Browse the directory

Build JavaScript and TypeScript apps with Bun, an all-in-one toolchain that replaces Node.js, npm, a bundler, and a test runner with one fast binary that executes TypeScript directly.

Build full-stack web apps with Svelte and SvelteKit. Minimal runtime overhead, reactive components, and server-side rendering. The most admired frontend framework of 2025. Svelte compiles components to vanilla JavaScript at build time, resulting in zero runtime overhead and exceptional performance.

Build end-to-end type-safe APIs with tRPC and TypeScript, eliminating code generation and runtime bloat for full-stack applications. tRPC provides end-to-end type safety without code generation, schema stitching, or serialization layers - delivering a lighter, more intuitive developer experience than REST or GraphQL.

TypeScript-first validation skill using Zod — define schemas once, get runtime checks and inferred types for APIs, forms, and data pipelines.

Official Dart team Agent Skills for AI coding agents working on Dart unit tests, CLI apps, coverage, runtime errors, mocks, package conflicts, static analysis, Native Assets, FFI, ffigen, and pattern matching.

Transcribe audio, synthesize speech, and run audio intelligence directly from Claude with the official Deepgram MCP server — dynamic tool discovery fetches new capabilities from Deepgram's API at runtime without requiring package upgrades.

Official Rust SDK for Model Context Protocol clients and servers, published as the `rmcp` crate with tokio async runtime support, server and client features, tool macros, resources, prompts, sampling, roots, logging, completions, notifications, Streamable HTTP, child-process transports, and OAuth support.

Apache-2.0 sandbox runtime and SDK suite for AI agents, with Python, Java/Kotlin, JavaScript/TypeScript, C#/.NET, and Go SDKs, Docker and Kubernetes runtimes, OpenSandbox MCP server, CLI, code interpreter, filesystem and command tools, network policy, credential vault, and secure container runtime guidance.

Unity MCP server, plugin, CLI, and skill generator for controlling Unity Editor and runtime projects from MCP clients through built-in game-dev tools.

Connect Claude to a Google Colab runtime. Colab MCP starts a local FastMCP server and websocket proxy, waits for an authorized Colab-origin browser connection, then exposes the session's notebook and runtime tools to your MCP client over stdio.

Expert FastMCP review skill for auditing Python MCP server structure, tools, resources, prompts, transports, and deployment readiness before release.

Connect Claude to Microsandbox microVMs for sandbox lifecycle, command execution, filesystem, volume, and metrics workflows.

Next.js App Router production-architecture specialist focused on the server/client boundary, the explicit caching model, route handlers, and Node-vs-Edge runtime tradeoffs — decisions, not component tips

A Claude agent persona for building multi-agent apps with Microsoft AutoGen v0.4: the asynchronous agent runtime, message-passing between agents, the AgentChat API, cross-language (Python and .NET) support, and tool use.

Open-source MCP platform for running MCP servers in isolated containers, managing registries, enforcing access policy, and operating local or Kubernetes-based MCP infrastructure.

Harden OpenClaw agent environments with secure defaults, policy boundaries, tool governance, and incident response playbooks.

Expert OpenNext + Cloudflare capability skill for Next.js on Workers, runtime constraints, cache strategy, and production-safe deploy architecture.

MIT-licensed frontend stack for agent-native applications and generative UI, with React, Angular, Vue, React Native, Slack and Teams surfaces, AG-UI protocol support, shared state, human-in-the-loop workflows, backend tool rendering, coding-agent skills, and runtime packages for agent apps.

Google Agents CLI skill suite for coding agents that build, scaffold, evaluate, deploy, publish, and observe ADK agents on Gemini Enterprise Agent Platform, Agent Runtime, Cloud Run, GKE, and Google Cloud.

Public streamable HTTP MCP server for Tandem documentation—install guides, SDK references, workflow docs, headless deployment, and docs-grounded setup help for the Tandem governed runtime.

MIT-licensed durable execution platform for building resilient applications with Workflows, Activities, Workers, Task Queues, Namespaces, retries, schedules, and event history.

MIT-licensed C/C++ LLM inference runtime for running GGUF models locally or through a lightweight OpenAI-compatible llama-server.

A source-backed collection for operators running AI services on infrastructure they control: local model runtime, CPU and GPU inference, model gateway, self-hosted MCP access, retrieval storage, model API packaging, container rebuilds, and image security checks.

Secure MCP servers with strict tool boundaries, auth controls, dependency hygiene, and abuse-resistant runtime policies.

Compile Rust, C++, or Go to WebAssembly and run it in the browser, Node.js, and serverless runtimes: wasm-bindgen JS interop, WASI for system access, the Component Model, and SIMD.

Microsoft-maintained MCP server and security-oriented WebAssembly component runtime for loading sandboxed tools, managing component permissions, and exposing Wasm component tools to Claude through MCP.

Build and review Hono TypeScript APIs for Cloudflare Workers, Bun, Deno, Node.js, Vercel, Netlify, and other Web Standards runtimes with routing, middleware, validation, RPC clients, OpenAPI generation, deployment checks, and production safety review.

Open-source SDK and runtime for building, running, and managing agent platforms with agents, teams, workflows, memory, knowledge, tools, MCP, and AgentOS.

A practical walkthrough of securely deploying Claude Agent SDK applications: the prompt-injection threat model, isolation options (sandbox runtime, containers, gVisor, VMs), least privilege, the proxy credential pattern, and filesystem controls.

A source-backed guide for designing Model Context Protocol servers with explicit authorization boundaries, narrow tools, scoped resources, privacy-aware logging, and least-privilege runtime access.