# Rdkit Molecular Descriptors

> Use this skill to compute compact cheminformatics descriptors from one SMILES string with RDKit. Do not use it for docking, quantum chemistry, or large library screening.

- **Type:** Skill
- **Install:** `agentstack add skill-ma-compbio-lab-skillfoundry-rdkit-molecular-descriptors`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ma-compbio-lab](https://agentstack.voostack.com/s/ma-compbio-lab)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [ma-compbio-lab](https://github.com/ma-compbio-lab)
- **Source:** https://github.com/ma-compbio-lab/SkillFoundry/tree/main/skills/drug-discovery-and-cheminformatics/rdkit-molecular-descriptors
- **Website:** https://ma-compbio-lab.github.io/SkillFoundry/

## Install

```sh
agentstack add skill-ma-compbio-lab-skillfoundry-rdkit-molecular-descriptors
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Purpose
Turn a SMILES string into a compact descriptor summary suitable for quick triage, featurization, and metadata enrichment.

## When to use
- You need a local RDKit-backed molecular summary from a SMILES string.
- You want canonical SMILES, formula, weight, and simple physicochemical descriptors.

## When not to use
- You need conformer generation, docking, or reaction modeling.
- You need batch-scale descriptor computation for millions of compounds.

## Inputs
- One SMILES string
- Optional molecule name
- Optional JSON output path

## Outputs
- JSON summary with canonical SMILES, formula, exact mass, logP, TPSA, HBA/HBD, rotatable bonds, ring count, and heavy-atom count

## Requirements
- `slurm/envs/chem-tools` with RDKit available

## Procedure
1. Run `slurm/envs/chem-tools/bin/python skills/drug-discovery-and-cheminformatics/rdkit-molecular-descriptors/scripts/compute_rdkit_descriptors.py --smiles "CC(=O)OC1=CC=CC=C1C(=O)O" --name aspirin`.
2. Inspect `canonical_smiles`, `formula`, `molecular_weight`, and `tpsa`.
3. Reuse the JSON payload for downstream filtering or reporting.

## Validation
- The command exits successfully.
- `canonical_smiles` is non-empty for a known valid molecule.
- Descriptor fields are numeric where expected.

## Failure modes and fixes
- Invalid SMILES: verify the input string and quoting.
- Missing RDKit environment: run the script with `slurm/envs/chem-tools/bin/python`.

## Safety and limits
- Descriptor calculation only.
- No medicinal-chemistry or safety interpretation is implied.

## Provenance
- RDKit docs: https://www.rdkit.org/docs/index.html
- RDKit repository: https://github.com/rdkit/rdkit

## Related skills
- `chembl-molecule-search`

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ma-compbio-lab](https://github.com/ma-compbio-lab)
- **Source:** [ma-compbio-lab/SkillFoundry](https://github.com/ma-compbio-lab/SkillFoundry)
- **License:** Apache-2.0
- **Homepage:** https://ma-compbio-lab.github.io/SkillFoundry/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ma-compbio-lab-skillfoundry-rdkit-molecular-descriptors
- Seller: https://agentstack.voostack.com/s/ma-compbio-lab
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.