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

by VectorSpaceLab in VectorSpaceLab/AREX-Skill

A skill your agent uses for RDKit cheminformatics tasks: molecule parsing and validation, descriptors and fingerprints, conformers and drawing, reactions and standardization, data integrations…

BSD-3-ClauseAuto-check passedResearch & Science

Install Rdkit

skills CLI
$ npx skills add VectorSpaceLab/AREX-Skill --skill rdkit -a claude-code

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

GitHub CLI
$ gh skill install VectorSpaceLab/AREX-Skill 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/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/rdkit .claude/skills/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
rdkit
GitHub stars
328
Token cost
~1.3k tokens
SKILL.md length
521 words
Files
7 (incl. scripts, references)
Skills in repo
157
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

A skill your agent uses for RDKit cheminformatics tasks: molecule parsing and validation, descriptors and fingerprints, conformers and drawing, reactions and standardization, data integrations…

  • RDKit cheminformatics tasks: molecule parsing and validation
  • SKILL.md covers Install and Import Check, Route by Task, Shared References and Quick Decision Rules, plus 1 more section
  • Runs Python scripts from its folder; calls conda and python
  • Descriptors and fingerprints

What it does

Rdkit is an agent skill from VectorSpaceLab/AREX-Skill. Use for RDKit cheminformatics tasks: molecule parsing and validation, descriptors and fingerprints, conformers and drawing, reactions and standardization, data integrations, optional Contrib utilities, or RDKit repository development.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/capability-map.md`, `references/repo-provenance.md` and `references/repo-routing-metadata.json`).

It sits in Research & Science, covering Drug discovery and cheminformatics. It works with RDKit. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is BSD-3-Clause.

When your agent uses it

  • RDKit cheminformatics tasks: molecule parsing and validation
  • Descriptors and fingerprints
  • Conformers and drawing
  • Reactions and standardization

Example prompts

  • “/rdkit”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit ac3fe1a. 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:

    • conda
    • python

    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 loads about 1.3k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 521 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its BSD-3-Clause licence (© VectorSpaceLab). 521 words, ~1,288 tokens.

Download SKILL.mdSave it as .claude/skills/rdkit/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
rdkit
description
Use for RDKit cheminformatics tasks: molecule parsing and validation, descriptors and fingerprints, conformers and drawing, reactions and standardization, data integrations, optional Contrib utilities, or RDKit repository development.
disable-model-invocation
true
metadata.disco-role
operating
license
BSD 3-Clause

RDKit Skill

Use this repo skill when a task involves RDKit, the open-source C++/Python cheminformatics toolkit. RDKit is commonly used for molecule I/O, structure validation, descriptors, fingerprints, similarity, conformers, drawing, reactions, standardization, R-group decomposition, feature definitions, tabular cheminformatics, optional Contrib utilities, and maintaining the RDKit source tree.

Install and Import Check

For normal Python use, prefer the documented binary install route:

bash
conda install -c conda-forge rdkit
python - <<'PY'
from rdkit import Chem
mol = Chem.MolFromSmiles('c1ccccc1O')
assert mol is not None
print(Chem.MolToSmiles(mol))
PY

Use scripts/check_rdkit_env.py when an agent needs a quick installed-package smoke check, module availability report, or diagnosis for a local source checkout that shadows an installed RDKit package.

