> browse/registry

> cube

Expert guidance for Cube, the headless BI and semantic layer that sits between your data warehouse and analytics applications. Helps developers define data models, create metrics APIs, and build analytics features in applications with consistent, governed access to business metrics.

> great-expectations

Great Expectations is a Python framework for data quality testing and validation. Learn to define expectations, create validation suites, build data docs, and integrate with data pipelines for automated quality checks.

> iptables

Configure Linux firewall with iptables/nftables. Use when a user asks to set up a firewall, block ports, allow specific traffic, configure NAT, or secure a Linux server network.

> brand-guidelines

Create and maintain brand style guides for consistent visual identity. Use when a user asks to create brand guidelines, build a style guide, define a brand identity, create a design system document, establish brand colors and typography, or produce any brand standards documentation.

> yup

Validate data with Yup schemas. Use when adding form validation, defining API request schemas, validating configuration, or building type-safe validation pipelines in JavaScript/TypeScript.

> protobuf

You are an expert in Protocol Buffers (protobuf), Google's language-neutral binary serialization format. You help developers define data schemas with `.proto` files, generate typed code for multiple languages, build efficient APIs with gRPC, and handle schema evolution with backward/forward compatibility — achieving 3-10x smaller payloads and 20-100x faster serialization than JSON.

> just

Run project commands with just (a modern make alternative). Use when a user asks to define project commands, replace Makefile, create a command runner, or standardize dev scripts.

> ipfs

Store and retrieve files on IPFS (InterPlanetary File System). Use when a user asks to store files in a decentralized way, pin content on IPFS, upload NFT metadata, or use content-addressed storage.

> solidity-debug

[AUTO-INVOKE] MUST be invoked when debugging failed on-chain transactions. Covers transaction receipt analysis, gas diagnosis, calldata decoding, revert reason extraction, and state verification. Trigger: any task involving failed tx analysis, revert debugging, or on-chain transaction troubleshooting.

> solana

You are an expert in Solana blockchain development. You help developers build on-chain programs (smart contracts) in Rust, interact with the Solana network using @solana/web3.js, create tokens (SPL), build NFT collections, and integrate with wallets — leveraging Solana's 400ms block times, parallel transaction processing, and sub-cent fees for high-throughput applications.

> maestro

When the user wants to write mobile UI tests using Maestro's simple YAML-based flow definitions. Also use when the user mentions "maestro," "mobile UI testing," "YAML mobile tests," "maestro flows," or "maestro studio." For React Native-specific gray-box testing, see detox. For cross-platform mobile automation, see appium.

> crewai

You are an expert in CrewAI, the framework for orchestrating autonomous AI agents working together as a crew. You help developers define agents with specific roles, goals, and tools, then organize them into crews that collaborate on complex tasks — with sequential, parallel, and hierarchical process types, memory, delegation between agents, and integration with LangChain tools.

> keystonejs

Expert guidance for KeystoneJS, the open-source headless CMS and application platform built on Node.js, GraphQL, and Prisma. Helps developers define content schemas, build admin interfaces, implement access control, and create custom GraphQL APIs for content-driven applications.

> 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.

> 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.

> motion

You are an expert in Motion, the production-ready animation library for React (formerly Framer Motion). You help developers create fluid animations, layout transitions, scroll-linked effects, gesture interactions, shared layout animations, and exit animations — using a declarative API where animations are defined as props rather than imperative code.

> mongoose

You are an expert in Mongoose, the elegant MongoDB object modeling library for Node.js. You help developers define schemas with validation, build queries with a fluent API, use middleware hooks, populate references, create virtual fields, and handle transactions — providing structure and type safety on top of MongoDB's flexible document model.

> artillery

When the user wants to perform load testing or performance testing using Artillery with YAML-based scenario definitions. Also use when the user mentions "artillery," "YAML load test," "WebSocket testing," "Socket.io load test," "scenario-based load testing," or "artillery run." For JavaScript-based load testing, see k6.

> cucumber

When the user wants to write behavior-driven development (BDD) tests using Gherkin syntax and Cucumber step definitions. Also use when the user mentions "cucumber," "BDD," "Gherkin," "feature files," "given-when-then," "step definitions," or "behavior-driven." For contract testing, see pact.

> hardhat

Develop and test Ethereum smart contracts with Hardhat. Use when a user asks to set up a Solidity development environment, test smart contracts, deploy to testnets, or debug Ethereum transactions.