encode-toolkit 0.3.0b5__tar.gz → 0.3.0b8__tar.gz

encode_toolkit-0.3.0b8/.claude-plugin/marketplace.json

@@ -0,0 +1,18 @@
+{
+  "name": "ammawla",
+  "owner": {
+    "name": "Dr. Alex M. Mawla, PhD"
+  },
+  "metadata": {
+    "description": "ENCODE Project genomics research infrastructure for Claude Code",
+    "homepage": "https://github.com/ammawla/encode-toolkit"
+  },
+  "plugins": [
+    {
+      "name": "encode-toolkit",
+      "version": "0.3.0-beta.8",
+      "source": "./plugin",
+      "description": "20 ENCODE API tools + 47 expert skills for genomics research. Search experiments, download files with MD5 verification, run pipelines, and cross-reference 14 databases."
+    }
+  ]
+}

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8}/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "encode-toolkit",
-  "description": "20 ENCODE API tools + 48 expert skills for genomics research. Search experiments, download files with MD5 verification, run pipelines, and cross-reference 14 databases.",
-  "version": "0.3.0-beta.5",
+  "description": "20 ENCODE API tools + 47 expert skills for genomics research. Search experiments, download files with MD5 verification, run pipelines, and cross-reference 14 databases.",
+  "version": "0.3.0-beta.8",
   "author": {
     "name": "Dr. Alex M. Mawla, PhD",
     "email": "ammawla@ucdavis.edu"
@@ -35,7 +35,12 @@
     "biology",
     "science"
   ],
-  "skills": "skills/*",
+  "mcpServers": {
+    "encode-toolkit": {
+      "command": "npx",
+      "args": ["-y", "encode-toolkit@latest"]
+    }
+  },
   "tools": [
     {
       "name": "encode_search_experiments",

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8}/.gitignore

@@ -51,6 +51,19 @@ data/
 # MCP Registry tokens
 .mcpregistry_*
 
+# Generated PDFs
+*.pdf
+
+# PDF build artifacts
+docs/pdf-build/
+
+# Smithery
+.smithery/
+
+# npm lock (thin wrapper, no deps to lock)
+package-lock.json
+
 # OS
 .DS_Store
 Thumbs.db
+buildwithclaude/

encode_toolkit-0.3.0b8/.mcp.json

@@ -0,0 +1,3 @@
+{
+  "mcpServers": {}
+}

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: encode-toolkit
-Version: 0.3.0b5
+Version: 0.3.0b8
 Summary: MCP server for querying and downloading ENCODE Project genomics data directly from Claude
 Project-URL: Homepage, https://github.com/ammawla/encode-toolkit
 Project-URL: Repository, https://github.com/ammawla/encode-toolkit
@@ -37,7 +37,7 @@ Description-Content-Type: text/markdown
 
 [![License: CC BY-NC-ND 4.0](https://img.shields.io/badge/License-CC_BY--NC--ND_4.0-red.svg)](LICENSE)
 [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
-[![Version](https://img.shields.io/badge/version-0.3.0--beta-yellow)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.3.0--beta.8-yellow)](CHANGELOG.md)
 [![Status](https://img.shields.io/badge/status-beta-yellow)]()
 [![Skills](https://img.shields.io/badge/skills-47-orange)](docs/skill-vignettes/)
 [![Tools](https://img.shields.io/badge/MCP_tools-20-purple)](src/encode_connector/server/main.py)
@@ -65,16 +65,31 @@ Search ENCODE, cross-reference 14 databases, run 7 analysis pipelines, and gener
 
 ## Quick Start
 
-### Claude Code (recommended)
+### Claude Code Plugin (recommended)
+
+Start a new Claude Code session and enter:
+
+```
+/plugin marketplace add ammawla/encode-toolkit
+
+/plugin install encode-toolkit
+```
+
+That's it. All 20 tools, 47 skills, and the MCP connector are now available.
+
+<details>
+<summary><strong>MCP-only install (tools only, no skills)</strong></summary>
+
+If you only need the 20 MCP tools without the 47 workflow skills:
 
 ```bash
 claude mcp add encode -- uvx encode-toolkit
 ```
 
-That's it. All 20 tools and 47 skills are now available in Claude Code.
+</details>
 
