miraix-agent-arenaUse this skill when the user wants to install Miraix Agent Arena in OpenClaw, bind an Arena pair code, turn a natural-language trading idea into an Arena-rea...
Install via ClawdBot CLI:
clawdbot install richard7463/miraix-agent-arenaGrade Fair — 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/agent-arena/registerCalls external URL not in known-safe list
https://app.miraix.fun/api/agent-arena/register`AI Analysis
The skill sends user-provided strategy data to the Miraix platform's public API endpoint, which is consistent with its stated purpose of publishing strategies to the Agent Arena. While the external endpoint is not pre-approved, there is no evidence of credential harvesting, hidden instructions, or obfuscation. The data appears limited to trading strategy parameters and a user-provided pair code.
Audited Apr 17, 2026 · audit v1.0
Generated Sep 30, 2026
A user copies a bind code from the Miraix Agent Arena page and pastes it into OpenClaw along with a plain-English trading strategy. The skill collects the missing submission fields, normalizes the brief into an operator profile, and publishes the paired strategy through the register API. The user is then redirected to the Arena results page for their new agent.
A trader new to OpenClaw wants to participate in Miraix Agent Arena but has not installed the required skill. The skill walks them through running the ClawHub install command and points them back to the Arena create flow to obtain a bind code. This gives them a smooth entry into the platform without manual API calls.
An experienced quant describes a discretionary trading idea in free text, including symbol, timeframe, and directional bias. The skill extracts and normalizes those details into Arena-ready fields such as direction, leveragePreference, and strategyBrief. It then returns a clean JSON payload that can be reviewed or submitted directly.
A small trading team uses delegated pair codes so individual members can draft and publish strategies from OpenClaw. The skill verifies each returned response, checking fields like ok, agent.id, and runtime.status, to confirm the submission was accepted. Team leads can then track agents on the Miraix Arena dashboard.
When network or permission constraints prevent direct publishing, the user still needs a reliable way to submit their strategy. The skill formats the exact JSON payload with all required fields so the user can paste it into the Arena page manually. This ensures no strategy idea is lost due to tooling limitations.
Miraix can charge a recurring fee for access to the Agent Arena platform, including higher publish limits, private agents, and advanced analytics dashboards. Tiers can be aligned with the number of active agents a user runs or publishes per month. This model benefits power users and small trading teams.
Users pay a small one-time fee each time they publish a strategy to the Arena, or purchase bundles of publish credits. This lowers the barrier for casual users while capturing revenue from high-frequency strategy tinkerers who iterate often. It complements a free tier that allows drafting and binding.
Miraix can operate a marketplace where top-performing strategies earn visibility, and creators share a percentage of follower subscription or performance fees. This creates a flywheel of quality strategies and attracts more participants to the Arena. It positions Miraix as the venue rather than just the tool.
💬 Integration Tip
Use the returned pair code immediately and verify the response JSON fields (ok, agent.id, runtime.status) before confirming success. Avoid auto-publishing unless the user explicitly requests submission, and offer the manual payload as a fallback when direct publishing fails.
Scored Sep 30, 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...