Agent Skills Hub

perf-analyzer

Synthesize performance profiling data into actionable recommendations and evidence-backed technical decisions.

ml-pipeline-workflow

Build and orchestrate end-to-end MLOps pipelines covering data preparation, training, validation, and automated deployment.

pymc

Bayesian modeling and probabilistic programming with PyMC. Build hierarchical models, perform MCMC sampling (NUTS), variational inference, and conduct rigorous model comparison using LOO and WAIC.

networkx

Comprehensive toolkit for graph creation, network analysis, and visualization in Python. Ideal for analyzing relationships, centrality, community detection, and synthetic network generation across diverse research domains.

training-data-curation

Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.

rag-engineer

Architect and optimize production-grade RAG systems. Master embedding models, vector databases, chunking strategies, and retrieval pipelines for high-accuracy LLM applications.

marketing-psychology

Apply behavioral science, mental models, and psychological principles to marketing strategy, copywriting, and decision-making.

literature-review

Conduct systematic literature reviews across PubMed, arXiv, and Semantic Scholar with AI-driven synthesis, verified citations, and mandatory schematic visualization.

polars

High-performance in-memory DataFrame library for Python and Rust. Features lazy evaluation, parallel execution, and an Apache Arrow backend for efficient ETL, data processing, and faster pandas alternatives.

manufacturing-failure-reason-codebook-normalization

Normalizes testing defect logs by correcting typos, abbreviations, and ambiguous descriptions based on product-specific codebooks and station validation.

meteorology-driver-classification

Classify and group meteorological and environmental variables into specific driver categories for consistent attribution analysis and environmental modeling.

single-cell-rna-qc

Automated single-cell RNA-seq quality control pipeline following scverse best practices. Performs MAD-based outlier detection, cell filtering, and diagnostic visualization for .h5ad and .h5 datasets.