 <details>
-<summary><strong>Other installation methods</strong></summary>
+<summary><strong>Other editors and platforms</strong></summary>
 
 #### npx (Node.js)
 
@@ -102,24 +117,10 @@ Then use `encode-toolkit` as the command in any MCP client configuration:
 }
 ```
 
-#### Claude Code — Plugin Install
-
-For the full experience (20 tools + 47 skills), install as a Claude Code plugin:
-
-```bash
-claude plugin add /path/to/encode-toolkit
-```
-
-Or install from a marketplace:
-
-```
-/plugin install encode-toolkit
-```
-
 </details>
 
 <details>
-<summary><strong>Claude Desktop</strong></summary>
+<summary><strong>Claude Desktop (MCP only)</strong></summary>
 
 Add to your `claude_desktop_config.json`:
 

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8}/README.md

@@ -4,7 +4,7 @@
 
 [![License: CC BY-NC-ND 4.0](https://img.shields.io/badge/License-CC_BY--NC--ND_4.0-red.svg)](LICENSE)
 [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
-[![Version](https://img.shields.io/badge/version-0.3.0--beta-yellow)](CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.3.0--beta.8-yellow)](CHANGELOG.md)
 [![Status](https://img.shields.io/badge/status-beta-yellow)]()
 [![Skills](https://img.shields.io/badge/skills-47-orange)](docs/skill-vignettes/)
 [![Tools](https://img.shields.io/badge/MCP_tools-20-purple)](src/encode_connector/server/main.py)
@@ -32,16 +32,31 @@ Search ENCODE, cross-reference 14 databases, run 7 analysis pipelines, and gener
 
 ## Quick Start
 
-### Claude Code (recommended)
+### Claude Code Plugin (recommended)
+
+Start a new Claude Code session and enter:
+
+```
+/plugin marketplace add ammawla/encode-toolkit
+
+/plugin install encode-toolkit
+```
+
+That's it. All 20 tools, 47 skills, and the MCP connector are now available.
+
+<details>
+<summary><strong>MCP-only install (tools only, no skills)</strong></summary>
+
+If you only need the 20 MCP tools without the 47 workflow skills:
 
 ```bash
 claude mcp add encode -- uvx encode-toolkit
 ```
 
-That's it. All 20 tools and 47 skills are now available in Claude Code.
+</details>
 
 <details>
-<summary><strong>Other installation methods</strong></summary>
+<summary><strong>Other editors and platforms</strong></summary>
 
 #### npx (Node.js)
 
@@ -69,24 +84,10 @@ Then use `encode-toolkit` as the command in any MCP client configuration:
 }
 ```
 
-#### Claude Code — Plugin Install
-
-For the full experience (20 tools + 47 skills), install as a Claude Code plugin:
-
-```bash
-claude plugin add /path/to/encode-toolkit
-```
-
-Or install from a marketplace:
-
-```
-/plugin install encode-toolkit
-```
-
 </details>
 
 <details>
-<summary><strong>Claude Desktop</strong></summary>
+<summary><strong>Claude Desktop (MCP only)</strong></summary>
 
 Add to your `claude_desktop_config.json`:
 

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8}/package.json

@@ -1,6 +1,6 @@
 {
   "name": "encode-toolkit",
-  "version": "0.3.0-beta.5",
+  "version": "0.3.0-beta.8",
   "mcpName": "io.github.ammawla/encode-toolkit",
   "description": "ENCODE Toolkit — Genomics research infrastructure with 20 MCP tools, 47 skills, 14 database integrations, and 7 pipelines for Claude Code",
   "main": "index.js",

encode_toolkit-0.3.0b8/plugin/.claude-plugin/plugin.json

@@ -0,0 +1,21 @@
+{
+  "name": "encode-toolkit",
+  "version": "0.3.0-beta.8",
+  "description": "20 ENCODE API tools + 47 expert skills for genomics research. Search experiments, download files with MD5 verification, run pipelines, and cross-reference 14 databases.",
+  "author": {
+    "name": "Dr. Alex M. Mawla, PhD"
+  },
+  "repository": "https://github.com/ammawla/encode-toolkit",
+  "license": "CC-BY-NC-ND-4.0",
+  "keywords": [
+    "genomics",
+    "encode",
+    "bioinformatics",
+    "epigenomics",
+    "chip-seq",
+    "atac-seq",
+    "rna-seq",
+    "pipelines",
+    "science"
+  ]
+}

