New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

RDKit Cheminformatics Practices

by aiming-lab in aiming-lab/AutoResearchClaw

Reference guide for working with molecules in RDKit: reading SMILES and SDF files, computing descriptors and fingerprints, and searching substructures.

MITAuto-check passedResearch & Science

Install RDKit Cheminformatics Practices

skills CLI
$ npx skills add aiming-lab/AutoResearchClaw --skill chemistry-rdkit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aiming-lab/AutoResearchClaw chemistry-rdkit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/chemistry-rdkit .claude/skills/chemistry-rdkit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
chemistry-rdkit
GitHub stars
15k
Token cost
~708 tokens
SKILL.md length
241 words
Files
1
Skills in repo
34
Repo updated
First seen
Licence
MIT

At a glance

Reference guide for working with molecules in RDKit: reading SMILES and SDF files, computing descriptors and fingerprints, and searching substructures.

  • Works in 6 steps: Create molecules from SMILES: mol =… → Always check for None: MolFromSmiles… → Convert to canonical SMILES:… → …
  • Parsing SMILES strings or SDF files into molecule objects
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Filtering a compound library by functional group with SMARTS patterns

What it does

This is a compact set of RDKit practices grouped by task. It covers creating molecules from SMILES with a check for None on invalid input, writing canonical SMILES, and reading or writing SDF and SMILES files. It lists common descriptors such as molecular weight, LogP, polar surface area, hydrogen-bond donors and acceptors and rotatable bonds, along with the Lipinski rule of five limits.

Further sections cover Morgan, RDKit and MACCS fingerprints with Tanimoto similarity, SMARTS substructure matching, batch property calculation, 3D embedding with energy minimization, and ADMET-style filtering. A pitfalls list reminds the agent to keep sanitization on, add hydrogens for 3D work, handle stereochemistry and stream large SDF files instead of loading them whole.

When your agent uses it

  • Parsing SMILES strings or SDF files into molecule objects
  • Filtering a compound library by functional group with SMARTS patterns
  • Checking compounds against Lipinski drug-likeness limits
  • Comparing molecules by fingerprint similarity

Example prompts

  • “Load compounds.sdf and flag every molecule that breaks Lipinski's rule of five.”
  • “Find all molecules in library.smi that contain a carboxylic acid group.”
  • “Compute Morgan fingerprints for these SMILES and rank them by Tanimoto similarity to aspirin.”

Requirements

  • RDKit, used from Python

Workflow steps

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

  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')

What it can do on your machine

Read from SKILL.md and the folder at commit be4ba47. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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.

Context cost

RDKit Cheminformatics Practices loads about 708 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 241 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~708

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 aiming-lab/AutoResearchClaw at commit be4ba47, republished under its MIT licence (© aiming-lab). 241 words, ~708 tokens.

Download SKILL.mdSave it as .claude/skills/chemistry-rdkit/SKILL.md (or your agent's skills folder).
name
chemistry-rdkit
description
Computational chemistry with RDKit for molecular analysis, descriptors, fingerprints, and substructure search. Use when working with SMILES, drug discovery, or cheminformatics tasks.
metadata.category
domain
metadata.trigger-keywords
molecule,SMILES,chemical,drug,rdkit,fingerprint,molecular,compound,reaction,cheminformatics
metadata.applicable-stages
9,10,12
metadata.priority
4
metadata.version
1.0
metadata.author
researchclaw
metadata.references
adapted from K-Dense-AI/claude-scientific-skills

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
  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

© aiming-lab, MIT. 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/chemistry-rdkit of aiming-lab/AutoResearchClaw.

Open the folder on GitHubat commit be4ba47

Compare with similar skills

RDKit Cheminformatics Practices next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

RDKit Cheminformatics Practices compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
RDKit Cheminformatics Practices this skillaiming-lab/AutoResearchClaw15k—~708Automated safety check: PassMIT
DiffDock Molecular DockingK-Dense-AI/scientific-agent-skills48k1 repos~3kAutomated safety check: NotesMIT
Biopipelineslocbp-uzh/biopipelines109—~2.4kAutomated safety check: PassMIT
Edu Chem Reactionwy51ai/edulab1.4k—~1.2kAutomated safety check: PassApache-2.0
Rowanlamm-mit/scienceclaw2464 repos~3.1kAutomated safety check: WarnProprietary
Coot Rdkitpemsley/coot168—~981Automated safety check: PassGPL-3.0

Similar skills

  • DiffDock Molecular Docking

    K-Dense-AI/scientific-agent-skills

    Predicts how small molecules bind to a protein with DiffDock, covering batch docking, pose ranking by confidence and checks on the results; not for binding affinity.

    48k GitHub starsUsed in 1 repo~3k tokens
    Research & ScienceAuto-check: notes

  • Biopipelines

    locbp-uzh/biopipelines

    Design and run computational protein and ligand workflows on a GPU: binder and enzyme design, de novo backbone generation, inverse folding and sequence redesign, structure prediction, protein-ligand…

    109 GitHub stars~2.4k tokensUpdated 9 days ago
    Research & ScienceAuto-check passed

  • Edu Chem Reaction

    wy51ai/edulab

    把一个化学反应做成自包含的微观 3D 交互演示网页：左/上为 Three.js 可交互分子动画 （拖滑块看断键·成键·原子重组，分步高亮），右为 KaTeX 反应方程 + 分步讲解 + 原子守恒计数 + 可选能量-反应进程曲线。支持三入口——给定文字反应/方程、随机出题、上传图片识别后演示。

    1.4k GitHub stars~1.2k tokensUpdated today
    Research & ScienceAuto-check passed

  • Rowan

    lamm-mit/scienceclaw

    Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.

