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

molfeat — Claude Code skill: molecular featurization

Converts molecular structures into fingerprints, descriptors, and embeddings for machine learning, similarity search, and screening. Requires Python 3.11+, RDKit, and PyTorch.

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

What molfeat does

This skill provides Molfeat 1.0.0 for turning SMILES and RDKit molecules into numerical features. Supports ECFP and MACCS fingerprints, RDKit 2D/3D descriptors, pharmacophore pairs, and pretrained embeddings from Hugging Face. You can persist and reload featurizer state in YAML format.

Version 1.0 removed DGL, legacy Graphormer, and protein adapters—older model cards referencing them no longer work. Requires Python 3.11–3.14; Intel macOS is limited to 3.11–3.12 with NumPy<2 and Transformers<5. Pretrained models download weights and need internet; core fingerprints run offline. Always retain source IDs, labels, preprocessing policy, package versions, and molecular standardization rules—state must be revalidated after upgrading to 1.x.

What it helps with

  • Calculate molecular fingerprints (ECFP, MACCS) for a dataset
  • Extract descriptors and pharmacophore features from structures
  • Load pretrained embeddings from Hugging Face models
  • Save and restore featurizer configuration across runs
  • Align results by molecule ID and exclude invalid records

Example prompts for the agent

  • Generate ECFP radius-2 fingerprints from these SMILES and filter invalid ones
  • Load ChemBERTa embeddings for my molecules
  • Save the featurizer state to YAML and apply it to the test set

How to install molfeat

1Skills CLI (Vercel)

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

2Manually: put the files in place

~/.claude/skills/molfeat/SKILL.md

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

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

azure-architecture-autopilot official github Design Azure infrastructure from a prompt or inspect existing resources, then work through diagrams, Bicep generation and deployment. Use it for a new build or changes to an existing setup. GitHub Copilot 1,500installs agent-owasp-compliance official github Checks an AI agent codebase against the 10 OWASP ASI risks. Use it before production deployment, for security review, or when preparing an audit report. GitHub Copilot 1,500installs rag-architect https://github.com/Jeffallan Designs production RAG systems: chunks documents, generates embeddings, configures vector stores, builds hybrid search pipelines, and evaluates retrieval quality. Claude Code CX Codex Cursor +1 4,700installs ads-microsoft AgriciDaniel Audits Microsoft Ads, Bing Ads, UET, and audience network campaigns: measurement, conversions, Google imports, keywords, creative, bidding, and budgets. Read-only; use ads-optimize to make changes. Claude Code CX Codex Cursor +1 3,800installs azure-speech-to-text calesthio Transcribes local audio files into text with word-level timestamps and speaker diarization using Azure AI Speech. Speeds up subtitle creation and audio processing in OpenMontage pipelines. Claude Code CX Codex Cursor +1 763installs langgraph-persistence langchain-ai A Claude Code skill for LangGraph persistence: wiring a checkpointer, keeping conversations apart by thread_id, and replaying older graph state. Claude Code CX Codex Cursor +1 18,000installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs

Questions about molfeat

How do I install molfeat in Claude Code?

Run npx skills add K-Dense-AI/scientific-agent-skills --skill molfeat -a claude-code. The skill will appear at ~/.claude/skills/molfeat/SKILL.md.

What are the requirements for molfeat?

Python 3.11–3.14 and molfeat 1.0.0, RDKit, datamol, and PyTorch. Intel macOS requires Python 3.11–3.12. Pretrained models need optional extras (molfeat[transformer]) and internet access.

What changed from version 0.11 to 1.0.0?

Removed DGL, Graphormer, and protein adapters. Older model cards referencing these no longer work. Refer to the 1.0 migration guide in the repository.

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