encode_toolkit-0.3.0b8/plugin/.mcp.json

@@ -0,0 +1,9 @@
+{
+  "mcpServers": {
+    "encode-toolkit": {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "encode-toolkit@latest"]
+    }
+  }
+}

encode_toolkit-0.3.0b8/plugin/CLAUDE.md

@@ -0,0 +1,168 @@
+# ENCODE Toolkit
+
+MCP server for the ENCODE Project (encodeproject.org) — the largest public catalog of functional genomic elements. Version 0.3.0-beta.
+
+## Quick Start
+
+```bash
+python -m venv .venv && source .venv/bin/activate
+pip install -e ".[dev]"
+pytest                    # 506 tests, 98% coverage
+ruff check src/           # lint
+ruff format src/          # auto-format
+encode-toolkit            # run MCP server
+```
+
+## Source Architecture
+
+```
+src/encode_connector/
+  server/main.py          # MCP server — 20 tools, ~1500 lines (entry point)
+  client/encode_client.py # Async ENCODE API client, ~585 lines, 1-hour TTL cache
+  client/downloader.py    # File download manager, ~305 lines, MD5 verification
+  client/auth.py          # OS keyring + Fernet credential storage, ~262 lines
+  client/models.py        # Pydantic models for API responses, ~332 lines
+  client/constants.py     # API URLs, filter values, ~348 lines
+  client/tracker.py       # SQLite experiment tracker, ~1129 lines
+  client/validation.py    # Input validation, ~188 lines
+skills/                   # 47 skills, each with SKILL.md + references/ + scripts/
+tests/                    # 506 tests (pytest-asyncio, asyncio_mode=auto), 98% coverage
+```
+
+## Package Identity
+
+- **PyPI / console command**: `encode-toolkit`
+- **npm**: `encode-toolkit` (thin wrapper → uvx encode-toolkit)
+- **Plugin marketplace**: `encode-toolkit`
+- **Python module**: `encode_connector`
+
+## Development Gotchas
+
+- Use `.venv/bin/python` on macOS (`python` may not exist)
+- `asyncio_mode = "auto"` in pytest — no need for `@pytest.mark.asyncio`
+- `main.py` is ~53KB — don't send full contents to subagents (causes timeouts)
+- MCP SDK: use `instructions=` parameter, not `description=`
+- Integration tests hit live ENCODE API — deselect with `-m "not integration"`
+- `server.json` is for MCP registry; `.claude-plugin/plugin.json` is for Claude marketplace — keep both in sync
+- `conftest.py` sets up shared fixtures (tmp_path, mock tracker) — read before adding tests
+- npm `package.json` + `index.js` are thin wrappers that call `uvx encode-toolkit` — no JS logic
+
+## What This Server Does
+
+Provides 20 tools to search, download, and track ENCODE data:
+- **Search**: Find experiments by assay, organ, biosample, target, organism
+- **Download**: Get BED, FASTQ, BAM, bigWig files with MD5 verification
+- **Track**: Local experiment tracking with publications, citations, provenance
+- **Cross-reference**: Link to PubMed, bioRxiv, ClinicalTrials, GEO
+
+## Key Concepts
+
+**Assay types**: Histone ChIP-seq, TF ChIP-seq, ATAC-seq, DNase-seq, RNA-seq, WGBS, Hi-C, scRNA-seq, scATAC-seq, CRISPR screen, STARR-seq, MPRA, eCLIP, CUT&RUN, CUT&Tag
+
+**Biosample hierarchy**: tissue > primary cell > cell line > in vitro differentiated > organoid
+
+**Tier 1 cell lines** (most data): K562, GM12878, H1-hESC
+
+**File selection priority**: preferred_default=True > IDR thresholded peaks > fold change over control
+
+**Assembly**: Use GRCh38 for human, mm10 for mouse. Never mix assemblies.
+
+## Tool Selection Guide
+
+| User wants to... | Use tool |
+|---|---|
+| Find experiments | `encode_search_experiments` |
+| Explore what data exists (live counts) | `encode_get_facets` |
+| Get valid filter strings (static list) | `encode_get_metadata` |
+| Get experiment details | `encode_get_experiment` |
+| Find specific file types | `encode_search_files` |
+| List files for experiment | `encode_list_files` |
+| Get file details | `encode_get_file_info` |
+| Download specific files by accession | `encode_download_files` |
+| Search + download in one step | `encode_batch_download` |
+| Track experiments locally | `encode_track_experiment` |
+| Compare experiments | `encode_compare_experiments` |
+| Get citations | `encode_get_citations` |
+| Log derived files | `encode_log_derived_file` |
+| Link to PubMed/GEO | `encode_link_reference` |
+| List tracked experiments | `encode_list_tracked` |
+| Export tracking data | `encode_export_data` |
+| View file provenance | `encode_get_provenance` |
+| View linked references | `encode_get_references` |
+| Get collection summary | `encode_summarize_collection` |
+| Manage API credentials | `encode_manage_credentials` |
+
+### Example Queries
+
+**Search**: `encode_search_experiments(assay_title="Histone ChIP-seq", organ="pancreas", target="H3K27ac")` → finds all H3K27ac ChIP-seq in pancreas tissue
+
