agent-guruUse when building, designing, or reviewing a multi-agent system for production — routing agents, orchestrating subagents, guarding tools with permissions, ma...
Install via ClawdBot CLI:
clawdbot install weixuanjiang/agent-guruGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://config.internal/agent-policyAI Analysis
The skill definition is a design guide for building multi-agent systems and does not contain executable code that directly sends user data or performs actions. The flagged signals are from example code snippets within the guide (e.g., a dangerous shell command example, a reference to an internal config URL) and do not represent the skill's own operational behavior.
Audited Apr 17, 2026 · audit v1.0
Generated May 19, 2026
A multi-agent support system where a router classifies incoming queries (billing, technical, general) and dispatches to specialized agents. For complex issues, a supervisor agent orchestrates multiple sub-agents, with human-in-the-loop for refunds or account changes. Cost tracking and session persistence enable audit and recovery.
Agents analyze pull requests for style, security, and performance issues. A router splits reviews by domain (frontend, backend, infra) and delegates to specialist agents. A planner agent can suggest refactoring steps, with human approval for irreversible changes. Observability tracks token cost per PR.
An orchestrator agent decomposes a financial portfolio into risk factors (market, credit, liquidity) and spawns parallel sub-agents with scoped tools. Memory layer stores historical risk snapshots; circuit breakers prevent runaway computations during high volatility. Human-in-the-loop triggers for large exposures.
A router classifies patient symptoms into urgency levels and dispatches to triage agents. Orchestrator coordinates between scheduling agent (with calendar tools) and insurance verification agent. Permission guards restrict access to PHI; persistence enables session resume if user disconnects.
A multi-agent system handles order processing, inventory checks, shipping, and returns. Router directs cancellations to a refund agent with HITL for high-value orders. Cost tracking per order and observability traces help optimize logistics. Long-term memory stores customer preferences.
Offer pre-built multi-agent systems for common domains (support, e-commerce, healthcare) on a per-seat or per-transaction subscription. Includes hosting, maintenance, and updates. Revenue from monthly/annual subscriptions plus usage-based overages for high-volume customers.
Provide consulting services to design and deploy custom multi-agent systems for enterprise clients. Includes architecture design, implementation, integration, and training. Revenue from project-based fees and ongoing support contracts.
Create a platform where third-party developers can build and sell specialized agents (e.g., compliance-checker, inventory-optimizer). Platform takes a cut of each transaction or subscription sold through the marketplace. Revenue from commission on sales plus premium listing fees.
💬 Integration Tip
Start with a single ReAct agent and add multi-agent complexity only when hitting concrete limits like context window, tool sprawl, or latency. Use LangGraph for complex branching and HITL; Strands for simple leaf agents.
Scored May 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...