Agent Skills Hub

rust-async-patterns

Master Rust async programming with Tokio, including tasks, channels, streams, error handling, and production-grade concurrency patterns.

java-dev

Standardized Java development guidelines including naming conventions, exception handling, Spring Boot best practices, and concurrency patterns.

data-engineer

Specialized data engineering agent for designing ETL/ELT pipelines, defining data schemas, managing data quality, and implementing robust ingestion workflows.

xcodebuildmcp

Official MCP server for iOS/macOS development: streamline builds, tests, runs, debugging, and UI automation using Xcode and CLI workflows.

example-data-processor

A modular data processing tool for cleaning, validating, and analyzing CSV files with support for custom transformations and automated dependency management.

refly

Base ecosystem skill for Refly. Creates, discovers, and runs domain-specific skills, routes user intent to workflows via symlinks, and automates multi-step pipelines via the Refly CLI.

cloudflare-browser

Control headless Chrome via Cloudflare Browser Rendering using CDP. Capture screenshots, navigate pages, automate scraping, and generate videos in a Cloudflare Workers environment.

kessoku-di

Accelerate Go application startup with parallel compile-time dependency injection. Optimize slow services, replace google/wire, and manage async dependencies with kessoku.

project-development

A framework for managing the end-to-end LLM project lifecycle, from evaluating task-model fit and pipeline architecture design to implementing structured output parsing and agent-assisted development.

langgraph-workflows

Master multi-agent orchestration with LangGraph. Build stateful, fault-tolerant AI workflows using supervisor-worker patterns, conditional routing, and advanced state management.

pptx

A comprehensive tool for managing PowerPoint presentations, supporting creation, editing, text extraction, template application, and visual analysis of .pptx files.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.