+**Download**: `encode_download_files(file_accessions=["ENCFF123ABC"], download_dir="/data/encode")` → downloads with MD5 verification
+
+**Track**: `encode_track_experiment(accession="ENCSR000ABC", notes="Liver H3K4me3 for enhancer analysis")` → saves to local SQLite with publications
+
+**Explore**: `encode_get_facets(assay_title="Histone ChIP-seq", organ="pancreas")` → shows available targets, labs, biosample types
+
+**Batch download**: `encode_batch_download(assay_title="ATAC-seq", organ="liver", file_format="bed", output_type="IDR thresholded peaks", dry_run=True)` → previews matching files before download
+
+**Compare**: `encode_compare_experiments(accession1="ENCSR123ABC", accession2="ENCSR456DEF")` → checks compatibility for combined analysis
+
+## 47 Skills Available
+
+**Core**: setup, search-encode, download-encode, track-experiments, cross-reference
+
+**Analysis**: quality-assessment, integrative-analysis, regulatory-elements, epigenome-profiling, compare-biosamples, visualization-workflow, motif-analysis, peak-annotation, batch-analysis
+
+**Functional Genomics**: functional-screen-analysis
+
+**Data Aggregation**: histone-aggregation, accessibility-aggregation, hic-aggregation, methylation-aggregation
+
+**External Databases**: gtex-expression, clinvar-annotation, cellxgene-context, gwas-catalog, jaspar-motifs, ensembl-annotation, geo-connector, gnomad-variants, ucsc-browser
+
+**Workflows**: data-provenance, cite-encode, variant-annotation, pipeline-guide, single-cell-encode, disease-research, publication-trust, bioinformatics-installer, scientific-writing, liftover-coordinates
+
+**Pipeline Execution**: pipeline-chipseq, pipeline-atacseq, pipeline-rnaseq, pipeline-wgbs, pipeline-hic, pipeline-dnaseseq, pipeline-cutandrun
+
+**Meta-Analysis**: scrna-meta-analysis, multi-omics-integration
+
+## Reference Files
+
+- `skills/histone-aggregation/references/histone-marks-reference.md` — Comprehensive chromatin biology catalog (1,442 lines, 74 references, 12 sections: histone marks, ChromHMM states, functional categories, contradictions, TF combinations, chromatin remodeling, DNA methylation interplay, nucleosome dynamics, 3D genome organization, chromatin in disease)
+- `skills/*/references/literature.md` — 34 literature reference documents (33 per-skill + 1 chromatin biology catalog, ~320 papers with DOI, PMID, citation counts, key findings)
+
+## Quality Awareness
+
+- ENCODE audits: ERROR > NOT_COMPLIANT > WARNING > INTERNAL_ACTION
+- ChIP-seq metrics: FRiP ≥1%, NSC >1.05, RSC >0.8, NRF ≥0.8 (Landt et al. 2012)
+- ATAC-seq metrics: TSS enrichment ≥6, fragment size nucleosomal ladder (Buenrostro et al. 2013)
+- RNA-seq: Mapping rate >80%, rRNA <10%, replicate correlation ≥0.9 (Conesa et al. 2016)
+- WGBS: Bisulfite conversion >99%, CpG coverage ≥10× for DMRs (Foox et al. 2021)
+- Hi-C: Cis/trans ratio >60%, long-range cis >40% (Yardimci et al. 2019)
+- CUT&RUN/CUT&Tag: Different QC profiles from ChIP-seq; use suspect list (Nordin et al. 2023)
+- Always use 2+ biological replicates
+- Always apply ENCODE Blacklist v2 (Amemiya et al. 2019)
+- No single metric is sufficient — interpret collectively
+
+## Provenance Standard
+
+Every operation should log: tool name + version, exact command, input accessions + MD5, reference files + source + MD5, output descriptions + counts, and statistics. Scripts stored with sequential numbering. Enables auto-generation of publication-ready methods sections.
+
+## Cross-Database Integration
+
+This plugin works with MCP servers:
+- **PubMed** (search_articles) — Literature search and citation
+- **bioRxiv** (search_preprints) — Preprint discovery
+- **ClinicalTrials.gov** (search_trials) — Clinical trial cross-reference
+- **Open Targets** (query_open_targets_graphql) — Drug target identification
+- **Consensus** (search) — Academic paper search across 200M+ papers
+
+And via skills (REST API/CLI):
+- **UCSC Genome Browser** — cCRE tracks, TF binding, sequence retrieval via REST API
+- **NCBI GEO** — Complementary expression/epigenomic datasets via E-utilities
+- **gnomAD** — Population allele frequencies and gene constraint via GraphQL
+- **Ensembl** — VEP variant annotation, Regulatory Build, coordinate liftover via REST API
+- **NCBI SRA** — Raw sequencing reads linked from GEO (via E-utilities elink)
+- **GTEx** — Tissue-specific gene expression for ENCODE regulatory element interpretation via REST API
+- **ClinVar** — Clinical variant significance for ENCODE-identified regulatory variants via E-utilities
+- **CELLxGENE** — Single-cell expression context for ENCODE bulk data via REST API
+- **GWAS Catalog** — GWAS associations in ENCODE regulatory regions via REST API
+- **JASPAR** — Transcription factor binding motifs for ENCODE ChIP-seq peak analysis via REST API

