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

Medchem

by aipoch in aipoch/medical-research-skills

Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries.

MITAuto-check passedResearch & Science

Install Medchem

skills CLI
$ npx skills add aipoch/medical-research-skills --skill medchem -a claude-code

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

GitHub CLI
$ gh skill install aipoch/medical-research-skills medchem --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/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'scientific-skills/Evidence Insight/medchem' .claude/skills/medchem && 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
medchem
GitHub stars
1.9k
Token cost
~1.3k tokens
SKILL.md length
384 words
Files
5 (incl. scripts, references)
Skills in repo
578
Repo updated
First seen
Licence
MIT

At a glance

Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries.

  • You need to apply drug-likeness rules
  • SKILL.md covers When to Use, Key Features, Dependencies and Example Usage, plus 1 more section
  • Runs Python scripts from its folder
  • PAINS/structural alerts

What it does

Medchem is an agent skill from aipoch/medical-research-skills. Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `medchem_audit_result_v1.json`, `references/api_guide.md` and `references/rules_catalog.md`).

It sits in Research & Science, covering Drug discovery and cheminformatics and Prioritization frameworks. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

  • You need to apply drug-likeness rules
  • PAINS/structural alerts
  • Complexity metrics to triage
  • Optimize libraries

Example prompts

  • “/medchem”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. 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.

    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

Medchem loads about 1.3k tokens when it runs, and up to ~8k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
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
~8k

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 aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 384 words, ~1,310 tokens.

Download SKILL.mdSave it as .claude/skills/medchem/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
medchem
description
Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries.
license
MIT
author
AIPOCH

Source: https://github.com/aipoch/medical-research-skills

When to Use

  • Screening large compound libraries to quickly triage for drug-like candidates (e.g., Lipinski/Veber + alerts).
  • Flagging problematic chemotypes (e.g., PAINS, reactive/toxicophores, curated structural alerts) before follow-up assays.
  • Prioritizing lead-optimization candidates with stricter criteria (lead-like rules, demerit systems, complexity caps).
  • Enforcing property constraints (MW/logP/TPSA/rotatable bonds) for target-specific design windows (e.g., CNS).
  • Identifying molecules containing specific functional groups/scaffolds (e.g., Michael acceptors, hinge binders) for SAR or risk assessment.

Key Features

  • Drug-likeness and medchem rule sets: Lipinski (Ro5), Veber, Oprea, CNS, lead-like (soft/strict), Rule of Three, REOS, Golden Triangle, etc.
  • PAINS and structural alert filtering: curated alert catalogs and pattern-based screening.
  • Curated industrial filter sets: e.g., NIBR filters; Lilly demerit scoring with pass/fail thresholds.
  • Functional-group detection via SMARTS-based group matchers (hinge binders, phosphate binders, Michael acceptors, reactive groups, custom patterns).
  • Named catalogs of curated structures (functional groups, protecting groups, reagents, fragments) for matching and annotation.
  • Molecular complexity metrics (e.g., Bertz/Whitlock/Barone-style) and threshold-based complexity filters.
  • Constraint-based filtering for property windows (MW/logP/TPSA/RB, etc.).
  • Query language to combine heterogeneous criteria (rules + alerts + numeric thresholds) into a single expression.

Dependencies

  • medchem (latest)
  • datamol (latest)
  • pandas (latest, for tabular workflows)

Example Usage

python
# End-to-end, runnable example:
# 1) load SMILES
# 2) apply Ro5 + Veber
# 3) apply common structural alerts
# 4) compute complexity and filter
# 5) export a CSV with decisions

import pandas as pd
import datamol as dm
import medchem as mc

smiles_list = [
    "CC(=O)OC1=CC=CC=C1C(=O)O",  # aspirin
    "CN1C=NC2=C1C(=O)N(C(=O)N2C)C",  # caffeine
    "c1ccccc1",  # benzene
]

df = pd.DataFrame({"smiles": smiles_list})
mols = [dm.to_mol(smi) for smi in df["smiles"]]

# 1) Drug-likeness rules
rule_filter = mc.rules.RuleFilters(rule_list=["rule_of_five", "rule_of_veber"])
rule_res = rule_filter(mols=mols, n_jobs=-1, progress=False)
df["passes_rules"] = rule_res["pass"]

