원클릭으로 Manus에서 모든 스킬 실행

mixed

Multiple LLM backends in one workshop. Claude and Codex agents working together. Use when different models have different strengths.

Manus에서 실행

개요

Multiple LLM backends in one workshop. Claude and Codex agents working together. Use when different models have different strengths.

설치 명령

npx skills add https://github.com/joshrotenberg/agent_workshop --skill mixed

이 명령을 Claude Code에 복사하여 붙여넣어 스킬을 설치하세요

출처

joshrotenberg/agent_workshop

스타0

포크0

업데이트2026년 4월 2일 19:53

SKILL.md

readonly

name	mixed
description	Multiple LLM backends in one workshop. Claude and Codex agents working together. Use when different models have different strengths.
license	MIT
metadata	{"author":"joshrotenberg","version":"1.0"}

Mixed Backends

Different LLMs for different roles. Same Workshop API regardless of backend.

Setup

configure(backend: AgentWorkshop.Backends.Claude,
  backend_config: ClaudeWrapper.Config.new(working_dir: "."))

agent(:impl, "You write code.", model: "sonnet")
agent(:reviewer, "Review only.",
  backend: AgentWorkshop.Backends.Codex,
  backend_config: CodexWrapper.Config.new(working_dir: "."),
  model: "o3")

When to use

Different models excel at different tasks
You want multiple perspectives from different LLMs
Cost optimization (cheaper model for simple tasks)

이 저장소의 다른 Skills

같은 저장소

workflow

joshrotenberg/agent_workshop

Declarative multi-stage workflows. Define staged pipelines where each stage feeds its result to the next. Use for structured multi-agent tasks.

2026-04-060

github

joshrotenberg/agent_workshop

GitHub integration via gh CLI. List issues, create PRs, comment on issues. Use for agents that bridge GitHub and the Workshop board.

2026-04-060

board-worker

joshrotenberg/agent_workshop

Autonomous board worker. Receives work items, implements them, reports results. Designed for agents that poll the board and execute tasks independently.

2026-04-050

board

joshrotenberg/agent_workshop

Work board driven development. Post typed work items with dependencies, agents poll by role. Use for multi-step features where ordering matters.

2026-04-020

monitor

joshrotenberg/agent_workshop

Scheduled agent for periodic checks. Use for CI monitoring, PR scanning, health checks, or any polling-based workflow.

2026-04-020

orchestrator

joshrotenberg/agent_workshop

Coordinate a team of AI agents to build software. Break tasks down, create specialist agents from profiles, delegate via ask/cast, review results, and clean up. Use when you need to orchestrate multi-agent workflows.

2026-04-020

출처

joshrotenberg

joshrotenberg/agent_workshop

GitHub 저장소 열기 Creator 저장소 보기

설치 명령

다운로드

Manus에서 실행

유용한 대상SOC

소프트웨어 개발자컴퓨터 및 수학직15-1252L4

name	mixed
description	Multiple LLM backends in one workshop. Claude and Codex agents working together. Use when different models have different strengths.
license	MIT
metadata	{"author":"joshrotenberg","version":"1.0"}

Mixed Backends

Different LLMs for different roles. Same Workshop API regardless of backend.

Setup

configure(backend: AgentWorkshop.Backends.Claude,
  backend_config: ClaudeWrapper.Config.new(working_dir: "."))

agent(:impl, "You write code.", model: "sonnet")
agent(:reviewer, "Review only.",
  backend: AgentWorkshop.Backends.Codex,
  backend_config: CodexWrapper.Config.new(working_dir: "."),
  model: "o3")

When to use

Different models excel at different tasks
You want multiple perspectives from different LLMs
Cost optimization (cheaper model for simple tasks)