Python

Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.

A comprehensive PDF manipulation toolkit that enables extracting text and tables, creating new PDFs, merging and splitting documents, and filling out forms. It includes Python scripts for both fillable PDF forms and non-fillable PDFs requiring visual annotation placement.

This skill provides a complete guide for building MCP (Model Context Protocol) servers that enable LLMs to interact with external services. It includes implementation patterns for Python (FastMCP) and TypeScript (MCP SDK), best practices for tool design, and an evaluation harness to test MCP server quality using Claude.

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

A comprehensive guide for building robust backtesting frameworks for trading strategies. Covers common biases (look-ahead, survivorship, overfitting), implementation patterns including event-driven and vectorized backtesters, walk-forward optimization, Monte Carlo analysis, and performance metrics calculation.

A comprehensive testing guide for Temporal Python workflows. Covers unit testing with time-skipping, integration testing with mocked activities, replay testing for determinism validation, and local development setup with Docker Compose and pytest configuration.

This skill provides comprehensive guidance for creating distributable Python packages. It covers project structure patterns, pyproject.toml configuration, CLI tool creation with Click or argparse, building wheels and source distributions, and publishing to PyPI with proper versioning and CI/CD automation.

A comprehensive guide to error handling patterns across Python, TypeScript, Rust, and Go. Covers exception hierarchies, Result types, circuit breakers, retry logic, and graceful degradation strategies for building resilient applications.

A comprehensive reference guide for calculating portfolio risk metrics. Provides Python code patterns for Value at Risk (VaR), Conditional VaR, Sharpe ratio, Sortino ratio, maximum drawdown, and other risk measurements used in portfolio management and risk monitoring systems.

A comprehensive guide to profiling and optimizing Python code. Covers CPU and memory profiling tools (cProfile, memory_profiler, py-spy), optimization patterns like list comprehensions, caching with lru_cache, NumPy vectorization, and parallel processing with multiprocessing and asyncio.

This skill provides comprehensive Python testing patterns using pytest. It covers unit testing, fixtures for setup/teardown, mocking external dependencies, parameterized tests, async testing, property-based testing with Hypothesis, database testing, and CI/CD integration. The guide includes best practices for test organization, naming, and coverage reporting.

This skill provides comprehensive guidance for building sophisticated LLM applications using LangChain 1.x and LangGraph. It covers agent orchestration with StateGraph, RAG implementations, multi-agent systems, memory management patterns, and production deployment best practices including LangSmith observability integration.

A comprehensive reference guide for Python asynchronous programming. Covers asyncio fundamentals, coroutines, tasks, async context managers, producer-consumer patterns, rate limiting with semaphores, and real-world examples including web scraping with aiohttp, async database operations, and WebSocket servers.

A comprehensive reference guide for the uv package manager, an extremely fast Python package installer written in Rust. Covers project setup, dependency management, virtual environments, Python version management, CI/CD integration, Docker workflows, and migration from pip/poetry/pip-tools.

This skill provides production-ready FastAPI project templates with comprehensive patterns for async database operations, CRUD repositories, service layers, JWT authentication, and testing. It guides developers in setting up well-structured Python API projects using modern async patterns and best practices.

This skill collection provides expert assistance for modern Python development. It includes specialized agents for Django, FastAPI, and general Python development, along with comprehensive documentation for async programming patterns, Python packaging with pyproject.toml, performance profiling and optimization, pytest testing strategies, and the fast uv package manager.

A comprehensive quantitative finance skill for building robust backtesting systems for trading strategies. It covers event-driven and vectorized backtesters, walk-forward optimization, Monte Carlo analysis, and risk metrics including VaR, CVaR, Sharpe ratio, and drawdown analysis.

A comprehensive FastAPI project template skill that provides production-ready project structures, async patterns, dependency injection examples, and best practices for building high-performance Python APIs. Includes guidance for Django, GraphQL, and general backend architecture.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

This skill provides comprehensive documentation for accessing the National Cancer Institute's Imaging Data Commons (IDC), a public repository of cancer imaging data. It teaches users how to query, download, and visualize radiology and pathology images (CT, MR, PET, slide microscopy) using the idc-index Python package, with guides for BigQuery advanced queries and DICOMweb integration.

This skill provides comprehensive documentation and Python templates for programming Opentrons lab automation robots (OT-2 and Flex). It covers liquid handling operations, hardware module control (thermocycler, heater-shaker, magnetic modules), and common protocol patterns like serial dilutions and PCR setup.

This skill guides users through statistical hypothesis testing (t-tests, ANOVA, chi-square, regression) with proper assumption checking, effect size calculation, and APA-formatted reporting. It includes Python utilities for diagnostic visualizations and comprehensive reference documentation covering Bayesian methods, power analysis, and test selection.

This skill provides comprehensive documentation and guidance for using datamol, a Python library that simplifies molecular cheminformatics tasks. It covers SMILES parsing, molecular descriptors, fingerprints, clustering, 3D conformer generation, visualization, and chemical reactions with sensible defaults built on top of RDKit.

This skill enables querying the KEGG (Kyoto Encyclopedia of Genes and Genomes) bioinformatics database through REST API calls. It supports pathway analysis, gene-pathway mapping, metabolic pathway exploration, drug interaction checking, and ID conversion between KEGG and external databases like UniProt and PubChem.

This skill enables querying the ChEMBL database, a manually curated collection of over 2 million bioactive molecules maintained by the European Bioinformatics Institute. It supports compound searches, target information retrieval, bioactivity data queries (IC50, Ki, EC50), similarity/substructure searches, and drug discovery workflows for medicinal chemistry research.

A documentation skill that teaches how to use Zarr, a Python library for storing large N-dimensional arrays with chunking and compression. It covers array creation, storage backends (local, cloud, memory), compression codecs, parallel computing with Dask, and integration with NumPy and Xarray for scientific computing workflows.

A comprehensive reference skill for Vaex, a high-performance Python library for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Covers DataFrame operations, data loading, filtering, aggregations, machine learning pipelines, visualization, and performance optimization strategies.

This skill provides comprehensive documentation and guidance for using UMAP (Uniform Manifold Approximation and Projection), a fast dimensionality reduction technique for visualization and machine learning. It covers installation, parameter tuning, supervised/unsupervised learning, clustering preprocessing with HDBSCAN, and advanced features like Parametric UMAP and inverse transforms.

A comprehensive reference skill for the statsmodels Python library, covering statistical modeling techniques including linear regression, generalized linear models, discrete choice models, time series analysis, and statistical diagnostics. Provides code examples, best practices, and detailed explanations for econometrics and rigorous statistical inference.

This skill provides comprehensive documentation and examples for using the seaborn Python library for statistical data visualization. It covers core plotting functions (scatter, line, distribution, categorical, regression, and matrix plots), the modern objects interface API, multi-plot grids, theming, and best practices for creating publication-quality figures.