Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

medchem — Claude Code skill: what it does, how to install

Filters compound libraries with drug-likeness rules, structural alerts, and complexity checks. Use it when triaging molecular candidates.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add K-Dense-AI/scientific-agent-skills --skill medchem -a claude-code
Open on GitHub

What medchem does

This skill applies Lipinski, Veber, CNS, and lead-like rules to molecular collections. It uses medchem, datamol, and RDKit; RuleFilters returns pandas DataFrames, while functional calls return boolean pass masks.

It can check PAINS, Brenk, NIBR, and ChEMBL-derived structural alerts. The skill also covers molecular complexity, chemical-group detection, and multi-criterion library filters written with the medchem query language.

It requires Python 3.11+, medchem 2.1.1, datamol 0.13.0, and RDKit 2026.3.6. Validate empty or unparsed structures before filtering: the functional NIBR filter with a 10 cutoff can pass parse failures that have zero severity. Lilly support needs native tools, a C++ compiler, make, zlib, and Ruby.

What it helps with

  • filter compounds that fail Lipinski rules
  • detect PAINS and Brenk structural alerts
  • screen a molecular library with NIBR rules
  • check molecular complexity against ZINC thresholds
  • build multi-criterion filters with medchem queries

Example prompts for the agent

  • Use the medchem skill to screen this library with Lipinski and Veber rules.
  • Run medchem to find PAINS and Brenk alerts in `mol_list`.
  • Apply the NIBR filter to `smiles_list` and remove structures with severity from `10`.

How to install medchem

1Skills CLI (Vercel)

npx skills add K-Dense-AI/scientific-agent-skills --skill medchem -a claude-code

2Manually: put the files in place

~/.claude/skills/medchem/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/medchem/

From the same set120

The whole set →
scientific-visualization K-Dense-AI Generates and audits publication-ready scientific figures in Matplotlib, Seaborn, and Plotly, focusing on truthful data encoding and accessibility. Claude Code CX Codex Cursor +1 2,400installs scientific-writing K-Dense-AI This skill drafts and audits scientific manuscripts and reports while tying claims to verified evidence. Use it for sections, references, declarations, and submission checks. Claude Code CX Codex Cursor +1 2,400installs statistical-analysis K-Dense-AI Runs hypothesis tests with assumption checking, effect sizes, and APA-formatted reports. Covers t-tests, ANOVA, correlation, regression, non-parametric and Bayesian methods. Claude Code CX Codex Cursor +1 2,300installs scientific-brainstorming K-Dense-AI Structures early-stage research ideation through independent idea generation, transparent scoring, and adversarial review. Useful for ranking hypotheses without premature consensus. Claude Code CX Codex Cursor +1 2,300installs literature-review K-Dense-AI This skill searches and synthesizes research literature, checks citations, and prepares Markdown or PDF reviews. Use it for reproducible searches and screening. Claude Code CX Codex Cursor +1 2,300installs scientific-critical-thinking K-Dense-AI Evaluates scientific claims, research methodology, and evidence quality. Applies GRADE and Cochrane Risk of Bias frameworks. Claude Code CX Codex Cursor +1 2,300installs scientific-schematics K-Dense-AI Creates PNG drafts of scientific diagrams and runs a separate quality review. Use it for neural network architectures, flowcharts, system diagrams, and biological pathways. Claude Code CX Codex Cursor +1 2,200installs scikit-learn K-Dense-AI A skill for Python machine learning tasks: classification, regression, clustering, preprocessing, and building ML pipelines with scikit-learn 1.9.1. Claude Code CX Codex Cursor +1 2,200installs

Similar

sr-screener Imbad0202 Applies protocol-driven screening to study records for reviews. It manages double-blind screening of titles, abstracts, and full texts. Claude Code CX Codex Cursor +1 449installs typst-author jihe520 Generates, edits, and troubleshoots Typst markup while enforcing syntax rules and formatting checks. Keeps agents grounded against hallucinations. Claude Code CX Codex Cursor +1 1,800installs anysearch anysearch-ai This skill gives an agent web search, domain-specific queries, parallel batch search, and page extraction. Use it when a task needs current information or a claim needs checking. Claude Code CX Codex Cursor +1 38,500installs academic-paper Imbad0202 This skill runs a 12-agent academic pipeline across 11 modes. It guides projects from literature searches and outlines to citation audits and rebuttal reviews. Claude Code CX Codex Cursor +1 10,800installs nature-figure Yuan1z0825 A skill that builds, revises and audits scientific figures for manuscripts in Python or R. Useful when plots go to submission, not to a report. Claude Code CX Codex Cursor +1 18,700installs academic-paper-reviewer Imbad0202 This skill reviews an academic paper through five role-based perspectives. Use it for peer review, revision checks, or a focused methodology assessment. Claude Code CX Codex Cursor +1 9,800installs nature-polishing Yuan1z0825 A skill that polishes, translates and tightens existing academic prose. Facts, terminology and evidence boundaries stay intact. Claude Code CX Codex Cursor +1 17,400installs nature-citation Yuan1z skill, refactored into static/dynamic layers Finds Nature and CNS-family papers for manuscript claims, maps claims to sources, and prepares a reference-manager export. Use it when the journal scope matters. Claude Code CX Codex Cursor +1 15,600installs

Questions about medchem

How do I install medchem in Claude Code?

Run npx skills add K-Dense-AI/scientific-agent-skills --skill medchem -a claude-code, then run npx skills add K-Dense-AI/scientific-agent-skills --skill medchem -a claude-code again. The skill file is at ~/.claude/skills/medchem/SKILL.md.

What does medchem do?

It filters and prioritizes molecules using drug-likeness rules, structural alerts, and complexity metrics. It also works with PAINS, Brenk, and NIBR catalogs.

What does medchem require?

It requires Python 3.11+, medchem 2.1.1, datamol 0.13.0, and RDKit 2026.3.6. Standard filters run locally without credentials, while installation needs network access.

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor