Explains machine learning predictions on omics data using SHAP values and LIME for feature attribution. Identifies which genes or features drive classifier decisions.
AI-powered molecular glue discovery for targeted protein degradation, enabling neo-substrate recruitment and undruggable target degradation through E3 ligase interface modulation.
Maps query single-cell data to reference atlases using scArches transfer learning with scVI and scANVI models.
End-to-end RNA-seq workflow from FASTQ files to differential expression results. Covers QC, quantification (Salmon or STAR+featureCounts), and DESeq2 analysis with visual — from…
Validate, gap-fill, and curate genome-scale metabolic models using memote for quality scores and COBRApy for manual curation.
Automates the drafting of regulatory documents (e.g., FDA CTD sections) with citation management and audit trails.
End-to-end CLIP-seq analysis from FASTQ to binding sites and motif enrichment. Use when analyzing protein-RNA interactions from CLIP-based methods. — from bg-szy/TOP-SKILLS
Preprocess CLIP-seq data including adapter trimming, UMI extraction, and PCR duplicate removal. Use when preparing raw CLIP, iCLIP, or eCLIP reads for peak calling.
Reusable plotting functions for common omics visualizations. Custom ggplot2/matplotlib implementations of volcano, MA, PCA, enrichment dotplots, boxplots, and survival cu — from…
Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful image and video generation.
Generate images/videos via Higgsfield AI. Default: GPT Image 2 for images/design/text, Seedance 2.0 for video, Nano Banana 2/Pro for character/reference image work, Marketing…
Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component — from…
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs — from…
Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups) — from…
Generate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on GPT Image 2 / gpt_image_2. Entry point for professional brand/product visuals.
Write cold emails that get replies using proven frameworks (AIDA, PAS, BAB). Enforces best practices like 50-125 word limit and personalized openers.
Review code for Playwright Guidelines compliance. Use when asked to "review my playwright tests", "check accessibility", or "check my tests against best practices".
Lab Results agent for healthcare workflows.
Generate marketplace product image cards through Higgsfield: compliant main image, secondary product images, and A+ style content modules.
Regulatory Drafting agent for healthcare workflows.
Research Literature agent for healthcare workflows.
Claims Appeals agent for healthcare workflows.
FHIR Development agent for healthcare workflows.
Generate insightful, publication-quality visualizations from complex datasets.
Care Coordination agent for healthcare workflows.
Predicts ADMET properties using ADMETlab 3.0 (119 endpoints with uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles,…
PC and console game development principles. Engine selection, platform features, optimization strategies. — from bg-szy/TOP-SKILLS
End-to-end multiome workflow for joint scRNA-seq + scATAC-seq analysis. Covers data loading, separate modality processing, and WNN integration with Seurat/Signac.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Filter and prioritize variants by pathogenicity, population frequency, and clinical evidence for rare disease analysis.
Analyze single-cell TCR and BCR data integrated with gene expression using scirpy. Use when working with 10x Genomics VDJ data alongside scRNA-seq or when integrating imm — from…
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows — from bg-szy/TOP-SKILLS
When the user wants to create, optimize, or audit a download page for desktop or mobile app. Also use when the user mentions "download page," "app download," "desktop download,"…
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers.
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks — from…
When the user wants to create, optimize, or audit media kit or press page. Also use when the user mentions "media kit," "press kit," "press page," "press resources," "brand…
Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or — from…
Creates DE-specific diagnostic and result visualizations using DESeq2/edgeR built-in functions and lightweight ggplot2 wrappers.
Build maximum likelihood phylogenetic trees using IQ-TREE2 and RAxML-NG with expert model selection, branch support assessment, and topology testing.
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management.
Generate reverse complements and complements of DNA/RNA sequences using Biopython. Use when working with opposite strands, primer design, or converting between template a — from…
When the user wants to create, optimize, or structure legal pages (Privacy, Terms, etc.). Also use when the user mentions "privacy policy," "terms of service," "legal pages,"…
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez).
Comprehensive frontend development skill for building modern, performant web applications using ReactJS, NextJS, TypeScript, Tailwind CSS.
Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolat — from…
Differential abundance testing for microbiome data using compositionally-aware methods like ALDEx2, ANCOM-BC2, and MaAsLin2.
Use when facing 3+ independent failures that can be investigated without shared state or dependencies.
Python SDK for inference.sh - run AI apps, build agents, and integrate with 150+ models. Package: inferencesh (pip install inferencesh).
View, query, and understand VCF/BCF variant files using bcftools and cyvcf2. Use when inspecting variants, extracting specific fields, or understanding VCF format structu — from…
Query PharmGKB and CPIC for drug-gene interactions, pharmacogenomic annotations, and dosing guidelines.
End-to-end single-cell RNA-seq workflow from 10X Genomics data to annotated cell types. Covers QC, normalization, clustering, marker detection, and cell type annotation — from…
Navigate protein structure hierarchy using Biopython Bio.PDB SMCRA model. Use when accessing models, chains, residues, and atoms, iterating over structure levels, or extr — from…
Orchestrate iOS/macOS app scaffolding and optional skill adoption for existing projects. Use when users want a guided wizard that can scaffold with XcodeGen and optionally install…
Generate AI videos with Google Veo, Seedance, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine Video, OmniHu — from…
Comprehensive security auditing workflow covering web application testing, API security, penetration testing, vulnerability scanning, and security hardening.
Perform V(D)J alignment and clonotype assembly from TCR-seq or BCR-seq data using MiXCR. Use when processing raw immune repertoire sequencing data to identify clonotypes — from…
Gene Ontology over-representation analysis using clusterProfiler enrichGO. Use when identifying biological functions enriched in a gene list from differential expression — from…
When the user wants to write, generate, or create article body content—blog post body, long-form content, how-to guide, listicle.
Detect and correct for horizontal pleiotropy in Mendelian randomization analyses using MR-PRESSO for outlier removal, MR-Egger regression for directional pleiotropy, and Steiger…
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design.