Skills
ENCODE Toolkit Setup and Configuration
Provides instructions for installing, configuring, and verifying the ENCODE Toolkit MCP server. It covers installation via uvx or pip, managing credentials, and testing connections using metadata and search queries.
Search and explore ENCODE genomics data
This skill facilitates comprehensive querying and exploration of the ENCODE Project's vast genomics dataset. It guides users through a structured, multi-phase search process, allowing them to first explore available facets, validate metadat…
Cross-study scRNA-seq meta-analysis and integration
This skill integrates multiple single-cell RNA-seq datasets into a unified cell atlas. It performs rigorous meta-analysis, correcting for batch effects, technical dropout, and ambient contamination to assess reproducible cell type definitio…
generate scientific writing from provenance data
This skill auto-generates publication-ready scientific documentation, including methods sections and figure legends, directly from ENCODE analysis provenance records. It ensures rigorous reporting of all experimental and computational param…
Characterize Genomic Regulatory Elements Using ENCODE Data
This skill facilitates the discovery and classification of cis-regulatory elements (cCREs) by integrating ENCODE's comprehensive catalog with multi-omic data. It supports advanced analysis of chromatin states, identifying promoters, enhance…
Comprehensive ENCODE Data Quality Assessment Skill
This skill evaluates the reliability of ENCODE experiments by interpreting multiple orthogonal quality metrics, such as FRiP, NSC, and NRF, alongside official audit flags. It provides deep guidance for filtering and comparing data across va…
Publication Trust Assessment and Reliability Check
This skill systematically assesses the scientific reliability of academic publications by checking for formal retractions, errata, and expressions of concern. It critically searches for independent contradictions and replication failures ac…
WGBS Pipeline: FASTQ to Methylation Calling
This skill executes the full ENCODE WGBS pipeline, processing paired-end FASTQ reads through alignment, deduplication, and methylation extraction. It generates per-CpG methylation levels in the standardized bedMethyl format, suitable for do…
ENCODE Hi-C Data Processing Pipeline
This Nextflow pipeline processes Hi-C FASTQ files to generate multi-resolution contact matrices and chromatin loop calls. It integrates BWA, pairtools, Juicer, and cooler for end-to-end chromatin conformation analysis.
ENCODE pipeline workflow generation and management
This skill facilitates the generation and execution of standardized ENCODE bioinformatics pipelines, supporting custom Nextflow or WDL workflows. It manages compute resource requirements and deployment across local, HPC, and major cloud pla…
Translate Contentrain Content Across Locales
This skill automates the translation of Contentrain content entries into new locales while adhering to strict i18n quality, vocabulary, and string length constraints. It manages the end-to-end workflow from identifying translation gaps to v…
Validate and fix content schema issues
This skill diagnoses content validity against defined model schemas, identifying structural, type, and relational errors. It can automatically apply safe fixes and guide the user through re-validation and submission workflows.
ENCODE DNase-seq Pipeline for Hotspots and Footprints
This skill executes the comprehensive ENCODE DNase-seq pipeline, processing paired FASTQ reads to identify DNase hypersensitive sites (DHSs) and perform TF footprinting analysis. It utilizes Nextflow to generate critical data products, incl…
Launch Contentrain Local Review Interface
Launches a local web interface for visual review of content, branches, and validation results. It acts as a monitoring and approval surface for developer-led decisions on agent-driven changes.
ENCODE ChIP-seq Analysis Pipeline for Peak Calling
This skill executes a complete, standards-compliant ChIP-seq workflow, processing raw FASTQ files through alignment, MACS2 peak calling, and IDR analysis. It generates comprehensive peak sets and signal tracks, adhering to ENCODE guidelines…
Type-safe Contentrain Query SDK
A type-safe SDK for querying Contentrain content using a Prisma-pattern generated client. It supports both synchronous local data access and asynchronous remote fetching via CDN mode.
ENCODE ATAC-seq Pipeline for Chromatin Accessibility Analysis
This skill executes the comprehensive ENCODE ATAC-seq workflow, processing raw FASTQ files through alignment, Tn5 offset correction, and filtering. It generates high-quality peak calls and signal tracks suitable for detailed chromatin acces…
ENCODE Peak Annotation and Functional Enrichment
Annotate ENCODE genomic peaks with regulatory features and nearby genes using ChIPseeker and GREAT. The workflow enables genomic feature distribution analysis and functional enrichment via clusterProfiler.
Comprehensive content quality and compliance review
This skill executes a comprehensive pre-publish audit, validating content against industry standards including SEO, accessibility, security, and i18n completeness. It generates a structured report detailing critical, warning, and informatio…
Content Quality and SEO Compliance Review
This skill enforces comprehensive content standards, covering SEO best practices, heading hierarchy, and structural integrity. It validates content against defined tone, vocabulary, and accessibility rules across various content types.
ENCODE Multi-Omics Data Integration
Integrates multiple ENCODE data types, including RNA-seq, ATAC-seq, and ChIP-seq, to construct a comprehensive regulatory landscape for specific tissues or cell types. It enables chromatin state annotation, enhancer-gene linkage, and the ch…
Codebase Normalization and Content Extraction
This skill normalizes codebases by extracting hardcoded strings into a managed content repository and subsequently patching the source files with content references. This two-phase process ensures content is centralized, translatable, and m…
Aggregate DNA Methylation Data Across Studies
Construct comprehensive tissue-level DNA methylation landscapes by aggregating WGBS data from multiple ENCODE experiments. The process includes quality-gating, coverage filtering, and the identification of hypomethylated regions and partial…
Motif discovery and enrichment analysis for peak data
This skill guides the enrichment analysis of transcription factor binding motifs in ChIP-seq and ATAC-seq peaks. It covers best practices and workflows using industry-standard suites like HOMER and MEME for both de novo and known motif disc…