Scientific

torchdrug is a PyTorch-native toolkit for molecular and protein machine learning. Use the torchdrug skill to choose tasks, datasets, and modular models for graph neural networks, protein modeling, knowledge graph reasoning, molecular generation, and retrosynthesis. It is best for custom model development and reproducible configs, not just canned demos.

optimize-for-gpu helps turn CPU-bound Python into NVIDIA GPU code with the right library choice. Use it for arrays, dataframes, ML pipelines, graph analytics, imaging, geospatial work, vector search, and custom kernels. It guides CuPy, cuDF, cuML, cuGraph, cuCIM, cuVS, KvikIO, Numba CUDA, and Warp decisions with practical optimize-for-gpu usage and migration advice.

diffdock is a docking skill for predicting protein-ligand binding poses from PDB structures or protein sequences plus ligands in SMILES, SDF, or MOL2. Use the diffdock skill for structure-based drug design, virtual screening, and confidence-scored pose analysis. It is not for binding affinity prediction.

scikit-survival skill for survival analysis and time-to-event modeling in Python. Use this guide for censored data, Cox models, random survival forests, gradient boosting, Survival SVMs, and survival metrics like concordance index and Brier score.

scientific-schematics turns natural-language prompts into publication-quality scientific diagrams with smart iterative refinement. It uses Nano Banana 2 for generation and Gemini 3.1 Pro Preview for review, regenerating only when output falls below the threshold for your document type. Built for neural network architectures, system diagrams, flowcharts, biological pathways, and other complex scientific visuals.

scanpy skill for single-cell RNA-seq data analysis in Python. Use it for QC, normalization, PCA, UMAP/t-SNE, clustering, marker gene discovery, trajectory analysis, and publication-quality plots. Best for exploratory scRNA-seq workflows built around AnnData, with clear scanpy usage and install guidance.

The research-grants skill helps turn a rough research idea into a grant-ready proposal for NSF, NIH, DOE, DARPA, or Taiwan NSTC. It supports sponsor fit, compliant structure, budget justification, review-criteria framing, and section drafting for principal investigators, postdocs, and technical writers.

protocolsio-integration is a protocols.io API integration skill for managing scientific protocols programmatically. Use it for search, create, update, publish, step editing, workspace organization, comments, and file handling. It is especially useful for protocolsio-integration for Backend Development, workflow automation, and repeatable protocols.io usage.

The peer-review skill helps you write formal, evidence-based manuscript and grant reviews. Use it to assess methodology, statistics, reproducibility, ethics, and reporting standards like CONSORT, STROBE, or PRISMA, with constructive feedback that authors and editors can act on.

parallel-web is a web research and extraction skill powered by parallel-cli. It helps you search the web, extract URL content, enrich data from sources, and run deeper research with academic and scientific sources prioritized. Use it for parallel-web usage, web research, citations, and evidence-first workflows.

paperzilla is a chat-and-CLI skill for working with Paperzilla projects, recommendations, canonical papers, markdown summaries, feedback, and feed export. Use it when you need direct access to Paperzilla data for Academic Research, not just a generic summary. It helps with paperzilla usage, paperzilla guide tasks, and structured output.

matplotlib skill for Python plotting with full control over axes, labels, legends, layouts, and export formats. Use it for scientific figures, multi-panel analyses, custom chart types, and reproducible visualizations when you need more precision than a generic chart prompt. It is a strong matplotlib guide for Data Analysis and publication-ready plots.

markdown-mermaid-writing is a Markdown and Mermaid diagram writing skill for scientific and technical documentation. Use it to turn workflows, architectures, analyses, and reports into editable text-first docs with clear diagrams, version control friendliness, and practical markdown-mermaid-writing usage for Technical Writing.

latex-posters helps you create professional research posters in LaTeX for conferences, symposia, thesis defenses, and scientific communication. It covers package-aware workflows for beamerposter, tikzposter, and baposter, with guidance on layout, hierarchy, figures, citations, and print-ready poster design.

The literature-review skill supports systematic literature-review workflows for Academic Research, including source discovery, citation verification, thematic synthesis, and polished markdown or PDF outputs. Use it for literature-review guide tasks, meta-analyses, scoping reviews, and research briefs across scientific and technical domains.

The lamindb skill helps you work with LaminDB, an open-source biology data framework for making data queryable, traceable, reproducible, and FAIR. Use it for lamindb for Data Analysis, metadata curation, ontology-based annotation, schema validation, and lineage-aware workflows across notebooks and pipelines.

imaging-data-commons helps you query and download public cancer imaging data from NCI Imaging Data Commons with idc-index. Use it for imaging-data-commons usage across CT, MR, PET, and pathology datasets, including metadata search, browser preview, licensing checks, and AI training or data analysis workflows. No authentication required.

The infographics skill helps you create publication-ready visuals from a topic, dataset, or narrative. It supports infographics for Data Visualization with Nano Banana Pro generation, Gemini 3 Pro quality review, optional research, accessible palettes, and iterative refinement for marketing, reports, timelines, comparisons, and social layouts.

gget is a bioinformatics skill for fast, unified access to 20+ genomic databases and analysis tools from CLI or Python. Use it for gene info, BLAST-related lookups, AlphaFold structures, expression data, disease associations, and enrichment-style analysis. It suits quick exploration and gget for Data Analysis workflows.

get-available-resources checks CPU, GPU, memory, and disk before heavy scientific or ML workflows. It returns a resource snapshot and practical recommendations for parallel processing, GPU acceleration, or memory-safe approaches, helping agents make better execution choices for workflow automation.

The exploratory-data-analysis skill turns scientific files into format-aware EDA reports. It detects file type, summarizes structure and quality, extracts key metadata, and suggests downstream analysis. Use it for exploratory-data-analysis for Data Analysis across chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and other scientific file formats.

exa-search is a web research skill powered by Exa for finding current information and extracting content from URLs. Use it for search, source discovery, article and PDF extraction, and technical or scientific research with semantic retrieval, academic-style filtering, and clear install and usage guidance.

etetoolkit is a phylogenetic tree toolkit for ETE workflows. Use the etetoolkit skill to parse, edit, compare, root, prune, and visualize trees in Newick, NHX, PhyloXML, or NeXML. It supports phylogenomics, orthology/paralogy analysis, NCBI taxonomy, and publication-style PDF or SVG output.

depmap helps analyze the Cancer Dependency Map for cancer cell line gene dependency scores, drug sensitivity, and gene effect profiles. Use it to identify cancer-specific vulnerabilities, synthetic lethal interactions, and validate oncology drug targets with a reproducible depmap guide for Data Analysis.