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/batch-analysis/SKILL.md

@@ -1,12 +1,6 @@
 ---
 name: batch-analysis
-description: >-
-  Guide for multi-experiment batch operations: QC screening, batch download, comparison,
-  and report generation across many ENCODE experiments simultaneously. Use when users
-  need to process 5+ experiments together, create experiment comparison tables, perform
-  batch quality checks, or generate summary reports. Trigger on: batch analysis, multiple
-  experiments, bulk processing, experiment comparison, batch QC, multi-sample, batch
-  download, experiment table, summary report, collection analysis.
+description: "Guide for multi-experiment batch operations: QC screening, batch download, comparison, and report generation across many ENCODE experiments simultaneously. Use when users need to process 5+ experiments together, create experiment comparison tables, perform batch quality checks, or generate summary reports. Trigger on: batch analysis, multiple experiments, bulk processing, experiment comparison, batch QC, multi-sample, batch download, experiment table, summary report, collection analysis."
 ---
 
 # Batch Analysis of ENCODE Experiments

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/bioinformatics-installer/SKILL.md

@@ -1,15 +1,6 @@
 ---
 name: bioinformatics-installer
-description: >-
-  Install bioinformatics tools for ENCODE data analysis. Covers CLI tools
-  (BWA, STAR, samtools, MACS2), R/Bioconductor packages (DESeq2, Seurat,
-  ChIPseeker), Python packages (Scanpy, deeptools), and Nextflow pipeline
-  infrastructure. Generates conda environments, R install scripts, and Python
-  requirements. Use when the user needs to set up a bioinformatics workstation,
-  install tools for a specific assay, create reproducible environments, or
-  troubleshoot dependency issues. Trigger on: install tools, set up environment,
-  conda create, bioinformatics setup, install R packages, install Bioconductor,
-  install pipeline tools.
+description: "Install bioinformatics tools for ENCODE data analysis. Covers CLI tools (BWA, STAR, samtools, MACS2), R/Bioconductor packages (DESeq2, Seurat, ChIPseeker), Python packages (Scanpy, deeptools), and Nextflow pipeline infrastructure. Generates conda environments, R install scripts, and Python requirements. Use when the user needs to set up a bioinformatics workstation, install tools for a specific assay, create reproducible environments, or troubleshoot dependency issues. Trigger on: install tools, set up environment, conda create, bioinformatics setup, install R packages, install Bioconductor, install pipeline tools."
 ---
 
