Drug Discovery

Community

beita6969

drug-discovery

Supports drug discovery workflows including target identification, virtual screening, ADMET prediction, lead optimization, pharmacokinetics modeling, and drug repurposing analyses; trigger when users discuss drug targets, compound libraries, medicinal chemistry, or pharmaceutical development.

Overview

Publisher	beita6969
Repository	`ScienceClaw`
Skill name	`drug-discovery`
Stars	950
Forks	106
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by beita6969 on GitHub. Read the source before you install it.

Installation

Install the Drug Discovery AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/beita6969/ScienceClaw/tree/main/skills/drug-discovery
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/beita6969/ScienceClaw.git /tmp/ScienceClaw
mkdir -p .claude/skills
cp -r /tmp/ScienceClaw/skills/drug-discovery .claude/skills/drug-discovery

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Drug Discovery in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Drug Discovery on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Drug Discovery is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

When to Trigger

Activate this skill when the user mentions:

Drug target identification, druggability assessment
Virtual screening, molecular docking, pharmacophore
ADMET (absorption, distribution, metabolism, excretion, toxicity)
Lead optimization, SAR (structure-activity relationship)
Pharmacokinetics (PK), pharmacodynamics (PD), PK/PD modeling
Drug repurposing, off-label, drug-disease associations
SMILES, InChI, compound libraries, chemical fingerprints
IC50, EC50, Ki, dose-response curves

Step-by-Step Methodology

Target identification and validation - Identify therapeutic target from literature, GWAS hits, or omics data. Assess druggability using Open Targets, DGIdb, or structural pocket analysis. Confirm target-disease association strength.
Compound sourcing - Search ChEMBL, PubChem, ZINC, or DrugBank for known active compounds. For novel scaffolds, consider de novo design tools (REINVENT, MolGPT).
Virtual screening - Structure-based: dock compound library against target (AutoDock Vina, Glide). Ligand-based: use pharmacophore models or molecular fingerprint similarity. Filter by drug-likeness (Lipinski Ro5, Veber rules).
ADMET prediction - Predict absorption (Caco-2 permeability, logP), distribution (plasma protein binding, Vd), metabolism (CYP inhibition/induction), excretion (clearance), and toxicity (hERG, hepatotoxicity, AMES mutagenicity). Use SwissADME, pkCSM, or ADMETlab.
Lead optimization - Analyze SAR from dose-response data. Identify key pharmacophoric features. Suggest modifications to improve potency, selectivity, or ADMET profile while maintaining drug-likeness.
PK/PD modeling - Build compartmental PK models. Estimate key parameters: Cmax, Tmax, AUC, half-life, bioavailability. For PD, model dose-response (Emax model, Hill equation).
Drug repurposing analysis - Query drug-gene interaction databases. Analyze shared pathways between drug targets and disease mechanisms. Check clinical trial databases for existing evidence.

Key Databases and Tools

ChEMBL - Bioactivity data for drug-like compounds
PubChem - Chemical structure and bioassay data
DrugBank - Drug and target information
Open Targets - Target-disease associations
ZINC - Purchasable compound library
SwissADME / pkCSM - ADMET prediction tools
BindingDB - Protein-ligand binding data

Output Format

Compound results as tables: SMILES, molecular weight, logP, key activity (IC50/EC50), ADMET flags.
Docking results: binding energy (kcal/mol), key interactions, pose description.
PK parameters: Cmax, Tmax, AUC, t1/2, clearance, bioavailability with units.
SAR analysis: matched molecular pair comparisons with activity changes.

Quality Checklist

Target-disease association supported by evidence (genetic, functional)
Drug-likeness filters applied (Lipinski, Veber, PAINS)
ADMET predictions include confidence levels or applicability domain
Docking validated against known co-crystal structures when available
IC50/EC50 reported with assay conditions and confidence intervals
PK parameters include units and species (human vs. preclinical)
Known liabilities (hERG, CYP inhibition, reactive metabolites) flagged
Comparison to existing drugs/compounds for the same target included

Frequently asked questions

What does the Drug Discovery AI skill do?

Why use Drug Discovery on TypingMind?

Because you install it once and use it with any model. Drug Discovery is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Drug Discovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/beita6969/ScienceClaw/tree/main/skills/drug-discovery. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Drug Discovery?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Drug Discovery?

As many as you like. As long as a model supports skills, you can use Drug Discovery with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Drug Discovery AI skill free?

Yes. It is published on GitHub by beita6969 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Documentation Lookup

affaan-m

CommunityPopular

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React,…

Everything Claude Code

affaan-m

CommunityPopular

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

Discord User Post

Post an approved message as the logged-in Discord user through the Discord desktop app. Use for release announcements or other direct user-authored Discord posts; not for OpenClaw channel sends, bots,…

Test Audit

Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

When to Trigger

Step-by-Step Methodology

Key Databases and Tools

Output Format

Quality Checklist

Frequently asked questions

Related AI Skills

Set up your own AI workspace now