Search Skills

Structured technique to refine rough ideas into validated design solutions using Socratic questioning and incremental validation before implementation.

Python toolkit for molecular biology data processing, handling sequence manipulation, file parsing (FASTA, GenBank), and BLAST workflows.

Computational materials science toolkit for crystal structure analysis, phase diagrams, band structure, and Materials Project integration.

Provides access to NCBI GEO database for searching, downloading, and retrieving gene expression and genomics datasets including microarray and RNA-seq data.

Automates AGENTS.md configuration to instruct agents to search for existing skills before scientific tasks, optimizing workflow efficiency.

Generates professional PDF documents including invoices, reports, and certificates through automated document creation.

AI-powered toolkit for analyzing whole-slide images and multiparametric pathology data using ML models, supporting 160+ slide formats and pathology workflows.

Efficient storage and parallel I/O for large N-D arrays in cloud storage (S3/GCS), compatible with NumPy, Dask, and Xarray for scientific computing pipelines.

Syncs local skills repository with upstream changes from obra/superpowers-skills repository.

Automates laboratory workflows through control of liquid handling robots, plate readers, and other lab equipment.

scvi-tools for single-cell omics data analysis: probabilistic modeling, batch correction, and multimodal integration for scRNA-seq, scATAC-seq, and spatial transcriptomics.

Comprehensive toolkit for protein language models (ESM3, ESM C) enabling sequence, structure, and function prediction, design, and engineering via local or cloud inference.

Processes mass spectrometry data (mzML/MGF/MSP) for metabolomics, enabling spectral similarity calculations and compound identification.

Provides modern JavaScript patterns (ES6+) for refactoring, optimizing, and writing clean code with features like async/await, destructuring, and functional programming.

Provides programmatic access to Data Commons for querying global statistical data including demographics, economics, health, and environmental metrics.

PyTorch-based toolkit for graph neural networks in drug discovery, enabling molecular property prediction, protein modeling, and molecular generation.

Phylogenetic tree toolkit for manipulating trees (Newick/NHX), detecting evolutionary events, and visualizing phylogenomic data.

Provides Python-based tools for reading, writing, and analyzing genomic data formats including SAM/BAM, VCF, and FASTQ in next-generation sequencing workflows.

Provides architectural guidance for designing microservices-based systems, including service decomposition, event-driven communication, and resilience strategies.

Provides tools for building and training Graph Neural Networks (GNNs) for node classification, link prediction, and molecular property prediction using PyTorch Geometric.

Provides access to 600+ scientific tools, datasets, and APIs for research in bioinformatics, genomics, and drug discovery workflows.

Applies medicinal chemistry rules including Lipinski, Veber, and PAINS filters to prioritize compounds and filter chemical libraries.

Applies TDD to documentation, testing with subagents before writing to ensure bulletproof, rationalization-resistant technical documentation.

Comprehensive toolkit for astronomical data analysis, including FITS I/O, coordinate transformations, cosmology calculations, and WCS support.