registry / launches
New This Week
Up to 40 newest skills, MCP servers, tools, LLMs, and agents — sorted by listing time.
- 01
Up to 40 newest skills, MCP servers, tools, LLMs, and agents — sorted by listing time.
Ukraine's defense forces have deployed an AI-powered turret to intercept fiber-optic drones, which are immune to electronic jamming. The turret autonomously detects and tracks incoming drones, allowing operators to conf…
The Helix-02 is a humanoid robot designed for collaborative tasks in shared environments. It can perform complex actions like making a bed and putting away groceries using a single learned Vision-Language-Action system.
A tearable cloth simulation using verlet integration. This project demonstrates how to simulate the behavior of cloth that can be torn apart.
A specialized skill for creating and maintaining DESIGN.md files for consistent UI generation by AI agents.
Illospace is a workspace where teams work together alongside agents, sharing the same memory and the same 'team brain'. It features a canvas of ideas and threads for collaboration, chat, and dynamic interface generation.
Benchmark allows you to upload a fintech proposal and see if the price is fair. It extracts line items and compares them to over 150 products and 660 data points from real market proposals, providing a color-coded repor…
Cardamom is an AI voice line for takeout-heavy restaurants that answers inbound phone calls and connects directly into the restaurant’s POS system. It helps restaurants track returning customers, offer rewards, and buil…
Photobomb is a fun photo party game designed for 3 to 12 players. Similar to Cards Against Humanity, one player receives a prompt and everyone else has 40 seconds to find the best matching photo from their camera roll.
Sendly is the first AI native SMS platform that allows both agents and developers to send SMS from their applications in less than 5 minutes.
OpenAI provides APIs and tools for building AI products, enabling developers to create and scale AI experiences using industry-leading models.
Lingo.dev is a localization engineering platform where teams create localization engines. It offers stateful translation APIs configured with glossaries, brand voice rules, per-locale model chains, and AI quality scorin…
MESA builds your Shopify workflow by turning plain-English requests into automations. It helps Shopify merchants automate repetitive store operations like orders, inventory, fulfillment, and customer support.
Anthropic’s AI coding assistant, designed for deep context understanding and capable of handling complex software tasks with a massive context window (up to 200K tokens).
FlowMarket is a network of AI agents that automatically discover, match, and generate B2B deals. Create your agent in minutes and let it run 24/7, finding partners and delivering qualified leads.
The Fitbit Air is a lightweight, screenless wearable designed for 24/7 health tracking. It offers advanced insights through the Google Health app, making it a proactive wellness partner.
GPT-Realtime-2 is OpenAI's most intelligent voice model yet, featuring GPT-5-level reasoning and a 128,000-token context window. It enables real-time voice interactions and can handle complex conversations seamlessly.
BGRemover is an AI-powered tool that allows you to remove video backgrounds effortlessly. With just one click, you can make any video background transparent, making it perfect for content creators and marketers.
PageIndex provides precise, verifiable answers and insights from complex documents. It features a chat interface that allows users to understand documents with explainable answers grounded in the source.
Discovers and invokes agent skills for effective task management in engineering workflows.
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior.
Creates specs before coding to clarify requirements and ensure successful project execution.
Grounds every implementation decision in official documentation for authoritative, source-cited code.
Prepares production launches with checklists for code quality, security, performance, and more to ensure safe deployments.
Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations.
Breaks work into ordered tasks for clear implementation and estimation.
Optimizes application performance by identifying and fixing bottlenecks based on profiling data.
Delivers changes incrementally to manage large features effectively.
Refines raw ideas into actionable concepts through structured divergent and convergent thinking.
Structures git workflow practices for making code changes, committing, branching, and resolving conflicts.
Build production-quality user interfaces that are accessible, performant, and visually polished.
Records decisions and documentation for architectural choices, public APIs, and feature shipping to aid future engineers and agents.
Manages deprecation and migration. Use when removing old systems, APIs, or features.
Guides systematic root-cause debugging for tests, builds, and unexpected errors.
Optimizes agent context setup for improved output quality during coding sessions.
Simplifies code for clarity while preserving behavior, making it easier to read, maintain, and extend.
Conducts multi-axis code review to assess code quality across correctness, readability, architecture, security, and performance before merging changes.
Automates CI/CD pipeline setup and ensures quality gates are met before deployment.
Tests in real browsers using Chrome DevTools MCP for debugging and inspecting web applications.
Guides stable API and interface design for creating REST or GraphQL endpoints and defining type contracts between modules.
Create and scaffold plugin directories for Codex with required and optional structures for easy plugin management.
Times use createdAt (approximate "first seen"). Skills, MCP servers, and tools are APPROVED only; LLMs and agents include all directory rows in range.