> browse/registry

> jupyter

Assists with interactive data analysis, visualization, and reproducible research using Jupyter notebooks. Use when building notebooks that combine code with rich output, managing kernels, converting to reports, or parameterizing notebooks for batch execution. Trigger words: jupyter, notebook, jupyterlab, ipynb, nbconvert, papermill.

> pandas-ai

PandasAI enables natural language queries on pandas DataFrames using LLMs. Learn to ask questions in plain English, generate charts, clean data, and integrate with OpenAI and local models for conversational data analysis.

> pandera

Expert guidance for Pandera, the Python library for validating pandas and Polars DataFrames with expressive schemas. Helps developers define data contracts, validate data pipelines, and catch data quality issues before they corrupt downstream systems.

> code-migration

Migrate codebases between frameworks, languages, and API versions. Use when a user asks to convert JavaScript to TypeScript, migrate React class components to hooks, upgrade Vue 2 to Vue 3, migrate Python 2 to 3, update deprecated APIs, switch ORMs, convert Express to Fastify, or modernize legacy code. Handles incremental migration with backward compatibility.

> polars

Polars is a blazingly fast DataFrame library written in Rust with a Python API. Learn eager and lazy evaluation, expressions, groupby, joins, and how Polars outperforms pandas for large datasets through parallel execution.

> poetry

Manage Python projects with Poetry. Use when a user asks to manage Python dependencies, create virtual environments, publish packages to PyPI, handle dependency resolution, or set up a Python project structure.

> prefect

Prefect is a modern workflow orchestration framework for Python data pipelines. Learn to define flows and tasks with decorators, handle retries and scheduling, create deployments, and monitor via the Prefect UI.

> powerpoint

Create, edit, and manipulate PowerPoint (.pptx) files programmatically using python-pptx. Use when a user asks to generate a PPTX, modify slides, extract text from a presentation, add charts or tables to PowerPoint, build slides from data, convert content to PPTX, or automate PowerPoint file creation.

> pytest

Test Python code with pytest. Use when a user asks to write unit tests, set up test fixtures, mock dependencies, run async tests, measure coverage, or implement test-driven development in Python.

> pydantic

Validate and serialize data with Pydantic. Use when a user asks to validate API inputs, parse JSON/env config, define data models in Python, serialize objects, or implement data validation with type hints.

> pytorch

Assists with building, training, and deploying neural networks using PyTorch. Use when designing architectures for computer vision, NLP, or tabular data, optimizing training with mixed precision and distributed strategies, or exporting models for production inference. Trigger words: pytorch, torch, neural network, deep learning, training loop, cuda.

> onnx

Open Neural Network Exchange format for model interoperability across frameworks. Export models from PyTorch, TensorFlow, and other frameworks to ONNX, optimize with ONNX Runtime, and deploy for cross-platform inference on CPU, GPU, and edge devices.

> sqlalchemy

Work with databases in Python using SQLAlchemy. Use when a user asks to set up a Python ORM, define database models, write async database queries, manage migrations with Alembic, or choose between SQLAlchemy and Django ORM.

> tensorflow

You are an expert in TensorFlow, Google's open-source machine learning framework. You help developers build, train, and deploy neural networks using Keras (TensorFlow's high-level API), custom training loops, TensorFlow Serving for production inference, TFLite for mobile/edge deployment, and TensorFlow.js for browser ML — from prototyping to production-scale distributed training.

> json-to-pydantic

Converts JSON data snippets into Python Pydantic data models.

> azure-mgmt-apicenter-py

Azure API Center Management SDK for Python. Use for managing API inventory, metadata, and governance across your organization. Triggers: "azure-mgmt-apicenter", "ApiCenterMgmtClient", "API Center", "API inventory", "API governance".

> azure-keyvault-py

Azure Key Vault SDK for Python. Use for secrets, keys, and certificates management with secure storage. Triggers: "key vault", "SecretClient", "KeyClient", "CertificateClient", "secrets", "encryption keys".

> azure-mgmt-botservice-py

Azure Bot Service Management SDK for Python. Use for creating, managing, and configuring Azure Bot Service resources. Triggers: "azure-mgmt-botservice", "AzureBotService", "bot management", "conversational AI", "bot channels".

> azure-data-tables-py

Azure Tables SDK for Python (Storage and Cosmos DB). Use for NoSQL key-value storage, entity CRUD, and batch operations. Triggers: "table storage", "TableServiceClient", "TableClient", "entities", "PartitionKey", "RowKey".

> robotics-testing

Testing strategies, patterns, and tools for robotics software. Use this skill when writing unit tests, integration tests, simulation tests, or hardware-in-the-loop tests for robot systems. Trigger whenever the user mentions testing ROS nodes, pytest with ROS, launch_testing, simulation testing, CI/CD for robotics, test fixtures for sensors, mock hardware, deterministic replay, regression testing for robot behaviors, or validating perception/planning/control pipelines. Also covers property-based