Agent Skills Hub

mind

Persistent, Git-friendly memory for Claude. Automatically store and retrieve project decisions, bug fixes, and coding patterns in a local .mv2 file.

instruments-profiling

Use when profiling native macOS or iOS apps with Instruments/xctrace. Covers binary selection, CLI commands, trace exports, and common debugging gotchas.

debug-cuda-crash

Tutorial for identifying and resolving CUDA runtime crashes using FlashInfer's API logging framework.

database-driver-design

Expert guidance for building production-ready Swift database client libraries, covering wire protocols, connection pooling, state machines, and NIO integration.

create-mcp-app

Scaffold and build interactive MCP Apps with custom UIs for hosts like Claude Desktop. Supports React, Vanilla JS, and various framework templates for tool-resource integration.

vercel-deploy

Deploy applications to Vercel instantly. Supports preview and production deployments, automatic framework detection, and fallback script execution for seamless project publishing.

writing-agents

A framework for creating, testing, and managing autonomous AI subagents within project environments using Test-Driven Development principles.

anthropic-api

Expert guidance for building production-ready applications with Anthropic's Claude API. Covers SDKs, prompt caching, batch processing, streaming, tool use, and cost optimization strategies.

react-native-best-practices

React Native performance optimization guide covering FPS, TTI, bundle size, memory leaks, and profiling patterns based on Callstack's industry-standard expertise.

python-plan-optimization

6-phase read-only Python analysis workflow that identifies design principle violations, code smells, and modernization opportunities based on specific project types (POC to Open Source).

list-directory

List files and directories in a specified path to explore project structures, locate files, and verify folder contents.

configuring-connection-pools

Optimizes Prisma Client connection pool settings for production databases, serverless environments, and high-concurrency architectures to prevent connection exhaustion and performance bottlenecks.