What is the MAESTRO principle for plugins?

MAESTRO principles emphasize modular, autonomous, and structured evaluation tiers where each plugin manages its own context and handles its own errors independently.

How does the Stateless Reducer Pattern work in this context?

It treats each plugin as a pure function—evaluate(context) -> result—ensuring there are no side effects, shared class attributes, or global state dependencies.

Can this skill help refactor existing evaluation engines?

Yes, it is specifically designed to help developers decompose monolithic engines into modular, single-responsibility plugins that are easier to test and maintain.

Why does this skill prefer structured outputs over raw dictionaries?

Using validated Pydantic models ensures data integrity, provides strict type checking, and makes the plugin's interface explicit and predictable for subsequent pipeline tiers.

MAS Plugin Design

Name: MAS Plugin Design
Author: qte77

byqte77

0•

개발자 도구

Architects robust, stateless agent evaluation plugins using 12-Factor and MAESTRO principles.

This skill provides specialized architectural guidance for designing Multi-Agent System (MAS) evaluation plugins within Claude Code. It enforces rigorous design patterns such as the Stateless Reducer Pattern, structured Pydantic outputs, and independent context windows to ensure plugins are portable, scalable, and resilient. By following these principles, developers can build evaluation tiers that handle their own errors and state, leading to more reliable AI pipelines and production-grade agentic workflows.

주요 기능

01Architecture-level guidance for 12-Factor and MAESTRO compliance

020 GitHub stars

03Structured Pydantic model integration for validated input and output

04Context window management to prevent global state leakage

05Stateless Reducer Pattern implementation for side-effect-free evaluations

06Error handling patterns that favor structured results over exceptions

사용 사례

01Architecting new metrics or evaluation tiers for agentic pipelines

02Refactoring monolithic evaluation engines into modular plugin patterns

03Designing portable evaluation components for production AI systems

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add qte77/claude-code-utils-plugin designing-mas-plugins

For use in Claude.ai and ChatGPT

주요 기능

01Architecture-level guidance for 12-Factor and MAESTRO compliance

020 GitHub stars

03Structured Pydantic model integration for validated input and output

04Context window management to prevent global state leakage

05Stateless Reducer Pattern implementation for side-effect-free evaluations

06Error handling patterns that favor structured results over exceptions

사용 사례

01Architecting new metrics or evaluation tiers for agentic pipelines

02Refactoring monolithic evaluation engines into modular plugin patterns

03Designing portable evaluation components for production AI systems

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add qte77/claude-code-utils-plugin designing-mas-plugins

For use in Claude.ai and ChatGPT