Agent Skills Hub

BattleScope

Streamline technical documentation for BattleScope features, maintaining consistency across API, frontend, and architecture layers.

vvm

VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM acts as the runtime. Orchestrate multi-agent workflows, manage state, and build resilient AI pipelines.

rag-engineer

Architect and optimize production-grade RAG systems. Master embedding models, vector databases, chunking strategies, and retrieval pipelines for high-accuracy LLM applications.

wiki-llms-txt

Generates llms.txt and llms-full.txt files to provide LLM-friendly documentation and project context.

tdd-london-chicago

Master professional TDD with the London (mockist) and Chicago (classicist) schools. Automate test-first workflows, style selection, and refactoring with AI agents.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.

mystery-novel-conventions

A framework for crafting suspense, detective, and mystery narratives, emphasizing fair play principles, clue placement, and plot structure.

mcp-development

Guidance for Model Context Protocol (MCP) server development, including tool design, resource handling, and AI/ML integration patterns.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

livewire-development

Develops reactive Livewire 4 components, handling wire directives, state management, real-time updates, component testing, and integration with Flux UI for high-performance Laravel applications.

ring:testing-skills-with-subagents

A meta-skill for building robust AI agent skills using a TDD approach: define failure (RED), implement the skill (GREEN), and plug rationalization loopholes (REFACTOR).