Horace-Maxwell/horosa-skill

What it solves

Horosa Skill provides a standardized, offline-first interface for AI agents to access 110 professional astrology and metaphysics techniques. It solves the problem of AI models hallucinating or guessing parameters for complex calculations by enforcing a strict, local-first execution environment where every result is traceable and verifiable.

How it works

It acts as an MCP (Model Context Protocol) server or a CLI tool that runs on your local machine. When an AI client requests a calculation, the tool executes the underlying algorithms (such as Western astrology, Bazi, Ziwei, or Qimen Dunjia) locally. It returns a structured "envelope" containing the calculation results, a "technique card" that explains the methodology used, and a snapshot of the data. It includes a "clarification gate" that forces the AI to confirm parameters like time zones or birth data with the user before proceeding, preventing inaccurate inputs.

Who it’s for

This project is for developers and power users who want to integrate professional-grade astrology and metaphysics calculations into AI agents (like Claude Code, Cursor, or Open WebUI) while maintaining data privacy, offline availability, and high analytical accuracy.

Highlights

• 110 Professional Techniques: Covers a wide range of systems including Western astrology, Bazi, Ziwei, Qimen, and more.
• Offline-First: All algorithms run locally on your machine; no data is uploaded to the cloud.
• Traceable Results: Every conclusion comes with a "technique card" detailing the source, methodology, and versioning.
• AI-Ready Architecture: Designed with a stable JSON contract and MCP support to ensure consistent, structured output for LLMs.
• Multi-Technique Synthesis: Supports parallel calculation and synthesis of multiple techniques while explicitly highlighting any analytical conflicts.