RDKit Descriptors and Fingerprints

What it does

When your agent uses it

• Computing Lipinski or physicochemical descriptors for a SMILES dataset
• Generating fingerprints as a NumPy array for machine learning
• Listing the RDKit descriptor names and presets that are available
• Cleaning a molecule list where some SMILES strings are invalid

Example prompts

• “Compute the physchem descriptors for molecules.csv and save them next to the input.”
• “Generate fingerprints for data.smi as a .npy file.”
• “Apply the Lipinski preset to my compounds file and tell me which rows were skipped.”

Requirements

• `uv` installed
• RDKit, pandas and NumPy, which `uv run` installs from inline metadata
• Compatibility (from SKILL.md): Requires uv. Dependencies (rdkit, pandas, numpy) are declared as PEP 723 inline script metadata and are installed automatically when the script is invoked with `uv run <script_path>` (do NOT use `uv run python <script_path>` -- that bypasses the inline metadata and will not install dependencies automatically).

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1Compute physicochemical descriptors → .csv
2. 2Compute molecular fingerprints → .npy or .csv
3. 3List available descriptors

What it can do on your machine

Read from SKILL.md and the folder at commit 5c19e75. 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

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • uv

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

• Network

  Links to these hosts (documentation or services it may open):

  • rdkit.org

  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 uv. Dependencies (rdkit, pandas, numpy) are declared as PEP 723 inline script metadata and are installed automatically when the script is invoked with `uv run <script_path>` (do NOT use `uv run python <script_path>` -- that bypasses the inline metadata and will not install dependencies automatically).

  From compatibility in the SKILL.md frontmatter.

Context cost

RDKit Descriptors and Fingerprints loads about 2.3k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 513 words of instructions outside code blocks.

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

~105

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

~2.3k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from jinzhezenggroup/computational-chemistry-agent-skills at commit 5c19e75, republished under its LGPL-3.0 licence (© jinzhezenggroup). 513 words, ~2,296 tokens.

name

rdkit-repr

description

A standardized CLI wrapper for RDKit molecular featurization workflows that handles physicochemical descriptor computation (outputs .csv) and molecular fingerprint extraction (outputs .npy or .csv), with built-in SMILES validation. USE WHEN you need to compute RDKit molecular descriptors or fingerprints from SMILES datasets (.csv/.smi), or when you want to list all available descriptor names and presets.

compatibility

Requires uv. Dependencies (rdkit, pandas, numpy) are declared as PEP 723 inline script metadata and are installed automatically when the script is invoked with `uv run <script_path>` (do NOT use `uv run python <script_path>` -- that bypasses the inline metadata and will not install dependencies automatically).

metadata.author

luzitian

metadata.version

1.0

metadata.repository

https://github.com/rdkit/rdkit

uv run <skill_path>/scripts/rdkit_helper.py --help

uv run <skill_path>/scripts/rdkit_helper.py desc --help
uv run <skill_path>/scripts/rdkit_helper.py fp --help
uv run <skill_path>/scripts/rdkit_helper.py list-desc --help

uv run <skill_path>/scripts/rdkit_helper.py --no-env desc --smiles "CCO" --output out.csv

uv run <skill_path>/scripts/rdkit_helper.py desc \
    --smiles "CCO" \
    --output /tmp/CCO.desc.csv

uv run <skill_path>/scripts/rdkit_helper.py desc \
    --file data.csv \
    --smiles-col smiles \
    --output data.desc.csv

uv run <skill_path>/scripts/rdkit_helper.py desc \
    --file molecules.smi \
    --output molecules.desc.csv

# Lipinski drug-likeness (6 descriptors: MolWt, MolLogP, NumHDonors, ...)
uv run <skill_path>/scripts/rdkit_helper.py desc \
    --file data.csv --preset lipinski --output data.lipinski.csv

# Extended physicochemical (25 descriptors, default)
uv run <skill_path>/scripts/rdkit_helper.py desc \
    --file data.csv --preset physchem --output data.physchem.csv

# Topological / graph indices (56 descriptors: BalabanJ, BertzCT, Chi*, PEOE_VSA*, ...)
uv run <skill_path>/scripts/rdkit_helper.py desc \
    --file data.csv --preset topological --output data.topo.csv

# All RDKit descriptors (~200 descriptors)
uv run <skill_path>/scripts/rdkit_helper.py desc \
    --file data.csv --preset all --output data.all_desc.csv

uv run <skill_path>/scripts/rdkit_helper.py desc \
    --file data.csv \
    --descriptors "MolWt,MolLogP,TPSA,NumHDonors,NumHAcceptors" \
    --output data.custom.csv

uv run <skill_path>/scripts/rdkit_helper.py desc \
    --file data.csv --preset physchem --no-merge --output data.desc_only.csv

uv run <skill_path>/scripts/rdkit_helper.py fp \
    --smiles "CCO" \
    --type morgan2 \
    --output /tmp/CCO.morgan2.npy

uv run <skill_path>/scripts/rdkit_helper.py fp \
    --file data.csv \
    --smiles-col smiles \
    --type morgan2 \
    --nbits 2048 \
    --output data.morgan2.npy

uv run <skill_path>/scripts/rdkit_helper.py fp \
    --file molecules.smi \
    --type maccs \
    --output molecules.maccs.npy

uv run <skill_path>/scripts/rdkit_helper.py fp \
    --file data.csv \
    --type rdkit \
    --nbits 1024 \
    --format csv \
    --output data.rdkfp.csv

uv run <skill_path>/scripts/rdkit_helper.py fp \
    --file data.csv \
    --type atompair \
    --nbits 4096 \
    --output data.atompair.npy

uv run <skill_path>/scripts/rdkit_helper.py list-desc

uv run <skill_path>/scripts/rdkit_helper.py list-desc --group lipinski
uv run <skill_path>/scripts/rdkit_helper.py list-desc --group physchem
uv run <skill_path>/scripts/rdkit_helper.py list-desc --group topological
uv run <skill_path>/scripts/rdkit_helper.py list-desc --group all

© jinzhezenggroup, LGPL-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

SKILL.md and 1 other file (scripts) in molecular-representation/rdkit-repr of jinzhezenggroup/computational-chemistry-agent-skills.

• SKILL.md
• scripts/rdkit_helper.py

Open the folder on GitHubat commit 5c19e75