Menu
Skills in this repository
SkillsMP has collected 810 skills from mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-. Open a skill to review its source and details.
mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-Showing 40 of 810 collected skills.
Design and operate browser and desktop agents that rely on screenshots, mouse and keyboard control, or hybrid bash/editor/computer loops. Use when deciding between DOM automation, browser agents, and full computer-use workflows.
Implement and operate Azure AI Foundry and Microsoft Foundry workloads with explicit identity, deployment, model versioning, safety, and agent-service controls. Use when deploying model endpoints, migrating model versions, or setting up production guardrails…
Integrate and operate Cohere APIs with current model, rerank, embedding, transcribe, and SDK guidance. Use when selecting Cohere models, building search or agent workflows, or planning migration across Cohere platform updates.
Build, evaluate, and deploy agents with Google's Agent Development Kit (ADK). Use when you want code-first multi-agent systems, workflow agents, MCP tools, or Google-supported agent deployment paths.
Build typed, provider-agnostic agents with PydanticAI. Use when structured I/O, dependency injection, MCP support, and OpenTelemetry-friendly observability matter more than framework hype.
Integrate and operate DeepSeek APIs with current docs and compatibility guidance. Use when implementing DeepSeek chat, reasoning, tool calling, or FIM workflows through its OpenAI-compatible API.
Integrate and operate Mistral APIs with current model catalog, SDKs, and agent features. Use when implementing Mistral chat, agents, conversations, files, or coding workflows.
Integrate and operate xAI Grok APIs with current documentation and SDK guidance. Use when implementing Grok tool use, Responses-style workflows, files or collections search, or migration from other provider SDKs.
Deploy AgentScope + AgentScope Runtime for secure sandboxed multi-agent services inside BioKernel.
Run OpenHands headless CLI/SDK missions from BioKernel swarms for autonomous software work.
Parse scholarly articles (PDF, DOI, URL) to extract metadata, GEO accessions, and acquisition links using OpenAlex + GROBID pipelines.
Cell type annotation for spatial transcriptomics data using marker-based scoring, Tangram mapping, scANVI transfer, or CellAssign probabilistic models.
Copy number variation inference from spatial transcriptomics expression data.
Cell-cell communication analysis via ligand-receptor interaction scoring using LIANA, CellPhoneDB, FastCCC, or CellChat.
Experimental condition comparison using pseudobulk differential expression with proper multi-sample statistics.
Differential expression analysis — find marker genes for clusters or compare two groups. Supports Wilcoxon rank-sum, t-test, and PyDESeq2 methods with publication-ready figures and CSV tables.
Cell type deconvolution for spatial transcriptomics — estimates per-spot cell type proportions using FlashDeconv, Cell2Location, RCTD, DestVI, Stereoscope, Tangram, SPOTlight, or CARD.
Identify tissue regions and spatial niches from preprocessed spatial transcriptomics data using Leiden, Louvain, SpaGCN, STAGATE, GraphST, or BANKSY.
Pathway and gene set enrichment analysis for spatial transcriptomics data.
Find genes with spatially variable expression patterns using Moran's I, SpatialDE, SPARK-X, or FlashS. Identifies genes whose expression is non-randomly distributed across tissue coordinates.
Multi-sample integration and batch correction for spatial transcriptomics data.
Load spatial transcriptomics data (Visium, Xenium, MERFISH, Slide-seq, generic h5ad), perform QC filtering, normalization, HVG selection, PCA, UMAP, and Leiden clustering.
Spatial registration and multi-slice alignment for spatial transcriptomics data.
Comprehensive spatial statistics toolkit — cluster-level (neighborhood enrichment, Ripley, co-occurrence), gene-level (Moran's I, Geary's C, local Moran, Getis-Ord), and network-level analysis.
Trajectory inference and pseudotime analysis for spatial transcriptomics data.
RNA velocity and cellular dynamics analysis for spatial transcriptomics data.
Bulk RNA-seq count matrix QC — library size, gene detection rates, and sample correlation.
WGCNA-style weighted gene co-expression network analysis — module detection, soft thresholding, hub genes.
Bulk RNA-seq differential expression analysis using PyDESeq2 with optional edgeR/limma-voom via rpy2.
Bulk RNA-seq cell type deconvolution using NNLS (built-in), with optional CIBERSORTx and MuSiC bridges.
Pathway enrichment analysis for bulk RNA-seq — ORA and GSEA via GSEApy, with built-in hypergeometric fallback.
Alternative splicing analysis — PSI quantification, differential splicing event detection from rMATS/SUPPA2 output.
Batch integration for multi-sample scRNA-seq using Harmony, scVI, Seurat CCA/RPCA, BBKNN, and fastMNN. Remove technical variation while preserving biological differences.
Automated cell type annotation using marker genes, CellTypist, SingleR, or scmap. Supports custom references and marker gene lists.
Cell-cell communication analysis via ligand-receptor interaction scoring using CellChat (R), NicheNet (R), LIANA (Python), or built-in L-R database.
Differential expression analysis for single-cell data — marker gene discovery using Wilcoxon, t-test, MAST, or DESeq2 pseudo-bulk analysis.
Doublet detection and removal using Scrublet (Python), DoubletFinder (R), and scDblFinder (R). Essential QC step before clustering.
Gene regulatory network inference using pySCENIC three-step pipeline (GRNBoost2 → cisTarget → AUCell), with correlation-based fallback. Identifies transcription factor regulons and scores their activity per cell.
Multi-omics integration for single-cell data (CITE-seq, 10X Multiome, SHARE-seq). Weighted Nearest Neighbor (WNN) analysis, MOFA+, and muon/MuData workflows.
Single-cell RNA-seq QC, normalization, HVG selection, PCA, UMAP, and Leiden clustering. Supports both Scanpy (Python) and Seurat (R) workflows.