miraix-lifi-earn-agentUse this skill when the user wants to discover the best USDC vaults with LI.FI Earn, ask an agent to choose a safe vault on Base/Arbitrum/Ethereum, prepare a...
Install via ClawdBot CLI:
clawdbot install richard7463/miraix-lifi-earn-agentGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://app.miraix.fun/api/earn/chatCalls external URL not in known-safe list
https://app.miraix.fun/api/earn/chatAI Analysis
The external API calls are directly related to the skill's stated purpose of interacting with LI.FI Earn vaults and Composer, with no evidence of credential harvesting, hidden instructions, or obfuscation. The primary risk is the standard dependency on a third-party service (miraix.fun) for financial operations, not malicious data exfiltration.
Audited Apr 17, 2026 · audit v1.0
Generated May 12, 2026
Users can describe their investment criteria in natural language, and the agent will find the best USDC vault, prepare a Composer-compatible deposit, and execute it using an Agentic Wallet. This removes manual research and multi-step DeFi actions.
By specifying a risk mode (safe, balanced, degen), the agent filters vaults accordingly and recommends the most suitable option. This helps users align their deposit with their risk tolerance without needing to analyze complex metrics.
Users can request vaults on Base, Arbitrum, or Ethereum, and the agent handles cross-chain discovery and deposit. This enables seamless yield strategies across different L2s and Ethereum mainnet.
After a successful deposit, the agent explains which receipt token was received (e.g., sparkUSDC) and that it represents the user's position. This educates users about tokenized vault positions in plain language.
If the wallet lacks sufficient native gas on the target chain, the agent alerts the user and pauses the deposit. This prevents failed transactions and helps users understand on-chain requirements.
The platform charges a small fee (e.g., 0.1%) on each deposit executed via the agent. This aligns with user success and scales with volume.
Offer advanced features like custom risk filters, priority execution, and historical analytics for a monthly subscription. Users who manage larger or frequent deposits would pay for access.
License the earn agent API to other platforms (e.g., wallet apps, portfolio trackers) for a flat fee or revenue share. This expands reach without direct user acquisition.
💬 Integration Tip
Integrate the earn agent into a chat interface that accepts natural language and outputs structured vault data; handle wallet connectivity via Agentic Wallet SDK for seamless deposit execution.
Scored May 12, 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...