multi-agent-voting

Community

Coordinate multi-agent voting for decisions.

Authormarcusgoll
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Executes multi-agent voting for critical decisions using MAKER-style first-to-ahead-by-k error correction.

Core Features & Use Cases

  • Read voting configuration and validate voting enabled for this operation.
  • Spawn N parallel agents with temperature variations for decorrelation.
  • Collect votes, apply red-flag filtering, and aggregate using MAKER-style algorithm or other strategies.
  • Calculate consensus, log outcomes, and support learning for adaptive voting.

Quick Start

  1. Determine operation type from context and load the voting config.
  2. Spawn the configured number of agents in parallel with varied temperatures.
  3. Collect votes from agents, filter red flags, and aggregate using chosen strategy.
  4. Determine consensus and commit decision; log results for learning.
  5. (Optional) Update adaptive parameters for future rounds.

Note

This skill includes a reference implementation with a Python-based aggregator and a bash orchestrator.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: multi-agent-voting
Download link: https://github.com/marcusgoll/Spec-Flow/archive/main.zip#multi-agent-voting

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.