数据处理
数据转换、清洗与 ETL
clinpgx-database
jaechang-hits
"Query PharmGKB (Clinical Pharmacogenomics) database via REST API for drug-gene interactions, clinical annotations, dosing guidelines (CPIC, DPWG), variant-drug associations, and pharmacogenomic pathways. Search by gene, drug, rsID, or pathway. No authentication required. For somatic cancer pharmacogenomics use cosmic-database or opentargets-database; for drug structures use chembl-database-bioactivity."
napari-image-viewer
jaechang-hits
"Interactive multi-dimensional image viewer for scientific microscopy data. Napari displays 2D/3D/4D arrays as Image, Labels, Points, Shapes, and Tracks layers; supports real-time annotation, plugin-based analysis, and headless screenshot export. Core visualization tool for bioimage analysis workflows. Use ImageJ/FIJI for macro-based processing; use napari for Python-native interactive visualization and plugin-based deep learning segmentation review."
cnvkit-copy-number
jaechang-hits
"Detect somatic copy number variants (CNVs) from WES, WGS, or targeted sequencing BAM files with CNVkit v0.9.x. Pipeline: calculate bin-level coverage in target/antitarget regions, normalize against a reference, segment copy ratios with CBS or HMM, call amplifications and deletions, generate scatter/diagram plots, estimate tumor purity and ploidy, and export to VCF/SEG. Both CLI and Python API (cnvlib) shown. Use GATK CNV instead for deep WGS with population-scale controls; use CNVkit for targeted or exome sequencing where antitarget bins are critical."
biopython-sequence-analysis
jaechang-hits
"Biopython toolkit for sequence analysis workflows: parse FASTA/FASTQ/GenBank/GFF with SeqIO, query NCBI databases via Entrez (esearch/efetch/elink), run remote and local BLAST with result parsing, perform pairwise and multiple sequence alignment (PairwiseAligner, MUSCLE/ClustalW), and build/visualize phylogenetic trees (Phylo module). Use for gene family studies, phylogenomics, comparative genomics, and programmatic NCBI pipelines. For PCR design, restriction digestion, and cloning workflows use biopython-molecular-biology; for SAM/BAM alignments use pysam."
templ-http
Xe
Integrate templ components with Go HTTP server using net/http. Use when connecting templ to web server, creating HTTP handlers, mentions 'templ server', 'HTTP routes', or 'serve templ components'.
opendataloader-pdf
chujianyun
PDF 数据提取工具。当用户提到"PDF 提取"、"PDF 转 Markdown"、"PDF 解析"、"提取 PDF 内容"、"PDF 转 JSON"、"RAG PDF"时使用。OpenDataLoader PDF 是目前基准测试第一的 PDF 解析器，支持本地模式（快速、确定）和混合 AI 模式（复杂表格、扫描件、公式），输出 Markdown、JSON（带边界框）、HTML。适用于需要从 PDF 提取结构化数据用于 RAG/LLM pipeline，或需要批量处理 PDF 文档的场景。
ai-prompt-engineering-safety-review
LeoYeAI
'Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations with extensive frameworks, testing methodologies, and educational content.'
agentic-eval
LeoYeAI
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
agent-browser
LeoYeAI
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
ai-model-router
LeoYeAI
Intelligent AI model router that automatically switches between two configured models (local for simple tasks, cloud for complex ones). Detects local models (Ollama, LM Studio) automatically, routes based on task complexity and privacy. Use when users ask to "switch model", "use local/cloud model", or mention API keys/passwords (triggers privacy mode). Trigger on: sensitive data detection (forces local), complex tasks like "design architecture" (uses cloud), or configuration requests.
agent-governance
LeoYeAI
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)
ai-model-router
LeoYeAI
Intelligent AI model router that automatically switches between two configured models (local for simple tasks, cloud for complex ones). Detects local models (Ollama, LM Studio) automatically, routes based on task complexity and privacy. Use when users ask to "switch model", "use local/cloud model", or mention API keys/passwords (triggers privacy mode). Trigger on: sensitive data detection (forces local), complex tasks like "design architecture" (uses cloud), or configuration requests.
