Instructions file CodexOpenCode
Instructions for TianGzlab/OmicsClaw, covering agents.md — omicsclaw guide for ai coding agents, repository working contract, project overview, setup and pip install -e .
Instructions file
Instructions for TianGzlab/OmicsClaw, covering claude.md — omicsclaw agent instructions, repository maintenance contract, agent skills, issue tracker and triage labels.
Agent
OmicsClaw uses one primary repository context with a Bench-specific supplement.
Agent
Issues and PRDs for this repository live in GitHub Issues for zhou-1314/OmicsClaw. Use the gh CLI for issue operations.
Agent
Engineering skills use five canonical triage roles. Each role maps directly to the corresponding GitHub label.
Skill Claude CodeCodex
Systematic workflow for clustering biological samples, features, or any quantitative data matrix. Implements multiple clustering algorithms with rigorous validation, comparison, and interpretation to identify meaningful data groupings.
Skill Claude CodeCodex
Core DESeq2 workflow for RNA-seq differential expression analysis with count data.
Skill Claude CodeCodex
Skill "Cell-Cell Communication Analysis (CellChat)" from TianGzlab/OmicsClaw, covering cell-cell communication analysis (cellchat v2), when to use this skill, installation, inputs and outputs.
Skill Claude CodeCodex
Compare two groups of experiments to identify differential peak regions (DPR) or differentially methylated regions (DMR) using the ChIP-Atlas Diff Analysis API.
Skill Claude CodeCodex
Find ChIP-seq peak enrichment near your genes using the official ChIP-Atlas Enrichment Analysis API.
Skill Claude CodeCodex
Find target genes for any transcription factor using pre-computed ChIP-Atlas public ChIP-seq data.
Skill Claude CodeCodex
Skill "ClinicalTrials.gov Disease Landscape Scanner" from TianGzlab/OmicsClaw, covering clinicaltrials.gov disease landscape scanner, when to use this skill, installation, inputs and outputs.
Skill Claude CodeCodex
Build weighted gene co-expression networks to identify modules of coordinately expressed genes and discover hub genes that may be key regulators. This workflow uses WGCNA (Weighted Gene Co-expression Network Analysis) to group genes into modules based on their expression patterns across samples, then correlates these…
Skill Claude CodeCodex
Use this skill when you have longitudinal patient omics data and want to.
Skill Claude CodeCodex
Comprehensive workflow for statistical experimental design in genomics, from power analysis and sample size determination to batch-balanced experimental layouts and multiple testing strategy.
Skill Claude CodeCodex
Translate differential expression results into biological insights using GSEA and ORA.
Skill Claude CodeCodex
Annotate genomic variants in VCF files with functional effects, clinical significance, and pathogenicity predictions.
Skill Claude CodeCodex
Infer gene regulatory networks (GRNs) de novo from single-cell RNA-seq data using pySCENIC. This workflow discovers transcription factor (TF) regulons directly from expression patterns and calculates cell-level TF activity scores.
Skill Claude CodeCodex
Identify genes whose genetically regulated expression is associated with disease risk, determine therapeutic directionality (inhibit vs. activate), and prioritize drug targets with causal genetic evidence using Transcriptome-Wide Association Study (TWAS) analysis.
Skill Claude CodeCodex
Select minimal, interpretable biomarker panels from high-dimensional omics data using penalized logistic regression (LASSO/elastic net) with nested cross-validation and stability selection.
Skill Claude CodeCodex
Search Consensus (consensus.app) for preclinical studies on a molecular target in a disease, then extract structured in vitro and in vivo experiment details from each paper.
Skill Claude CodeCodex
Not suitable for: One-sample MR (individual-level data), non-linear MR, multivariable MR with >2 exposures.
Skill Claude CodeCodex
Identify latent factors driving variation across 2+ omics layers using MOFA+ (Multi-Omics Factor Analysis). Decomposes multi-omics data into interpretable factors, each capturing shared or view-specific biological signal. Handles missing data across views natively.
Skill Claude CodeCodex
Comprehensive PCR and qPCR primer design following MIQE 2.0 guidelines with automated validation.