By galeep
Cheminformatics, molecular ML featurization, docking, and medicinal chemistry workflows.
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.
Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A curated Claude Code plugin marketplace. Currently hosts K-Dense AI's scientific tooling split into focused, individually-installable plugins so you only load what you need.
# Add the marketplace (one time)
claude plugin marketplace add galeep/plugin-place
# List what's available
claude plugin search @plugin-place
# Install whichever pieces you want
claude plugin install sci-bioinformatics-genomics@plugin-place
claude plugin install sci-machine-learning@plugin-place
claude plugin install kdense-document-skills@plugin-place
19 plugins, 135 skills, all sourced from K-Dense AI and licensed MIT. Two upstream repos vendor in, pinned to release tags:
v2.38.0 — 135 scientific skills, split here into 17 domain plugins
plus the general-purpose kdense-document-skills pluginv2.13.0 — full writer plugin with a /scientific-writer-init command| Plugin | Skills | What it covers |
|---|---|---|
sci-bioinformatics-genomics | 20 | Sequence analysis, scRNA-seq, gene regulatory networks, variants, phylogenetics, biomedical DBs |
sci-cheminformatics-drug-discovery | 9 | Cheminformatics, molecular ML, docking, medicinal chemistry |
sci-proteomics-mass-spec | 3 | LC-MS/MS, spectral matching, glycoengineering |
sci-clinical-research | 4 | CDS, clinical/case/trial reports, treatment plans, ISO 13485 |
sci-healthcare-ai | 2 | PyHealth, NeuroKit2 biosignal processing |
sci-medical-imaging | 4 | DICOM, WSI, computational pathology, NCI Imaging Data Commons |
sci-machine-learning | 16 | scikit-learn, Lightning, transformers, RL, time series, GNNs, Bayesian, SHAP, GPU/compute helpers |
sci-materials-chemistry | 2 | pymatgen, COBRApy |
sci-physics-astronomy | 6 | astropy, sympy, qutip, qiskit, cirq, pennylane |
sci-engineering-simulation | 4 | SimPy, pymoo, CFD, molecular dynamics |
sci-data-analysis-viz | 14 | Stats, EDA, networks, survival, plotting, big-data dataframes, MATLAB, US fiscal data |
sci-geospatial | 2 | GIS, remote sensing, earth-observation ML |
sci-lab-automation | 11 | Benchling, DNAnexus, LatchBio, OMERO, Opentrons, protocols.io, PyLabRobot, flow cytometry, Neuropixels |
sci-scientific-communication | 22 | Lit review, peer review, writing, citations, posters, slides, schematics, infographics, academic web search |
sci-multi-omics | 3 | DepMap, PrimeKG, scvi-tools |
sci-protein-engineering | 2 | ESM, Adaptyv Bio Foundry |
sci-research-methodology | 7 | Hypothesis generation, grant writing, brainstorming, critical thinking, scenario analysis |
kdense-document-skills | 4 | General-purpose .docx, .pdf, .pptx, .xlsx tools (useful with any plugin) |
claude-scientific-writer | 23 | K-Dense's full writer plugin including the /scientific-writer-init command |
The claude-scientific-writer plugin and the sci-* plugins share most of
their skills (K-Dense maintains the same skill code in both upstreams).
Specifically:
sci-* plugins
(mostly sci-scientific-communication, plus sci-clinical-research and
sci-research-methodology)/scientific-writer-init slash
command (which the bare skills lack)Pick one approach:
sci-* plugins: get exactly the domain slices
you want, granular enable/disableInstalling both will give you duplicate skill names, which is unsupported and will confuse Claude Code's skill router.
plugins.yaml is the source of truth. Everything else is generated:
git submodule update --init --recursive
bash scripts/build.sh
This regenerates plugins/* and .claude-plugin/marketplace.json from
the YAML and the pinned upstream submodules. The build is idempotent —
edits inside plugins/* will be overwritten.
The built plugin kind copies a chosen subset of skills from an upstream
submodule. The vendored plugin kind copies an entire upstream plugin
intact (skills, commands, agents, hooks) and generates a plugin.json
from its upstream marketplace metadata. A local kind is reserved for
plugins authored directly in this repo.
To add a new plugin, edit plugins.yaml and rerun scripts/build.sh.
npx claudepluginhub galeep/plugin-place --plugin sci-cheminformatics-drug-discoveryClinical decision support, clinical/case/trial reports, treatment plans, and ISO 13485 QMS docs.
Sequence analysis, single-cell RNA-seq, gene regulatory networks, variant data, phylogenetics, and biomedical database lookup.
LC-MS/MS processing, spectral matching, peptide ID, and glycoengineering.
DICOM, whole-slide imaging, computational pathology, and NCI Imaging Data Commons.
EHR/physiological-signal ML: PyHealth pipelines and NeuroKit2 biosignal processing.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.