# 2) Structural alerts
alerts = mc.structural.CommonAlertsFilters()
alert_res = alerts(mols=mols, n_jobs=-1, progress=False)
df["has_alerts"] = alert_res["has_alerts"]

# 3) Complexity (example threshold)
complex_filter = mc.complexity.ComplexityFilter(max_complexity=500)
complex_res = complex_filter(mols=mols, n_jobs=-1, progress=False)
df["passes_complexity"] = complex_res["pass"]

# 4) Final decision
df["keep"] = df["passes_rules"] & (~df["has_alerts"]) & df["passes_complexity"]

# 5) Save results
df.to_csv("medchem_screening_results.csv", index=False)
print(df)
Show full SKILL.md (197 more words)Show less

Implementation Details

  • Rule evaluation (medchem.rules)

    • Rules are implemented as callable checks over SMILES or RDKit-like molecule objects (commonly via datamol).
    • RuleFilters(rule_list=[...]) applies multiple rules and returns a structured result (typically including an overall pass plus per-rule details).
    • Typical use: start broad (Ro5/Veber), then tighten (CNS/lead-like) as project constraints become clearer.

  • Structural alerts (medchem.structural)

    • Alert systems are primarily SMARTS/pattern-based matchers curated from literature/industrial practice.
    • CommonAlertsFilters, NIBRFilters, and LillyDemeritsFilters provide different philosophies:
      • Common alerts: general-purpose red flags.
      • NIBR: curated industrial filter set.
      • Lilly demerits: assigns penalties per matched rule; a common convention is reject if total demerits > 100.

  • Complexity (medchem.complexity)

    • Complexity scores approximate synthetic difficulty / structural intricacy using established heuristics (e.g., Bertz/Whitlock/Barone-style metrics).
    • ComplexityFilter(max_complexity=...) converts a numeric score into a pass/fail gate for library triage.

  • Constraints (medchem.constraints)

    • Property windows (MW/logP/TPSA/rotatable bonds, etc.) are applied as hard filters.
    • Use constraints to encode target-specific design hypotheses (e.g., CNS-like space) rather than universal “good/bad” judgments.

  • Groups and catalogs (medchem.groups, medchem.catalogs)

    • Group detection is SMARTS-driven and returns boolean matches and/or match details (substructure hits).
    • Named catalogs provide curated sets for consistent annotation and matching across projects.

  • Parallelization

    • Most batch APIs accept n_jobs; set n_jobs=-1 to use all available CPU cores for large libraries.

© aipoch, MIT. 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 4 other files (scripts, references) in scientific-skills/Evidence Insight/medchem of aipoch/medical-research-skills.

  • SKILL.md
  • medchem_audit_result_v1.json
  • references/api_guide.md
  • references/rules_catalog.md
  • scripts/filter_molecules.py

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Medchem 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.

Medchem compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Medchem this skillaipoch/medical-research-skills1.9k—~1.3kAutomated safety check: PassMIT
Tooluniverse Gwas Drug Discoverywu-yc/LabClaw1.1k2 repos~4.7kAutomated safety check: PassNone
Tooluniverse Drug Target Validationwu-yc/LabClaw1.1k2 repos~9.9kAutomated safety check: PassNone
Bio Workflows Causal Genomics PipelineGPTomics/bioSkills1.2k2 repos~5.5kAutomated safety check: PassMIT
Bio Causal Genomics Heritability PartitioningGPTomics/bioSkills1.2k2 repos~8.9kAutomated safety check: PassMIT
Regulomedb Databasejaechang-hits/SciAgent-Skills3741 repos~5.3kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Tooluniverse Gwas Drug Discovery

    wu-yc/LabClaw

    Transform GWAS signals into actionable drug targets and repurposing opportunities.

    1.1k GitHub starsUsed in 2 repos~4.7k tokens
    Research & ScienceAuto-check passed

  • Tooluniverse Drug Target Validation

    wu-yc/LabClaw

    Comprehensive computational validation of drug targets for early-stage drug discovery.

    1.1k GitHub starsUsed in 2 repos~9.9k tokens
    Product & Project ManagementAuto-check passed

  • Bio Workflows Causal Genomics Pipeline

    GPTomics/bioSkills

    End-to-end post-GWAS causal inference pipeline orchestrating heritability partitioning, genetic correlation, Mendelian randomization with CHP-aware sensitivity (CAUSE / LHC-MR), colocalization…

    1.2k GitHub starsUsed in 2 repos~5.5k tokens
    Research & ScienceAuto-check passed

  • Bio Causal Genomics Heritability Partitioning

    GPTomics/bioSkills

    Estimates SNP heritability and partitions it across functional annotations, cell types, and loci from GWAS summary statistics or individual-level genotypes.

