Skill Claude CodeCodex
This directory contains bioinformatics upstream analysis skills for agent-assisted data processing. Each skill provides workflow guidance, code templates, and best practices for specific analysis types.
Agent
Analysis expert in Single-Cell and Spatial Omics data analysis, with expertise in analyze data with python tools in scverse ecosystem and jupyter notebook. It's has the visual understanding ability can observe and understand the images.
Agent
Biologist agent, thinking like a professional biologist, with expertise in generating hypotheses and interpreting the analysis results. It's has the ability to combine the observation of the analysis results and collect the background information from the literatures to interpret the results in the biological aspect.
Agent
Browser use agent, with expertise in using the browser to search the web and collect the information.
Agent
You are an team leader AI-agent for perform single-cell/Spatial Omics related tasks.
Agent
Reporter agent, summarizing the results and conclusions. It's has the ability to summarize the all work process and the results and organize them in a professional paper format.
Agent
System manager agent, responsible for the system environment investigation and software environment installation.
Skill Claude CodeCodex
Here are some skills about the best practices for analyzing the single-cell/Spatial Omics data. When you need to do the specific analysis tasks described in this file, you can load the related skill files linked here to help you.
Agent
Specialized execution agent for OmicVerse-based analysis. Uses OmicVerse lookup helpers from the same Python runtime as notebook execution, avoiding dependency on a separate Pantheon omicverse toolset.
Agent
Coordinator for OmicVerse analysis projects. Routes work between the OmicVerse execution specialist, researcher, and illustrator while keeping analysis outputs organized in a reproducible workdir.
Agent
Develops, tests, and maintains reusable Pantheon packages. Expert in ToolSet API, docstring best practices, and package structure.
Agent
Information-gathering specialist: codebase research, web & literature search, reading and structuring existing material. Use for "explore / read / understand / search / look into ..." tasks. Returns findings and reference documents — does NOT run analyses, execute code, or produce computational deliverables (that…
Agent
BioRender-style scientific illustration expert. Generates publication-quality figures for papers using the generateimage tool. Specializes in clean vector-style diagrams, pathways, and cell structures.
Skill Claude CodeCodex
Skills for biological image analysis: cell/nucleus segmentation, image restoration, and spatial data processing.
Skill Claude CodeCodex
Cell and nucleus segmentation tools for microscopy images. Covers Cellpose, SAM-based methods, StarDist, InstanSeg, and Mesmer.
Skill Claude CodeCodex
Drive the user's Atrium desktop: open files in installed viewer apps (Viv bioimages, Vitessce/Spatial 3D omics, Mol structures, IGV/Gosling genomics, Volume 3D, Cytoscape, MSA, PhyloTree, RDKit), read and steer ANY window — including ones the user opened — and call app backends.
Skill Claude CodeCodex
Aesthetic guidelines and output-type recipes for scientific figure production. Supports lightweight default-agent use through SKILL.md + one outputType recipe, with optional venue-specific style guides when requested.
Skill Claude CodeCodex
Skills for single-cell and spatial omics data analysis. Best practices, code snippets, and workflows for the scverse ecosystem.
Skill Claude CodeCodex
Skills for querying and downloading data from genomic, transcriptomic, 3D-genome, and cancer-genomics databases. Covers programmatic access to public repositories, gene annotation, sequence retrieval, processed functional-genomics tracks, Hi-C / Micro-C contact matrices, TCGA-style cohorts, and large-scale single-cell…
Skill Claude CodeCodex
Panel design for DEVELOPING / dynamic systems (embryonic organs, differentiation, regeneration). The target experiment is usually a LATE / terminal stage, but the biology is a trajectory: terminal cell types are end-products of earlier lineage programs. A panel built from the target stage alone resolves terminal…
Skill Claude CodeCodex
End-to-end workflow for gene panel design in scRNA-seq and spatial transcriptomics, that should be STRICTLY followed: dataset understanding + smart downsampling + train/test splits, algorithmic selection (HVG/DE/RF/scGeneFit/SpaPROS), optimal sub-panel discovery (ARI vs size), biological completion with a stability…
Skill Claude CodeCodex
General-purpose skills for data analysis infrastructure: workspace file organization, environment management, parallel computing, and performance.
Skill Claude CodeCodex
Skills derived from the Single-cell Best Practices book (sc-best-practices.org). Comprehensive workflows and guidelines for single-cell and spatial omics analysis.
Skill Claude CodeCodex
Workflow guidance and model reference for single-cell foundation models (scGPT, Geneformer, UCE, scBERT, etc.). Covers model selection, validation-first workflow, and per-model I/O contracts.