Agora is a powerful multi-agent orchestration skill that spawns a specialized council of three agents to solve complex problems through parallel reasoning and debate.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agora-council
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agora-council using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Agora?
Agora transforms a standard AI interaction into a high-level collaborative session by invoking a specialized debate council. This tool is a standout among Openclaw Skills, inspired by advanced multi-agent architectures to provide a 360-degree analysis of any query. By acting as a Captain, the main agent coordinates three distinct personas—the Scholar, the Engineer, and the Muse—to ensure that every answer is backed by thorough research, logical rigor, and creative nuance.
This skill is particularly effective for complex, multi-faceted tasks where a single perspective might overlook critical details. By running these agents in parallel, Agora provides a comprehensive synthesis that highlights consensus, identifies conflicts, and offers a level of depth that single-agent sessions cannot match.
Agora Use Cases
- Solving intricate technical problems that require both deep research and code verification.
- Strategic decision-making that benefits from diverse, competing perspectives and lateral thinking.
- Comprehensive fact-checking and source verification for high-stakes research tasks.
- Debugging complex system architectures where logic flows and edge cases must be scrutinized from multiple angles.
How Agora Works
- The user triggers the council using the /agora command followed by a complex query.
- The Captain agent parses model flags and decomposes the query into specialized sub-tasks.
- Three specialized sub-agents (Scholar, Engineer, and Muse) are dispatched in parallel sessions.
- Each sub-agent provides a structured response including findings, confidence levels, and potential dissent.
- The Captain synthesizes these independent outputs into a single, high-confidence final answer, noting points of agreement and conflict.
Agora Setup
To activate this council within your Openclaw Skills setup, use the integrated command structure. No additional configuration is needed beyond ensuring your environment supports parallel session spawning.
/agora <your question>
/agora <question> --preset=premium
/agora <question> --scholar=sonnet --engineer=opus --muse=haiku
Agora Data Schema & Taxonomy
Agora organizes its output using a structured taxonomy to ensure clarity across the different perspectives provided by the council:
| Component | Responsibility |
|---|---|
| Scholar | Real-time web search, fact verification, and source citations. |
| Engineer | Step-by-step logic, mathematical calculations, and code verification. |
| Muse | Creative angles, user-friendly explanations, and challenging assumptions. |
| Captain Synthesis | Final consensus, conflict investigation, and cross-check verification. |
Agora Advanced Features
- Parallel execution of sub-agents via session spawning for maximum speed and efficiency.
- Customizable model selection per role to balance cost and performance.
- Predefined presets like cheap, balanced, premium, and diverse for rapid deployment.
- Automated conflict resolution that flags disagreements between agents for human review.
- Extensible architecture that supports model aliases for all major LLM providers within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Agent-to-Agent Communication Protocol
A foundational communication layer enabling AI agents to interact via events and automate multi-step workflows without human intervention.
Bits MCP Browser Automation
Control AI-powered browser automation agents to scrape data, fill forms, and navigate complex web workflows using a TypeScript SDK.
AgentTunnel
AgentTunnel is a specialized messaging service designed for AI agents to communicate securely without accounts or complex API configurations.
Leadership Prompts
A specialized library of 25+ high-impact AI prompts designed for engineering managers, tech leads, and VPs to navigate complex leadership challenges.
Personal Analytics
A local-first analytics tool that tracks conversation patterns, sentiment, and productivity markers to provide actionable self-knowledge insights.
Proactive Research
Transform your AI assistant from reactive to proactive by continuously monitoring specific topics and alerting you only when important developments occur.
Featured*
