home / skills / omer-metin / skills-for-antigravity / genomics-pipelines

genomics-pipelines skill

This skill helps you design robust, reproducible genomics pipelines by applying patterns for workflow management, data processing, and variant analysis.

npx playbooks add skill omer-metin/skills-for-antigravity --skill genomics-pipelines

Review the files below or copy the command above to add this skill to your agents.

Files (4)

SKILL.md

1.1 KB

---
name: genomics-pipelines
description: Patterns for building robust, reproducible genomics analysis pipelines. Covers workflow managers, NGS data processing, variant calling, RNA-seq, and common bioinformatics pitfalls. Use when ", " mentioned. 
---

# Genomics Pipelines

## Identity



## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Overview

This skill presents patterns for building robust, reproducible genomics analysis pipelines. It focuses on workflow managers, NGS data processing, variant calling, RNA-seq, and common bioinformatics pitfalls. Use this skill when the phrase ", " is present to trigger guidance tied to these patterns and safety checks.

How this skill works

When creating pipelines, I consult the canonical patterns file to decide architecture, tooling, and modular structure. For diagnosing problems, I use the sharp edges reference to identify critical failure modes and explain root causes. For reviews and validations, I apply the strict rules from the validations reference to check inputs, outputs, and constraints objectively.

When to use it

Designing a new end-to-end genomics workflow (alignment → QC → variant calling)
Refactoring pipelines to improve reproducibility, modularity, or scalability
Troubleshooting pipeline failures or unexpected biological results
Validating pipeline inputs/outputs against strict constraints
Preparing pipelines for cloud deployment or workflow orchestration

Best practices

Follow the patterns reference for structure: modular tasks, clear I/O contracts, and workflow manager conventions
Embed comprehensive validations: sample metadata checks, file formats, and parameter ranges before execution
Fail fast on critical errors identified in the sharp edges guidance to avoid downstream corruption
Containerize tools and pin versions to ensure reproducibility across environments
Log deterministic provenance information for each run: inputs, parameters, code commit, and environment

Example use cases

Implementing a Snakemake or Nextflow pipeline for paired-end RNA-seq with QC and differential expression
Building a variant-calling workflow that standardizes pre-processing, alignment, duplicate marking, and joint genotyping
Diagnosing intermittent crashes linked to input validation or resource exhaustion using the sharp edges checklist
Reviewing user-submitted pipelines to ensure they meet the validations constraints before production deployment

FAQ

What references does this skill use to make recommendations?

Creation guidance comes from the patterns reference; diagnosis uses the sharp edges file to explain failures; reviews follow the validations reference for strict checks.

How do I reduce non-reproducible behavior in my pipeline?

Pin tool versions, use containers, record deterministic provenance, validate inputs early, and follow the modular patterns to avoid hidden state.