imaging-data-commons
jaechang-hits
"Query NCI Imaging Data Commons (IDC) for cancer radiology and pathology imaging datasets hosted on Google Cloud. Search DICOM collections by modality, anatomical site, cancer type, or collection name. Download images via Google Cloud Storage or IDAT tool. 50TB+ of publicly accessible DICOM images. Requires Google Cloud account for large downloads; small queries work without billing. For local DICOM processing use pydicom-medical-imaging; for whole-slide pathology use histolab."
gwas-database
jaechang-hits
"NHGRI-EBI GWAS Catalog REST API for SNP-trait associations from published genome-wide association studies. Query studies, associations, variants, traits, genes, and summary statistics. Build polygenic risk score candidates, analyze variant pleiotropy, download summary statistics for Manhattan plots. No authentication required."
cbioportal-database
jaechang-hits
"Access TCGA and other cancer genomics datasets via cBioPortal REST API. Retrieve somatic mutations, copy number alterations, gene expression profiles, and clinical data (survival, stage, treatment) for thousands of cancer studies. Use for tumor mutation burden analysis, oncoprint queries, and survival analysis. For population variant frequencies use gnomad-database; for drug-gene interactions use dgidb-database."
prompt-architect
ckelsoe
Analyzes and transforms prompts using 7 research-backed frameworks (CO-STAR, RISEN, RISE-IE, RISE-IX, TIDD-EC, RTF, Chain of Thought, Chain of Density). Provides framework recommendations, asks targeted questions, and structures prompts for maximum effectiveness. Use when users need expert prompt engineering guidance.
Response Format Skill
wasintoh
Version 2.0.0 - Consolidated from response-format and response-excellence skills
gene-database
jaechang-hits
"Query NCBI Gene via E-utilities for curated gene records across 1M+ taxa. Retrieve official gene symbols, aliases, RefSeq accessions, summary descriptions, genomic coordinates, GO annotations, and interaction data. Use for gene ID resolution, cross-species queries, and gene function summaries. For sequence retrieval use Ensembl; for expression data use geo-database."
omero-integration
jaechang-hits
"OMERO is an open-source platform for biological image data management. Use the omero-py Python client to connect to an OMERO server, search and retrieve images as numpy arrays, annotate images with tags and key-value pairs, manage ROIs, and integrate OMERO image data into downstream analysis pipelines — all programmatically without the OMERO desktop GUI."
pymc-bayesian-modeling
jaechang-hits
"Bayesian modeling with PyMC 5. 8-step workflow: define model, set priors, define likelihood, sample (NUTS/ADVI), diagnose (R-hat, ESS, divergences), interpret posteriors, compare models (LOO/WAIC), predict. Hierarchical, logistic, GP model variants. Prior/posterior predictive checks."
encode-database
jaechang-hits
"Query the ENCODE Portal REST API for regulatory genomics data: TF ChIP-seq experiments, ATAC-seq/DNase-seq accessibility peaks, histone mark tracks, and RNA-seq datasets across 1000+ cell types and tissues. Search experiments by assay, biosample, or target protein; download BED/bigWig files; retrieve candidate cis-regulatory elements (cCREs) from ENCODE SCREEN by genomic region or gene. Use for finding regulatory tracks to annotate variants, identifying open chromatin in a cell type of interest, and downloading peak files for ChIP-seq or ATAC-seq analysis. For regulatory variant scoring use regulomedb-database; for GWAS associations use gwas-database."
cosmic-database
jaechang-hits
"Query COSMIC (Catalogue Of Somatic Mutations In Cancer) for cancer somatic mutations, gene census data, mutational signatures, drug resistance variants, and cancer gene annotations. REST API v3.1 supports gene/sample/variant queries. Free registration required. For germline clinical variants use clinvar-database; for drug-target data use opentargets-database or chembl-database-bioactivity."
pyhealth
jaechang-hits
"PyHealth is a Python library for healthcare machine learning. Build clinical prediction models from EHR (Electronic Health Record) data: process MIMIC-III/IV, eICU, and OMOP-CDM datasets, encode medical codes (ICD, ATC, NDC), construct patient-level datasets, and train models (Transformer, RETAIN, GRASP, MedBERT) for tasks including mortality prediction, drug recommendation, readmission, and diagnosis prediction. Alternatives: FIDDLE (EHR preprocessing only), clinical-longformer (NLP on clinical notes only), ehr-ml (EHR embedding only)."
fixing-metadata
agentset-ai
Ship correct, complete metadata.