 # Bioinformatics Installer for ENCODE Data Analysis

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/cellxgene-context/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: cellxgene-context
-description: >-
-  Guide for integrating CellxGene Census single-cell data with ENCODE bulk experiments.
-  Use when users need cell-type-specific expression context for ENCODE regulatory data,
-  want to deconvolve bulk ENCODE signals, or validate regulatory elements at single-cell
-  resolution. Trigger on: CellxGene, single-cell atlas, cell type expression, Census,
-  cell type specificity, single-cell context, scRNA-seq atlas.
+description: "Guide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when users need cell-type-specific expression context for ENCODE regulatory data, want to deconvolve bulk ENCODE signals, or validate regulatory elements at single-cell resolution. Trigger on: CellxGene, single-cell atlas, cell type expression, Census, cell type specificity, single-cell context, scRNA-seq atlas."
 ---
 
 # Integrating CellxGene Census Single-Cell Data with ENCODE Bulk Experiments

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/clinvar-annotation/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: clinvar-annotation
-description: >-
-  Guide for annotating ENCODE regulatory variants with ClinVar clinical significance.
-  Use when users need to check if variants in ENCODE peaks have clinical associations,
-  find pathogenic variants in regulatory regions, or assess variant clinical impact.
-  Trigger on: ClinVar, clinical significance, pathogenic variant, variant classification,
-  clinical variant, disease variant, VUS, benign, likely pathogenic.
+description: "Guide for annotating ENCODE regulatory variants with ClinVar clinical significance. Use when users need to check if variants in ENCODE peaks have clinical associations, find pathogenic variants in regulatory regions, or assess variant clinical impact. Trigger on: ClinVar, clinical significance, pathogenic variant, variant classification, clinical variant, disease variant, VUS, benign, likely pathogenic."
 ---
 
 ## When to Use

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/gtex-expression/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: gtex-expression
-description: >-
-  Guide for integrating GTEx tissue expression data with ENCODE regulatory elements.
-  Use when users need to check if a gene is expressed in a tissue, correlate
-  regulatory elements with expression, or validate ENCODE findings against GTEx.
-  Trigger on: GTEx, tissue expression, gene expression levels, expression atlas,
-  eQTL, tissue-specific expression, TPM values.
+description: "Guide for integrating GTEx tissue expression data with ENCODE regulatory elements. Use when users need to check if a gene is expressed in a tissue, correlate regulatory elements with expression, or validate ENCODE findings against GTEx. Trigger on: GTEx, tissue expression, gene expression levels, expression atlas, eQTL, tissue-specific expression, TPM values."
 ---
 
 # Integrating GTEx Tissue Expression with ENCODE Regulatory Data

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/gwas-catalog/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: gwas-catalog
-description: >-
-  Guide for integrating NHGRI-EBI GWAS Catalog associations with ENCODE regulatory data.
-  Use when users need to find GWAS variants in ENCODE peaks, connect regulatory elements
-  to disease associations, or prioritize functional variants using ENCODE annotations.
-  Trigger on: GWAS, genome-wide association, SNP association, trait association,
-  GWAS Catalog, disease association, risk variant, lead SNP, LD proxy.
+description: "Guide for integrating NHGRI-EBI GWAS Catalog associations with ENCODE regulatory data. Use when users need to find GWAS variants in ENCODE peaks, connect regulatory elements to disease associations, or prioritize functional variants using ENCODE annotations. Trigger on: GWAS, genome-wide association, SNP association, trait association, GWAS Catalog, disease association, risk variant, lead SNP, LD proxy."
 ---
 
 # Integrating NHGRI-EBI GWAS Catalog with ENCODE Regulatory Data

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/jaspar-motifs/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: jaspar-motifs
-description: >-
-  Guide for using JASPAR transcription factor binding profiles with ENCODE ChIP-seq data.
-  Use when users need to find TF binding motifs in ENCODE peaks, validate ChIP-seq
-  targets with known motifs, or scan regulatory regions for TF binding potential.
-  Trigger on: JASPAR, motif database, binding profile, PWM, position weight matrix,
-  TF motif, motif enrichment, motif scanning, binding site prediction.
+description: "Guide for using JASPAR transcription factor binding profiles with ENCODE ChIP-seq data. Use when users need to find TF binding motifs in ENCODE peaks, validate ChIP-seq targets with known motifs, or scan regulatory regions for TF binding potential. Trigger on: JASPAR, motif database, binding profile, PWM, position weight matrix, TF motif, motif enrichment, motif scanning, binding site prediction."
 ---
 