    1.2k GitHub starsUsed in 2 repos~8.9k tokens
    Research & ScienceAuto-check passed

  • Regulomedb Database

    jaechang-hits/SciAgent-Skills

    Query RegulomeDB v2 GET REST API to score variants for regulatory function and retrieve overlapping evidence (TF binding, histone marks, DNase peaks, footprints, motifs, eQTLs, chromatin state).

    374 GitHub starsUsed in 1 repo~5.3k tokens
    Research & ScienceAuto-check passed

  • Molecode

    AtomFlow-AI/MoleCode

    A skill your agent uses for deterministic molecule understanding, graph-level editing, generation, and validation with MoleCode — an explicit Mermaid graph in which every atom and bond is a typed…

    306 GitHub stars~1.9k tokensUpdated 4 mo ago
    Research & ScienceAuto-check passed

More from aipoch/medical-research-skills

All 578 skills in this repo

  • Academic Poster Generator

    aipoch/medical-research-skills

    Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster…

    1.9k GitHub stars~2.2k tokensUpdated 23 days ago
    Auto-check passed

  • Diagnostic Study Quality Assessment Quadas

    aipoch/medical-research-skills

    Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool.

    1.9k GitHub stars~1.4k tokensUpdated 23 days ago
    Auto-check passed

  • Exploratory Data Analysis

    aipoch/medical-research-skills

    Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.

    1.9k GitHub stars~3.7k tokensUpdated 23 days ago
    Auto-check passed

  • Iso Certification

    aipoch/medical-research-skills

    A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS.

    1.9k GitHub stars~1.8k tokensUpdated 23 days ago
    Auto-check passed

  • Journal Skills

    aipoch/medical-research-skills

    Recommends target journals for manuscript submission by analyzing the paper topic/abstract and the journal distribution of similar PubMed literature; use when users ask for journal…

    1.9k GitHub stars~1.7k tokensUpdated 23 days ago
    Auto-check passed

  • Latex Posters

    aipoch/medical-research-skills

    Creates academic-poster writing packages for LaTeX using beamerposter, tikzposter, or baposter.

    1.9k GitHub stars~1.3k tokensUpdated 23 days ago
    Auto-check passed

Categories

Questions about Medchem

What does Medchem do?

Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries. Medchem is an agent skill from aipoch/medical-research-skills. Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries.

When should I use Medchem?

Medchem fits situations like: you need to apply drug-likeness rules; PAINS/structural alerts; complexity metrics to triage; optimize libraries.

How do I install Medchem in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill medchem -a claude-code`. Or copy the skill folder (scientific-skills/Evidence Insight/medchem in aipoch/medical-research-skills) into .claude/skills/medchem in your project. Claude Code loads it when a task matches its description.

How do I install Medchem in Codex?

Run `npx skills add aipoch/medical-research-skills --skill medchem -a codex`. Or copy the skill folder (scientific-skills/Evidence Insight/medchem in aipoch/medical-research-skills) into .agents/skills/medchem in your project. Codex loads it when a task matches its description.

Can I use Medchem 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 aipoch/medical-research-skills --skill medchem -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/medchem, .gemini/skills/medchem, .github/skills/medchem and .opencode/skills/medchem in your project.

What does Medchem need to run?

Going by SKILL.md and its folder, Medchem needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Medchem 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 Medchem 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 Medchem use?

Medchem is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Medchem 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 6.7k tokens, read only when the agent opens those files.

What are the alternatives to Medchem?

Skills that share tags, products or a category with Medchem: Tooluniverse Gwas Drug Discovery (wu-yc/LabClaw, 1.1k stars), Tooluniverse Drug Target Validation (wu-yc/LabClaw, 1.1k stars), Bio Workflows Causal Genomics Pipeline (GPTomics/bioSkills, 1.2k stars) and Bio Causal Genomics Heritability Partitioning (GPTomics/bioSkills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Medchem?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,937 GitHub stars. The repository holds 578 skills in this directory. The repository was last updated on September 17, 2026.

Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.