skills.rest
enkira-ai
enkira-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

agent-chat

Coordinate multi-agent collaboration with a deterministic round-robin protocol and auditable transcripts.

2|Updated Mar 7, 2026
Search Tags:#collaboration#python#cli#audit#multi-agent#transcripts#round-robin
One-click install
npx skills add https://github.com/enkira-ai/claude-plugins --skill agent-chat-enkira-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-chat
Source: https://github.com/enkira-ai/claude-plugins/tree/main/plugins/agent-chat/skills/agent-chat
Command: npx skills add https://github.com/enkira-ai/claude-plugins --skill agent-chat-enkira-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Two or more AI agents can be organized to collaborate on hard problems using a deterministic round-robin protocol, ensuring transparent, auditable transcripts and safe, human-in-the-loop governance.

Core Features & Use Cases

  • Round-robin collaboration for 2..N agents with strict turn order.
  • Per-agent JSONL transcripts and end-to-end audit prompts for reproducibility.
  • Easy spawning of subagents and unified session management from a CLI workflow.

Quick Start

Create a new session with at least two participants, then open the main agent's message and let others join by listening.

Frequently Asked Questions about agent-chat

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate multiple AI agents to collaborate on a design problem?▼

Multi-agent collaboration is coordinated using a deterministic round-robin protocol that enforces strict turn order, enabling agents to brainstorm and critique reasoning safely. It provides transparent governance and preserves an auditable prompt history for reproducibility.

How do I generate auditable transcripts for multi-agent AI sessions?▼

Auditable transcripts are generated as per-agent JSONL files during multi-agent collaboration sessions. The system automatically records turn enforcement and prompt history, ensuring end-to-end reproducibility for later review.

Can I spawn subagents during a round-robin collaboration session?▼

Yes, subagents can be spawned during an active round-robin collaboration session. The system manages unified session workflows from a CLI and includes optional subagent spawning with automatic prompt recording.

What is the best way to enforce turn order for two or more AI agents?▼

Turn order for two or more AI agents is enforced using a deterministic round-robin protocol. This approach guarantees strict turn-taking, preventing agents from interrupting each other and maintaining structured human-in-the-loop governance.

Does this multi-agent collaboration approach require any external dependencies?▼

No external dependencies are required for this multi-agent collaboration approach. It operates entirely through CLI scripts, providing session management and transcript recording without needing additional software libraries.

Related Skills

Explore More Software Engineering Skills→
adamtwissadamtwiss
18

local-rr

Automate local round-robin chess engine testing with cutechess-cli.

Community
Intermediate
augustsclaugustscl
2

session-logs

Extract user and assistant messages from session JSONL files using jq and rg.

Community
Intermediate
forgivesam168forgivesam168
2

agentic-eval

Evaluate AI agent outputs using structured rubrics and JSON feedback loops.

Community
Advanced
softsparksoftspark
161

swarm

Distribute complex tasks across multiple autonomous agents using map-reduce, consensus, or relay modes.

Community
Intermediate