generative-design

Methods and tools for generating new drug-like molecules with machine-learning models. De novo design means creating molecules from scratch rather than only modifying known compounds.

In plain words
What is it for?
Use it to compare molecule-generation methods, create analogues or new scaffolds, optimize several properties, generate molecules for a protein pocket, or design linkers between fragments.
Why use it?
It helps explore chemical possibilities that are too large to search manually and focus candidate generation on desired properties or a protein binding site.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/kdevos12/alkyl/generative-design
Any agent
npx skills add Kdevos12/ALKYL --skill generative-design
Clone the repo
git clone --depth 1 https://github.com/Kdevos12/ALKYL

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,781 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00078 $0.01781
Opus 5 $0.00039 $0.00890
Sonnet 5 $0.00016 $0.00356
Haiku 4.5 $0.00008 $0.00178

Measured 2d ago against content hash 5af0859e1534, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generative-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/generative-design/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generative Molecular Design

De novo design of novel molecules with desired properties using generative models — the core ML capability for lead generation and scaffold hopping in drug discovery.

When to Use This Skill

  • Generate molecules with target properties (QED, LogP, SA, docking score)
  • Explore chemical space around a hit/lead (analogue generation, scaffold hopping)
  • Design molecules conditioned on a protein pocket (SBDD)
  • Optimize multi-property objectives (Pareto front: potency + selectivity + ADMET)
  • Benchmark or compare generative models (MOSES / GuacaMol suites)
  • Build a RL-based focused library generator (REINVENT 4)
  • Design linkers or grow fragments (fragment-based generative design)

Generation Paradigms

Paradigm Method Strength Weakness
Language model SMILES/SELFIES GPT, LSTM Fast, scalable, fine-tunable SMILES can be invalid; needs SELFIES
VAE JT-VAE, MolVAE Smooth latent space, BO-ready Mode collapse; slow tree encode
GNN flow/GAN GraphAF, GCPN, JunctionGAN Graph-native; no linearity Training instability
RL optimization REINVENT 4, REINFORCE Property-guided; no new arch needed Reward hacking; mode collapse
3D diffusion DiffSBDD, TargetDiff Pocket-conditioned; 3D geometry Slow, needs structure
Fragment-based DeLinker, DiffLinker Fragment growing, FBDD Limited to provided fragments

Evaluation Metrics (Know These)

Metric What it measures Target
Validity % chemically valid ~100% (SELFIES) / 85-99% (SMILES LM)
Uniqueness % unique in generated set >99%
Novelty % not in training set >99%
FCD Fréchet ChemNet Distance (distribution) Lower = closer to drug-like distribution
KL divergence Property distributions vs. reference Lower
Scaffold diversity # unique Murcko scaffolds / N Higher
IntDiv Internal diversity (mean pairwise 1-Tc) > 0.85
SNN Similarity to nearest neighbor in training < 0.6 (novel)

Read the full file on GitHub · 145 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 145 lines · 78 tokens per session scan A 5af0859e1534

Subscribe to this mod's changes

generative-design is a skill published in the GitHub repository Kdevos12/ALKYL (6 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 1,781 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

add-tool

Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.

cyanheads/pubchem-mcp-server · 35 tokens

api-errors

McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.

cyanheads/pubchem-mcp-server · 54 tokens

field-test

Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…

cyanheads/pubchem-mcp-server · 76 tokens

tool-defs-analysis

Read-only audit of MCP definition language across an existing surface — tools, resources, prompts, server instructions. Walks every definition file and checks 16 categories the LLM reads to decide whether and how to call: voice & tense, internal leaks, audience leaks, defaults, recovery hints, field descriptions…

cyanheads/pubchem-mcp-server · 177 tokens

add-service

Scaffold a new service integration. Use when the user asks to add a service, integrate an external API, or create a reusable domain module with its own initialization and state.

cyanheads/pubchem-mcp-server · 38 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…

cyanheads/pubchem-mcp-server · 112 tokens