 # Using JASPAR Transcription Factor Binding Profiles with ENCODE ChIP-seq Data

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/motif-analysis/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: motif-analysis
-description: >-
-  Guide for de novo and known motif enrichment analysis of ENCODE ChIP-seq and ATAC-seq
-  peaks using HOMER and MEME Suite. Use when users need to discover TF binding motifs
-  in peaks, validate ChIP-seq targets, or find co-binding partners. Trigger on: motif
-  analysis, HOMER, MEME, de novo motif, motif enrichment, findMotifsGenome, AME,
-  MEME-ChIP, known motif, TF binding motif, co-factor, motif discovery.
+description: "Guide for de novo and known motif enrichment analysis of ENCODE ChIP-seq and ATAC-seq peaks using HOMER and MEME Suite. Use when users need to discover TF binding motifs in peaks, validate ChIP-seq targets, or find co-binding partners. Trigger on: motif analysis, HOMER, MEME, de novo motif, motif enrichment, findMotifsGenome, AME, MEME-ChIP, known motif, TF binding motif, co-factor, motif discovery."
 ---
 
 # Motif Analysis of ENCODE Peak Data

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/peak-annotation/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: peak-annotation
-description: >-
-  Guide for annotating ENCODE peaks with genomic features using ChIPseeker and GREAT.
-  Use when users need to assign peaks to genes, determine genomic feature distribution
-  (promoter, intron, intergenic), or perform gene ontology enrichment of peak-associated
-  genes. Trigger on: peak annotation, ChIPseeker, GREAT, peak to gene, genomic feature,
-  promoter enrichment, gene ontology, peak distribution, TSS distance, nearest gene.
+description: "Guide for annotating ENCODE peaks with genomic features using ChIPseeker and GREAT. Use when users need to assign peaks to genes, determine genomic feature distribution (promoter, intron, intergenic), or perform gene ontology enrichment of peak-associated genes. Trigger on: peak annotation, ChIPseeker, GREAT, peak to gene, genomic feature, promoter enrichment, gene ontology, peak distribution, TSS distance, nearest gene."
 ---
 
 # Peak Annotation of ENCODE Data

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/pipeline-atacseq/SKILL.md

@@ -1,13 +1,6 @@
 ---
 name: pipeline-atacseq
-description: >-
-  Execute ENCODE ATAC-seq processing pipeline from FASTQ to peaks and signal tracks.
-  Child of pipeline-guide. Provides stage-by-stage Nextflow execution with Docker
-  containers and cloud deployment. Handles Tn5 transposase offset correction,
-  mitochondrial read removal, nucleosome-free fragment selection, and TSS enrichment
-  scoring. Use when users need to process ATAC-seq data following ENCODE standards.
-  Trigger on: ATAC-seq pipeline, run ATAC-seq, process ATAC-seq, chromatin
-  accessibility, open chromatin, Tn5 shift, TSS enrichment.
+description: "Execute ENCODE ATAC-seq processing pipeline from FASTQ to peaks and signal tracks. Child of pipeline-guide. Provides stage-by-stage Nextflow execution with Docker containers and cloud deployment. Handles Tn5 transposase offset correction, mitochondrial read removal, nucleosome-free fragment selection, and TSS enrichment scoring. Use when users need to process ATAC-seq data following ENCODE standards. Trigger on: ATAC-seq pipeline, run ATAC-seq, process ATAC-seq, chromatin accessibility, open chromatin, Tn5 shift, TSS enrichment."
 ---
 
