> browse/registry

> stagehand

You are an expert in Stagehand by BrowserBase, the AI-powered browser automation framework that lets you control web pages using natural language instructions. You help developers build web automations that act, extract data, and observe pages using plain English commands instead of brittle CSS selectors — powered by GPT-4o or Claude for visual understanding of page layouts.

> 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.

> langchain

Build LLM-powered applications with LangChain. Use when a user asks to create AI chains, build RAG pipelines, implement agents with tools, set up document loaders, create vector stores, build conversational AI, implement prompt templates, chain LLM calls, add memory to chatbots, or orchestrate language model workflows. Covers LangChain v0.3+ with LCEL (LangChain Expression Language), structured output, tool calling, retrieval, and production deployment patterns.

> svgo

Optimize SVG files with SVGO — remove unnecessary metadata, minify paths, merge shapes, configure plugins, and integrate into build pipelines. Use when tasks involve reducing SVG file size, cleaning up exported SVGs from design tools, building icon systems, or automating SVG optimization in CI/CD.

> telegram-export

Export and download Telegram chats, media, and channel content. Use when a user asks to export Telegram chat history, download media from Telegram channels or groups, archive Telegram conversations, backup Telegram messages, extract images or videos from Telegram, bulk download from Telegram channels, scrape Telegram content, or migrate Telegram data. Covers Telegram Desktop export, Telethon-based scripting, and TDLib approaches.

> ai-guardrails

Implement safety guardrails for AI systems — content filtering, prompt injection detection, output validation, bias mitigation, and responsible AI practices. Use when tasks involve adding safety layers to LLM applications, detecting prompt injection attacks, filtering harmful content, implementing rate limiting for AI APIs, validating LLM outputs against schemas, building moderation pipelines, or ensuring AI systems comply with safety policies.

> testcontainers

When the user wants to run integration tests with real dependencies using Docker containers managed by Testcontainers. Also use when the user mentions "testcontainers," "integration testing with Docker," "database integration tests," "containerized tests," or "test with real database." For API mocking without containers, see mockoon or wiremock.

> tiktok-marketing

Create, optimize, and automate TikTok content for brand awareness, audience growth, and conversions. Use when someone asks to "grow on TikTok", "create TikTok content", "TikTok marketing strategy", "TikTok API integration", "automate TikTok posting", "TikTok analytics", or "TikTok for business". Covers short-form video strategy, trending sounds, TikTok Content Posting API, analytics, and growth tactics.

> spring-boot

Spring Boot is a Java framework that simplifies building production-ready applications. It provides auto-configuration, embedded servers, and opinionated defaults for REST APIs, data access with JPA, security, and monitoring via Actuator.

> ai-pentesting

Run autonomous AI-driven penetration tests on web applications using tools like Shannon, PentAGI, and similar frameworks. Use when tasks involve setting up automated penetration testing pipelines, combining AI agents with security tools (nmap, subfinder, nuclei, sqlmap), building autonomous exploit chains, generating pentest reports with proof-of-concept exploits, or integrating AI pentesting into CI/CD pipelines. Covers the full pentest lifecycle from reconnaissance to reporting using AI orches

> llamaindex

Assists with building RAG pipelines, knowledge assistants, and data-augmented LLM applications using LlamaIndex. Use when ingesting documents, configuring retrieval strategies, building query engines, or creating multi-step agents. Trigger words: llamaindex, rag, retrieval augmented generation, vector index, query engine, document loader, knowledge base.

> cypress

Assists with end-to-end testing of web applications using Cypress. Use when writing E2E tests, setting up component testing, configuring CI pipelines with parallelization, or building custom test commands. Trigger words: cypress, e2e testing, end-to-end, cypress run, cy.get, integration testing, browser testing.

> d1-database

Build serverless applications with Cloudflare D1 — SQLite at the edge. Use when someone asks to "serverless database", "Cloudflare D1", "SQLite at the edge", "database for Workers", "edge database", or "serverless SQL". Covers schema setup, queries, migrations, Workers integration, and Drizzle ORM.

> datadog

Configure and manage Datadog for infrastructure monitoring, application performance monitoring (APM), log management, and alerting. Use when a user needs to set up Datadog agents, create dashboards, configure monitors and alerts, integrate services, or query metrics and logs through Datadog's API.

> n8n

Build workflow automations with n8n. Use when a user asks to automate business workflows, connect APIs visually, build integrations between apps, self-host a Zapier alternative, or create data pipelines with a visual editor.

> davinci-resolve

Automate and script DaVinci Resolve workflows. Use when a user asks to script DaVinci Resolve via Python/Lua API, automate color grading, batch render projects, manage timelines programmatically, automate media import, build render queues, create Fusion compositions via script, automate Fairlight audio processing, manage project databases, build custom tool scripts, or integrate Resolve into production pipelines. Covers the Resolve Scripting API (Python/Lua), Fusion scripting, and workflow autom

> db-backup

Set up automated database backup, restore, and disaster recovery procedures for PostgreSQL, MySQL, MongoDB, and Redis. Use when you need to implement backup schedules, point-in-time recovery, cross-region replication, backup verification, or disaster recovery runbooks. Trigger words: database backup, pg_dump, mysqldump, mongodump, disaster recovery, point-in-time recovery, WAL archiving, backup rotation, restore database, RTO, RPO, backup verification.

> xata

Expert guidance for Xata, the serverless data platform that combines PostgreSQL, Elasticsearch, and AI capabilities in a single API. Helps developers build applications with full-text search, vector similarity search, file attachments, and branching — all through a type-safe TypeScript SDK.

> youtube-marketing

Create, optimize, and manage YouTube content for channel growth, audience building, and monetization. Use when someone asks to "grow on YouTube", "optimize YouTube videos", "YouTube SEO", "YouTube Shorts strategy", "YouTube API integration", "automate YouTube uploads", "YouTube analytics", "YouTube thumbnail", or "YouTube content strategy". Covers long-form video, Shorts, SEO, thumbnail design, YouTube Data API, analytics, monetization, and growth strategies.

> 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."