> browse/registry

> smolagents

You are an expert in smolagents, Hugging Face's minimalist agent framework. You help developers build AI agents that write and execute Python code to solve tasks, use tools from the Hugging Face Hub, chain multiple agents together, and run on any LLM (OpenAI, Anthropic, local models) — providing a simple, code-first approach to building agents without complex abstractions.

> mcp-server-builder

Build Model Context Protocol (MCP) servers that connect AI agents to external services and data sources. Use when a user asks to create an MCP server, build an MCP tool, connect an AI agent to an API, create a tool server for Claude, build MCP resources, or expose a database/service via MCP. Generates TypeScript or Python MCP servers with tools, resources, and prompts following the official MCP specification.

> locust

When the user wants to perform load testing using Python with Locust's distributed architecture and real-time web UI. Also use when the user mentions "locust," "Python load testing," "distributed load test," "locust web UI," or "locustfile." For JavaScript-based load testing, see k6 or artillery.

> blender-3d-modeling

Create 3D models procedurally with Blender Python. Use when the user wants to generate meshes from code, build geometry with bmesh, apply modifiers, create parametric shapes, procedural landscapes, grids, curves, or any programmatic 3D modeling in Blender.

> deepeval

Expert guidance for DeepEval, the open-source framework for unit testing LLM applications. Helps developers write test cases, define custom metrics, and integrate LLM quality checks into CI/CD pipelines using a pytest-like interface.

> blender-render-automation

Automate Blender rendering from the command line. Use when the user wants to set up renders, batch render scenes, configure Cycles or EEVEE, set up cameras and lights, render animations, create materials and shaders, or build a render pipeline with Blender Python scripting.

> dlt

You are an expert in dlt, the open-source Python library for building data pipelines. You help developers load data from any API, file, or database into warehouses and lakes using simple Python decorators — with automatic schema inference, incremental loading, and built-in data contracts. dlt is the "requests library for data pipelines."

> computer-vision-expert

Design, implement, debug, and review computer vision systems in Python, including image processing, detection, segmentation, classification, tracking, OCR, camera pipelines, and dataset-driven evaluation. Use when working with OpenCV, PyTorch vision models, video/image analysis, model-selection tradeoffs, annotation strategy, failure analysis, or CV performance and robustness problems.

> pandas

Assists with loading, cleaning, transforming, and analyzing tabular data using pandas. Use when importing CSV/Excel/SQL data, handling missing values, performing groupby aggregations, merging datasets, working with time series, or building analysis-ready datasets. Trigger words: pandas, dataframe, csv, groupby, merge, time series, data cleaning.

> ibis

Expert guidance for Ibis, the Python dataframe library that provides a pandas-like API but generates SQL for execution on any backend — DuckDB, PostgreSQL, BigQuery, Snowflake, Spark, and more. Helps developers write analytics code once and run it anywhere without rewriting SQL for each database.

> mise

Manage tool versions and tasks with mise (formerly rtx). Use when a user asks to manage Node.js/Python/Go versions per project, replace nvm/pyenv/asdf, or define project-level tool requirements.

> blender-scripting

Write and run Blender Python scripts for 3D automation. Use when the user wants to automate Blender tasks, run headless scripts, manipulate scenes, batch process .blend files, import/export 3D models, manage objects, or script Blender from the command line using the bpy API.

> pipedream

You are an expert in Pipedream, the workflow automation platform built for developers. You help teams build event-driven integrations connecting 2,000+ apps using Node.js/Python code steps, pre-built triggers, and managed auth — with built-in key-value store, queues, and HTTP endpoints for complex automation that goes beyond simple no-code tools.

> unit-test-starter

Generate thorough Python 3 pytest unit tests across a repo by scanning every *.py file and each function, writing one test module per source file while skipping IO/network behavior and documenting gaps.

> ray

Framework for scaling Python applications from a laptop to a cluster. Includes Ray Core for distributed computing, Ray Serve for model serving, Ray Tune for hyperparameter optimization, and Ray Data for distributed data processing.

> mojo

Expert guidance for Mojo, the programming language by Modular that combines Python's usability with C-level performance. Helps developers write high-performance AI/ML code, optimize numerical computations with SIMD and parallelism, and gradually port Python code to Mojo for orders-of-magnitude speedups.

> dspy

You are an expert in DSPy, the Stanford framework that replaces prompt engineering with programming. You help developers define LLM tasks as typed signatures, compose them into modules, and automatically optimize prompts/few-shot examples using teleprompters — so instead of manually crafting prompts, you write Python code and DSPy finds the best prompts for your task.

> django

Django is a batteries-included Python web framework that follows the model-template-view pattern. It provides an ORM, admin interface, authentication, and everything needed to build full-featured web applications rapidly and securely.

> fastapi

FastAPI is a modern, high-performance Python web framework for building APIs. It leverages Python type hints and Pydantic for automatic validation, serialization, and OpenAPI documentation generation with async/await support out of the box.

> instructor

You are an expert in Instructor, the library for getting structured, validated output from LLMs. You help developers extract typed data from unstructured text using Pydantic models (Python) or Zod schemas (TypeScript), with automatic retries on validation failures, streaming partial objects, and support for OpenAI, Anthropic, Google, and local models — turning LLMs into reliable data extraction engines.