MedChem (Claude Skill)

Claude skill providing Python recipes for MedChem, a medicinal-chemistry filtering library built on RDKit — drug-likeness rules, structural alerts, complexity metrics, and synthetic-accessibility scoring for compound-library triage.

   
Type Claude Skill
Supplier K-Dense Inc. (community OSS)
Availability GA — actively maintained 2025–2026
Pricing Free / OSS skill (MIT collection); MedChem itself is Apache-2.0
Capabilities Read/Write — Claude executes MedChem via the Bash/Python tool

How to install

  • Also packaged in the SciAgent-Skills collection (jaechang-hits (community OSS, CC BY 4.0)): clone jaechang-hits/SciAgent-Skills and run /plugin install sciagent-skills in Claude Code (or copy skills/structural-biology-drug-discovery/medchem into ~/.claude/skills/).
  • Claude Code / Claude.ai — Skills CLI (recommended): 
    npx skills add K-Dense-AI/scientific-agent-skills

    Installs the K-Dense collection; enable the medchem skill when prompted (also works in Cursor/Codex via the Agent Skills spec; requires Node ≥ 18).

  • Claude Code / Claude Desktop — manual clone: 
    git clone https://github.com/K-Dense-AI/scientific-agent-skills
cp -r scientific-agent-skills/skills/medchem ~/.claude/skills/
pip install medchem

Project-scoped alternative: copy into .claude/skills/ instead of ~/.claude/skills/.

What it does

SKILL.md with recipes for:

  • Drug-likeness rule sets — Lipinski’s Rule of Five, Veber, Egan, Muegge
  • Structural alerts — PAINS, BRENK, NIH, and other medicinal-chemistry filter catalogues
  • Molecular-complexity metrics and synthetic-accessibility scoring (SAScore)
  • ADMET-flag detection on compound libraries
  • Parallel filter application across large screening sets

Primary use cases: Triage and prioritisation of virtual-screening hit lists, drug-likeness assessment for lead-optimisation analog sets, removal of pan-assay interference and reactive moieties before in-vitro follow-up.

Notes

Skill is documentation plus Python recipes — Claude executes MedChem locally via Bash/Python. Designed to slot in after the rdkit-skill / datamol / molfeat steps in K-Dense’s lead-optimisation example workflow. Rule cut-offs are configurable — defaults match the published medicinal-chemistry literature but should be tuned per project.

Sources

Installed this tool?

Share feedback — install path, OS, errors, workarounds. The form opens with this tool pre-selected and a link back to this page.