Route by Task

  • sub-skills/molecule-io-core/ handles molecule creation, SMILES/SMARTS/MolBlock/SDF I/O, sanitization, hydrogens, atom/bond/ring queries, substructure matching, and editable molecules.
  • sub-skills/descriptors-fingerprints/ handles scalar descriptors, QED/Lipinski/Crippen/TPSA properties, Morgan/RDKit/atom-pair/topological-torsion fingerprints, DataStructs similarity, feature tables, and Butina clustering.
  • sub-skills/conformers-drawing/ handles ETKDG conformer generation, UFF/MMFF optimization, 3D alignment/RMSD, 2D coordinates, and SVG/PNG/grid rendering.
  • sub-skills/reactions-standardization/ handles reaction SMARTS/RXN workflows, product sanitization, MolStandardize cleanup/normalization/fragment/tautomer workflows, R-group decomposition, and stereochemistry/CIP handling.
  • sub-skills/data-cli-integration/ handles RDConfig data files, feature-definition files, chemical feature factories, PandasTools, lightweight DB helpers, and installed-package CLI-style helpers.
  • sub-skills/contrib-utilities/ handles optional community Contrib utilities such as SA Score, NP Score, NIBR filters, Fraggle, MMPA, FreeWilson, and MolVS-derived recipes.
  • sub-skills/repo-development/ handles editing, building, testing, formatting, wrapper boundaries, generated stubs/docstrings, and source-checkout diagnostics for RDKit itself.

Shared References

  • references/capability-map.md maps common user requests to sub-skills, bundled scripts, and verification evidence.
  • references/troubleshooting.md covers cross-cutting install/import, source-checkout shadowing, optional dependency, data-file, and compiled-extension failures.
  • references/repo-provenance.md records the source snapshot, selected evidence paths, dirty state, and inspection-package facts for future refresh decisions.
Show full SKILL.md (274 more words)Show less

Quick Decision Rules

  • If a task starts with invalid SMILES, suppliers, None molecules, properties on atoms/bonds, or substructure matching, start with molecule-io-core before any downstream chemistry.
  • If a task asks for feature vectors, similarity search, clustering, or descriptor columns, start with descriptors-fingerprints and cross-link back to molecule validation when inputs are untrusted.
  • If a task mentions 3D coordinates, RMSD, force fields, or images, start with conformers-drawing; do not treat 2D depiction coordinates as 3D conformers.
  • If a task transforms molecules chemically, standardizes salts/tautomers, runs reactions, or decomposes analog series into R groups, start with reactions-standardization.
  • If a task asks where RDKit data lives, how to use BaseFeatures.fdef, how to attach molecules to a DataFrame, or how to make a tiny CLI around installed RDKit, start with data-cli-integration.
  • If a task mentions Contrib, SA/NP score, Fraggle, MMPA, FreeWilson, or optional community scripts, start with contrib-utilities and check availability before assuming modules/data are installed.
  • If a task is about changing this repository or an import fails from an unbuilt checkout with rdBase missing, start with repo-development.

Working Safely

  • Prefer installed RDKit package APIs for user workflows; only use source-tree instructions for repository-development tasks.
  • Validate molecule creation before passing objects to descriptors, fingerprints, reactions, conformer embedding, or drawing.
  • Treat optional wrappers and integrations such as PostgreSQL cartridge, Java/C# wrappers, FreeSASA, InChI, Avalon, CoordGen, Contrib tools, and database helpers as availability-dependent.
  • Keep long-running native tests, benchmarks, fuzzers, full CMake builds, and database workflows out of routine user tasks unless the user explicitly asks for maintainer validation.
  • Do not depend on original RDKit repository examples or scripts at runtime; use the bundled references and scripts in this skill tree.

© VectorSpaceLab, BSD-3-Clause. 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 6 other files (scripts, references) in skills/repositories/repo-skills/rdkit of VectorSpaceLab/AREX-Skill.

  • SKILL.md
  • references/capability-map.md
  • references/repo-provenance.md
  • references/repo-routing-metadata.json
  • references/troubleshooting.md
  • scripts/check_rdkit_env.py
  • sub-skills

Open the folder on GitHubat commit ac3fe1a

Compare with similar skills

Rdkit 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rdkit this skillVectorSpaceLab/AREX-Skill328—~1.3kAutomated safety check: PassBSD-3-Clause
DiffDock Molecular DockingK-Dense-AI/scientific-agent-skills48k1 repos~3kAutomated safety check: NotesMIT
Edu Chem Reactionwy51ai/edulab1.4k—~1.2kAutomated safety check: PassApache-2.0
Biopipelineslocbp-uzh/biopipelines109—~2.4kAutomated safety check: PassMIT
RDKit Conformer Generatorjinzhezenggroup/computational-chemistry-agent-skills1481 repos~2.4kAutomated safety check: PassLGPL-3.0
RDKit Descriptors and Fingerprintsjinzhezenggroup/computational-chemistry-agent-skills1481 repos~2.3kAutomated safety check: PassLGPL-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

