rdkit-repr

Official

RDKit descriptors and fingerprints via a CLI.

Authorjinzhezenggroup
Version1.0.0
Installs0

System Documentation

What problem does it solve?

RDKit descriptor and fingerprint computations from SMILES datasets can be error-prone and time-consuming when done ad-hoc. This Skill provides a standardized CLI wrapper to compute RDKit descriptors and fingerprints, handle invalid SMILES, and output results for ML pipelines.

Core Features & Use Cases

  • Compute RDKit descriptors (Lipinski, physchem, topological, or all) and save as CSV.
  • Compute molecular fingerprints (morgan, rdkit, maccs, etc.) to .npy or .csv, with robust input validation.
  • List available descriptors and presets to quickly explore features for QSAR and ML experiments.
  • Use case: Given a dataset of SMILES, generate descriptor features and fingerprint vectors for model training.

Quick Start

Run uv run <skill_path>/scripts/rdkit_helper.py desc --smiles "CCO" --output data.desc.csv to produce a descriptor CSV.

Dependency Matrix

Required Modules

rdkitpandasnumpy

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: rdkit-repr
Download link: https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/archive/main.zip#rdkit-repr

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.