Agent Skills Hub

parxy

A unified document processing gateway for PDF parsing, text extraction, conversion, and document manipulation across multiple local and cloud providers.

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.

ultraqa

Autonomous QA cycling workflow that runs test-verify-fix loops until your quality goals are met.

reviewing-code

Perform rigorous code reviews for FastMCP projects, focusing on API design, dependency management, and codebase consistency.

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.

create-prd

Plan features through an interactive, multi-step process that generates comprehensive Product Requirements Documents (PRDs) with user stories, acceptance criteria, and technical specifications.

getting-started-guide

A structured guide for novelists to navigate the seven-step writing process, from constitution and specification to planning, tasking, drafting, and quality analysis.

code-review-facilitator

Automated static code review for Arduino, ESP32, and RP2040 projects. Identifies memory safety issues, structure improvements, and best practices to enhance firmware quality and reliability.

dojo-debug

Diagnose and resolve connection, sync, subscription, and type issues in Dojo.js applications. Use for troubleshooting Torii, entity queries, and state updates.

xrk-bot

Expert for XRK-AGT runtime core, bot main class, event bus, server startup (HTTP/WS), and global object management.

let-fate-decide

Injects entropy into decision-making using Tarot card readings when user prompts are vague, casual, or require creative tie-breaking.

orchestrator

Autonomous multi-agent orchestration framework for Claude Code with memory-driven workflows, parallel-first task execution, Aristotle-based deconstruction, and multi-stage quality gates.