A sophisticated prompting framework that simulates a multi-expert panel to provide diverse viewpoints and consensus for complex decision-making.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jz-roundtable
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 jz-roundtable 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 Roundtable?
Roundtable is a multi-perspective decision analysis framework designed to eliminate cognitive bias and identify blind spots in AI-driven workflows. Instead of relying on a single linear response, this skill simulates a panel of specialized experts—such as Risk Guardians, Technical Architects, and Growth Strategists—to stress-test ideas and build robust strategies. It is an essential component within the Openclaw Skills ecosystem for users who require high-confidence outcomes for critical tasks.
By executing directly within the main session, Roundtable avoids the overhead of subagent spawning, ensuring faster response times while maintaining full conversational context. It transforms a simple query into a structured debate, culminating in a synthesized consensus and actionable checklists, making it ideal for everything from code architecture reviews to financial risk assessment.
Roundtable Use Cases
- Validating high-risk operations like financial trading or system-wide configuration changes.
- Reviewing public-facing content or marketing campaigns to detect potential PR risks.
- Assessing complex architectural decisions in software development where technical debt must be weighed against speed.
- Facilitating strategic planning sessions by incorporating perspectives like the Devils Advocate or Historian Analyst.
How Roundtable Works
- The user triggers the workflow using keywords like roundtable this or by describing an important decision.
- The skill assesses the risk level to determine the optimal panel size, ranging from 3 experts for quick judgments to 8+ for strategic shifts.
- Relevant roles are dynamically selected from an expert pool based on the specific domain of the task.
- Two rounds of structured discussion are conducted where each role provides 2-3 sentences of focused insight or critique.
- The agent synthesizes all perspectives into a Consensus report, including a final recommendation and a checkbox-formatted action plan.
Roundtable Setup
Roundtable is a prompt-based skill that operates within the main execution session. To use it with Openclaw Skills, ensure the skill definition is available in your agent's library. There is no need for environment isolation or subagent spawning.
# To trigger the analysis, simply use the keyword in your prompt:
roundtable "Should we deploy the new API Gateway to production today?"
Roundtable Data Schema & Taxonomy
The skill produces a structured Markdown output designed for clarity and tracking:
| Section | Content Description |
|---|---|
| Discussion Rounds | Emoji-labeled expert viewpoints organized into two distinct rounds of dialogue. |
| Consensus | A synthesized final recommendation summarizing the collective expert opinion. |
| Action Items | A checklist (- [ ]) of specific tasks required to implement the decision safely. |
| Priority Score | (Optional) A calculated ranking: (impact * 0.4) + (confidence * 0.35) + ((100 - effort) * 0.25). |
Roundtable Advanced Features
- Dynamic Scaling: Automatically adjusts the number of participants based on the monetary or technical risk involved.
- specialized Protocols: Includes pre-configured modes like pre_trade for financial analysis and think_tank_review for high-risk system changes.
- Role-Based Diversity: Accesses a deep library of roles including Security Auditor, Skeptical Operator, and Legal Counsel to ensure non-obvious risks are caught.
- Consensus Logic: Focuses on resolving genuine disagreements rather than providing generic agreement, ensuring a true stress test of the proposal.
SKILL.md
Loading
Related Openclaw Skills
Humanizer
A writing editor skill designed to identify and eliminate the telltale signs of machine-generated text to restore natural human rhythm and voice.
Agent Guardrails
A mechanical enforcement suite that replaces soft markdown suggestions with hard git hooks and automated validation scripts for AI agents.
context-doctor
Visualize and diagnose context window allocation and token usage for AI coding agents.
AWI (Agentic Web Interface)
AWI is a zero-configuration single-binary tool for AI agents to read webpages and search the internet using an intelligent three-level fallback strategy.
Agent Workflow Enforcer
A framework to stabilize AI Agent execution by replacing soft prompts with hard-coded gate scripts and persistent style contexts.
Hyperliquid Market Data Assistant
A comprehensive read-only market data assistant for the Hyperliquid exchange that supports natural language and terminal-style command parsing.
Featured*