 # ENCODE ATAC-seq Pipeline

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/pipeline-chipseq/SKILL.md

@@ -1,12 +1,6 @@
 ---
 name: pipeline-chipseq
-description: >-
-  Execute ENCODE ChIP-seq processing pipeline from FASTQ to peaks and signal tracks.
-  Child of pipeline-guide. Provides stage-by-stage Nextflow execution with Docker
-  containers and cloud deployment. Use when users need to process ChIP-seq data
-  following ENCODE standards, run peak calling with MACS2, perform IDR analysis,
-  or generate signal tracks. Trigger on: ChIP-seq pipeline, run ChIP-seq, process
-  ChIP-seq, MACS2 peak calling, IDR analysis, ChIP-seq FASTQ processing.
+description: "Execute ENCODE ChIP-seq processing pipeline from FASTQ to peaks and signal tracks. Child of pipeline-guide. Provides stage-by-stage Nextflow execution with Docker containers and cloud deployment. Use when users need to process ChIP-seq data following ENCODE standards, run peak calling with MACS2, perform IDR analysis, or generate signal tracks. Trigger on: ChIP-seq pipeline, run ChIP-seq, process ChIP-seq, MACS2 peak calling, IDR analysis, ChIP-seq FASTQ processing."
 ---
 
 # ENCODE ChIP-seq Pipeline

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/pipeline-cutandrun/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: pipeline-cutandrun
-description: >-
-  Execute CUT&RUN processing pipeline from FASTQ to peaks and signal tracks.
-  Child of pipeline-guide. Provides Nextflow execution with Docker and cloud
-  deployment. Use when processing CUT&RUN or CUT&Tag data, an alternative to
-  ChIP-seq with lower background. Trigger on: CUT&RUN pipeline, CUT&Tag,
-  SEACR, Henikoff, targeted chromatin, pA-MNase, process CUT&RUN.
+description: "Execute CUT&RUN processing pipeline from FASTQ to peaks and signal tracks. Child of pipeline-guide. Provides Nextflow execution with Docker and cloud deployment. Use when processing CUT&RUN or CUT&Tag data, an alternative to ChIP-seq with lower background. Trigger on: CUT&RUN pipeline, CUT&Tag, SEACR, Henikoff, targeted chromatin, pA-MNase, process CUT&RUN."
 ---
 
 # ENCODE CUT&RUN Pipeline: FASTQ to Peaks and Signal Tracks

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/pipeline-dnaseseq/SKILL.md

@@ -1,12 +1,6 @@
 ---
 name: pipeline-dnaseseq
-description: >-
-  Execute ENCODE DNase-seq pipeline from FASTQ to hotspots and footprints.
-  Child of pipeline-guide. Provides Nextflow execution with Docker and cloud
-  deployment. Use when processing DNase-seq data, calling DNase hypersensitive
-  sites, performing footprinting analysis. Trigger on: DNase-seq pipeline,
-  DNase hypersensitive, DHS, Hotspot2, footprinting, DNase I, chromatin
-  accessibility DNase.
+description: "Execute ENCODE DNase-seq pipeline from FASTQ to hotspots and footprints. Child of pipeline-guide. Provides Nextflow execution with Docker and cloud deployment. Use when processing DNase-seq data, calling DNase hypersensitive sites, performing footprinting analysis. Trigger on: DNase-seq pipeline, DNase hypersensitive, DHS, Hotspot2, footprinting, DNase I, chromatin accessibility DNase."
 ---
 
 # ENCODE DNase-seq Pipeline: FASTQ to Hotspots and Footprints

{encode_toolkit-0.3.0b5 → encode_toolkit-0.3.0b8/plugin}/skills/pipeline-hic/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: pipeline-hic
-description: >-
-  Execute ENCODE Hi-C pipeline from FASTQ to contact matrices and loop calls.
-  Child of pipeline-guide. Provides Nextflow execution with Docker and cloud
-  deployment. Use when processing Hi-C data, generating contact matrices,
-  calling loops or TADs. Trigger on: Hi-C pipeline, chromatin conformation,
-  contact matrix, loop calling, TAD detection, Juicer, HiCCUPS, 3D genome.
+description: "Execute ENCODE Hi-C pipeline from FASTQ to contact matrices and loop calls. Child of pipeline-guide. Provides Nextflow execution with Docker and cloud deployment. Use when processing Hi-C data, generating contact matrices, calling loops or TADs. Trigger on: Hi-C pipeline, chromatin conformation, contact matrix, loop calling, TAD detection, Juicer, HiCCUPS, 3D genome."
 ---
 
 # ENCODE Hi-C Pipeline: FASTQ to Contact Matrices and Loops