemistry with RDKit for molecular analysis, descriptors, fingerprints, and substructure search. Use when working with SMILES, drug discovery, or cheminformatics tasks.

Install

npx vskill@latest install sumit11402/knights-ae-02/chemistry-rdkit

SKILL.md

The same SKILL.md was published earlier as boboegg/ai-resources/chemistry-rdkit.

RDKit Cheminformatics Best Practice

Molecular I/O
  1. Create molecules from SMILES: mol = Chem.MolFromSmiles('CCO')
  2. Always check for None: MolFromSmiles returns None on invalid input
  3. Convert to canonical SMILES: Chem.MolToSmiles(mol)
  4. Read SDF files: suppl = Chem.SDMolSupplier('file.sdf')
  5. Read SMILES files: suppl = Chem.SmilesMolSupplier('file.smi')
  6. Write molecules: writer = Chem.SDWriter('output.sdf')
Molecular Descriptors
  1. Molecular weight: Descriptors.MolWt(mol)
  2. LogP (lipophilicity): Descriptors.MolLogP(mol)
  3. TPSA (polar surface area): Descriptors.TPSA(mol)
  4. H-bond donors/acceptors: Descriptors.NumHDonors(mol), Descriptors.NumHAcceptors(mol)
  5. Rotatable bonds: Descriptors.NumRotatableBonds(mol)
  6. Lipinski Rule of 5: MW <= 500, LogP <= 5, HBD <= 5, HBA <= 10
Fingerprints and Similarity
  1. Morgan (circular) fingerprints: AllChem.GetMorganFingerprintAsBitVect(mol, radius=2, nBits=2048)
  2. RDKit fingerprints: Chem.RDKFingerprint(mol)
  3. MACCS keys: MACCSkeys.GenMACCSKeys(mol)
  4. Tanimoto similarity: DataStructs.TanimotoSimilarity(fp1, fp2)
  5. Use radius=2 (ECFP4 equivalent) as default for most applications
  6. For virtual screening, Tanimoto > 0.7 suggests structural similarity
Substructure Search
  1. SMARTS patterns: pattern = Chem.MolFromSmarts('[OH]')
  2. Check match: mol.HasSubstructMatch(pattern)
  3. Get all matches: mol.GetSubstructMatches(pattern)
  4. Common SMARTS: [#6](=O)[OH] (carboxylic acid), [NH2] (primary amine)
  5. Filter compound libraries by functional group presence
Property Calculation Patterns
  1. Batch processing: iterate over SDMolSupplier, skip None entries
  2. Use Chem.Descriptors.descList for all available descriptors
  3. For ADMET filtering, calculate Lipinski, Veber, and PAINS filters
  4. Generate 3D coordinates: AllChem.EmbedMolecule(mol, AllChem.ETKDG())
  5. Minimize energy: AllChem.MMFFOptimizeMolecule(mol)
Common Pitfalls
  1. Always sanitize molecules (default behavior) — disable only when needed
  2. Add hydrogens explicitly for 3D work: Chem.AddHs(mol)
  3. Handle stereochemistry: use Chem.AssignStereochemistry(mol)
  4. Large SDF files: use ForwardSDMolSupplier for memory efficiency
  5. Kekulization errors usually indicate invalid SMILES input

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/sumit11402/knights-ae-02/chemistry-rdkit/badge)](https://verified-skill.com/skills/sumit11402/knights-ae-02/chemistry-rdkit)

Something wrong with this skill or its page? Tell us.