Agent Skills Hub

writing-standards

A professional writing standard plugin for high-quality Korean technical content, enforcing omniscient 3rd-person perspectives, AI pattern elimination, and systematic citation systems.

copy-editing

Systematically improve marketing copy through a 7-pass editing framework to boost clarity, tone, and conversion impact.

context-engineering-collection

A structured repository of Agent Skills for context engineering, multi-agent architectures, and production-grade agent system optimization.

autonomous-skill

Enable long-running, multi-session autonomous development tasks with state tracking, resumable execution, and dual-agent planning-execution workflows.

skill-from-github

Create high-performance AI skills by reverse-engineering successful GitHub projects and proven open-source methodologies.

hf-mcp

Connect your AI agent to the Hugging Face Hub via MCP. Search models, datasets, and papers, manage repos, run cloud compute jobs, and invoke Gradio Spaces as functional AI tools.

prompt-rewriter

Advanced prompt rewriting and optimization service. Analyzes prompts for clarity, specificity, and structure, providing actionable improvements, variations for testing, and prompt engineering best practices.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

ensue-memory

Augmented cognition layer that connects conversations to a persistent knowledge tree, enabling long-term memory, recall, and contextual reasoning across projects.

claude-api

Expert guidance for Claude Messages API: structured outputs, prompt caching, tool use, and migration from deprecated Claude 3.x models to 4.5. Prevents common API errors.

grammar-check

Expert copyeditor and writing specialist that identifies grammar, logic, and flow errors in text with actionable, targeted fix suggestions.

massive-context-mcp

Process massive files and large codebases (10M+ tokens) by recursively chunking, sub-querying, and aggregating results to overcome LLM context limits.