OpenClaw skill
arbiter
An OpenClaw skill that enables a primary agent to delegate a query to multiple configured sub-agents and arbitrate their responses to produce a final output. It supports arbitration strategies such as voting, ranking, and synthesis explicitly defined in its configuration.
Security notice: review the SKILL.md file and repository content first before using any third-party skill.
Files
Review the files below to add this skill to your agents.
SKILL.md content
Unable to load SKILL.md content from source.
How this skill works
- The Arbiter skill receives a list of candidate responses generated by the base model or other skills
- It prompts an LLM to score each candidate on criteria: relevance, coherence, safety, and helpfulness
- Scores are normalized to 0-1 range
- Aggregate score is computed as weighted sum using config weights
- The candidate with the highest aggregate score is selected
- The skill outputs the selected response and a brief rationale
When to use it
- When multiple agents submit proposals for a task and one must be selected
- When resolving conflicts or disagreements between agent-generated plans
- When a consensus decision is required from voting among agent options
- When evaluating and choosing the optimal response from competing agent outputs
Example use cases
- Multi-Agent Debate Resolution: The arbiter judges competing arguments from multiple agents in a debate format and selects the winner with reasoning.
- Proposal Selection in Planning: Evaluates multiple action or plan proposals from sub-agents and chooses the optimal one based on specified criteria.
- Response Quality Judging: Compares outputs from different LLM agents responding to the same query and ranks or selects the best response.
- Conflict Arbitration in Collaborative Tasks: Resolves disagreements between agents on task execution steps by voting or scoring their suggestions.
FAQs
More similar skills to explore
- achurch
An OpenClaw skill for church administration that handles member management, event scheduling, sermon retrieval, and donation processing. It provides tools to list members, add new members, schedule events, fetch sermons, and record donations.
- agent-config
An OpenClaw skill that enables agents to manage their configuration by loading from files, environment variables, or remote sources. It supports retrieving, setting, and validating configuration values. The skill allows for hot-reloading of configurations.
- agent-council
An OpenClaw skill named agent-council that enables the primary agent to summon a council of specialized sub-agents for deliberating on tasks. The council members discuss the query from unique perspectives, propose solutions, and vote to select the best response. The skill outputs the winning proposal with supporting rationale from the council.
- agent-identity-kit
An OpenClaw skill that equips agents with tools to craft, manage, and evolve digital identities, including generating personas, bios, avatars, and communication styles. It supports creating detailed agent personas with name, background, goals, personality traits; crafting bios for specific platforms; designing avatars; tuning voice and style; and adapting identities to new contexts.
- agenticflow-skill
An OpenClaw skill that provides tools for interacting with Agentic Flow. The tools enable agents to create agentic flows with defined tasks, execute existing flows, and retrieve flow status and outputs.
- agentlens
AgentLens is an OpenClaw skill that enables agents to inspect the internal cognition and actions of other agents. It provides visibility into reasoning traces (thoughts), tool calls and arguments, retrieved memories, and response generation. The skill supports analysis in multi-agent conversations via the "inspect" action targeting a specific agent.