  • 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 9 days ago
    Research & ScienceAuto-check passed

  • 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 7 days ago
    Research & ScienceAuto-check passed

  • RDKit Conformer Generator

    jinzhezenggroup/computational-chemistry-agent-skills

    Generates 3D molecular conformers from SMILES strings or files with RDKit, keeps the lowest-energy one per molecule, and falls back to 2D coordinates when embedding fails.

    148 GitHub starsUsed in 1 repo~2.4k tokens
    Research & ScienceAuto-check passed

  • RDKit Descriptors and Fingerprints

    jinzhezenggroup/computational-chemistry-agent-skills

    Computes RDKit physicochemical descriptors and molecular fingerprints from SMILES through a uv-run CLI script that skips and logs invalid molecules.

    148 GitHub starsUsed in 1 repo~2.3k tokens
    Research & ScienceAuto-check passed

  • RDKit Cheminformatics Practices

    aiming-lab/AutoResearchClaw

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

    15k GitHub stars~708 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from VectorSpaceLab/AREX-Skill

All 157 skills in this repo

  • Agent Lightning

    VectorSpaceLab/AREX-Skill

    Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…

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

  • Agent Tools

    VectorSpaceLab/AREX-Skill

    A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…

    328 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents And Awel

    VectorSpaceLab/AREX-Skill

    Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.

    328 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents And Middleware

    VectorSpaceLab/AREX-Skill

    Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…

    328 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Agents Workflows

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.

    328 GitHub stars~500 tokensUpdated 1 mo ago
    Auto-check passed

  • Alphafold3

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.

    328 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Rdkit

What does Rdkit do?

A skill your agent uses for RDKit cheminformatics tasks: molecule parsing and validation, descriptors and fingerprints, conformers and drawing, reactions and standardization, data integrations…. Rdkit is an agent skill from VectorSpaceLab/AREX-Skill. Use for RDKit cheminformatics tasks: molecule parsing and validation, descriptors and fingerprints, conformers and drawing, reactions and standardization, data integrations, optional Contrib utilities, or RDKit repository development.

When should I use Rdkit?

Rdkit fits situations like: RDKit cheminformatics tasks: molecule parsing and validation; descriptors and fingerprints; conformers and drawing; reactions and standardization.

How do I install Rdkit in Claude Code?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill rdkit -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/rdkit in VectorSpaceLab/AREX-Skill) into .claude/skills/rdkit in your project. Claude Code loads it when a task matches its description.

How do I install Rdkit in Codex?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill rdkit -a codex`. Or copy the skill folder (skills/repositories/repo-skills/rdkit in VectorSpaceLab/AREX-Skill) into .agents/skills/rdkit in your project. Codex loads it when a task matches its description.

Can I use Rdkit 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 VectorSpaceLab/AREX-Skill --skill 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/rdkit, .gemini/skills/rdkit, .github/skills/rdkit and .opencode/skills/rdkit in your project.

What does Rdkit need to run?

Going by SKILL.md and its folder, Rdkit needs Python for the scripts in its folder and the command-line tools its instructions call (conda and python). Our summary lists: Python 3.

Does Rdkit 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 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Rdkit use?

Rdkit is published under the BSD-3-Clause licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Rdkit use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Rdkit?

Skills that share tags, products or a category with Rdkit: DiffDock Molecular Docking (K-Dense-AI/scientific-agent-skills, 48k stars), Edu Chem Reaction (wy51ai/edulab, 1.4k stars), Biopipelines (locbp-uzh/biopipelines, 109 stars) and RDKit Conformer Generator (jinzhezenggroup/computational-chemistry-agent-skills, 148 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rdkit?

VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 328 GitHub stars. The repository holds 157 skills in this directory. The repository was last updated on September 3, 2026.

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