mixture-of-agents
OfficialEnhance planning with cross-lab model ensemble and broadcast refinement.
Software Engineering#planning#model ensemble#cross-lab ensemble#broadcast refinement#repository-based planning
Authordrivelineresearch
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill facilitates collaborative planning by leveraging an ensemble of models from different labs, enabling comprehensive analysis and refined outcomes.
Core Features & Use Cases
- Cross-Lab Ensemble: Utilizes models from OpenAI, Zhipu, Anthropic, and Moonshot to ensure diverse perspectives and insights.
- Broadcast Refinement: All proposals are reviewed by independent models, promoting robust verification and conflict resolution.
- Use Case: Ideal for complex architecture decisions where multiple perspectives are crucial, such as evaluating different approaches to software development projects.
Quick Start
/mixture-of-agents --spec ./docs/cache-layer-spec.md
Dependency Matrix
Required Modules
codexopencodeclaudecursor
Components
scriptsreferencesassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: mixture-of-agents Download link: https://github.com/drivelineresearch/moa-x/archive/main.zip#mixture-of-agents Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.