    246 GitHub starsUsed in 4 repos~3.1k tokens
    Research & ScienceAuto-check: warnings

  • Coot Rdkit

    pemsley/coot

    RDKit molecular manipulation and visualization within Coot's Python environment.

    168 GitHub stars~981 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

  • RDKit Cheminformatics

    davila7/claude-code-templates

    Guides molecular work with RDKit in Python: reading SMILES and SDF, sanitization, descriptors, fingerprints, substructure and similarity search, reactions and coordinates.

    33k GitHub starsUsed in 14 repos~5k tokens
    Research & ScienceAuto-check passed

More from aiming-lab/AutoResearchClaw

All 34 skills in this repo

  • A-Evolve Agent Improvement

    aiming-lab/AutoResearchClaw

    Diagnoses where an agent failed across runs and turns the findings into new skills, system prompt patches and knowledge entries, using the A-Evolve loop.

    15k GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Metabolic Study Planner

    aiming-lab/AutoResearchClaw

    Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.

    15k GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

  • MFA Pipeline Orchestrator

    aiming-lab/AutoResearchClaw

    Runs a metabolic flux analysis from model loading to phenotype prediction and figures by handing work to four sub-agents in sequence.

    15k GitHub stars~923 tokensUpdated 1 mo ago
    Auto-check passed

  • Qiskit 2.x Quantum ML Reference

    aiming-lab/AutoResearchClaw

    Reference patterns for writing qiskit 2.x code for variational quantum machine learning: feature maps, VQC training, VQE for chemistry, MPS circuits and noise models.

    15k GitHub stars~4.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Genome-Scale Metabolic Model Builder

    aiming-lab/AutoResearchClaw

    Builds or loads a genome-scale metabolic model in COBRApy, sets its growth medium and objective, and exports it as a validated JSON file for flux analysis.

    15k GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Biopython Bioinformatics

    aiming-lab/AutoResearchClaw

    Quick reference for Biopython work: sequence operations, SeqIO file parsing, BLAST searches, Entrez queries, phylogenetic trees and PDB structure analysis.

    15k GitHub stars~810 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about RDKit Cheminformatics Practices

What does RDKit Cheminformatics Practices do?

Reference guide for working with molecules in RDKit: reading SMILES and SDF files, computing descriptors and fingerprints, and searching substructures. This is a compact set of RDKit practices grouped by task. It covers creating molecules from SMILES with a check for None on invalid input, writing canonical SMILES, and reading or writing SDF and SMILES files.

When should I use RDKit Cheminformatics Practices?

RDKit Cheminformatics Practices fits situations like: parsing SMILES strings or SDF files into molecule objects; filtering a compound library by functional group with SMARTS patterns; checking compounds against Lipinski drug-likeness limits; comparing molecules by fingerprint similarity.

How do I install RDKit Cheminformatics Practices in Claude Code?

Run `npx skills add aiming-lab/AutoResearchClaw --skill chemistry-rdkit -a claude-code`. Or copy the skill folder (.claude/skills/chemistry-rdkit in aiming-lab/AutoResearchClaw) into .claude/skills/chemistry-rdkit in your project. Claude Code loads it when a task matches its description.

How do I install RDKit Cheminformatics Practices in Codex?

Run `npx skills add aiming-lab/AutoResearchClaw --skill chemistry-rdkit -a codex`. Or copy the skill folder (.claude/skills/chemistry-rdkit in aiming-lab/AutoResearchClaw) into .agents/skills/chemistry-rdkit in your project. Codex loads it when a task matches its description.

Can I use RDKit Cheminformatics Practices in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiming-lab/AutoResearchClaw --skill chemistry-rdkit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chemistry-rdkit, .gemini/skills/chemistry-rdkit, .github/skills/chemistry-rdkit and .opencode/skills/chemistry-rdkit in your project.

What does RDKit Cheminformatics Practices need to run?

SKILL.md names no scripts, command-line tools or credentials: RDKit Cheminformatics Practices is instructions for the agent only. Our summary lists: RDKit, used from Python.

Does RDKit Cheminformatics Practices access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is RDKit Cheminformatics Practices safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does RDKit Cheminformatics Practices use?

RDKit Cheminformatics Practices is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does RDKit Cheminformatics Practices use?

About 708 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to RDKit Cheminformatics Practices?

Skills that share tags, products or a category with RDKit Cheminformatics Practices: DiffDock Molecular Docking (K-Dense-AI/scientific-agent-skills, 48k stars), Biopipelines (locbp-uzh/biopipelines, 109 stars), Edu Chem Reaction (wy51ai/edulab, 1.4k stars) and Rowan (lamm-mit/scienceclaw, 246 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains RDKit Cheminformatics Practices?

aiming-lab (a GitHub organization) maintains it in aiming-lab/AutoResearchClaw, which has 14,607 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on August 19, 2026.

Source: aiming-lab/AutoResearchClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.