Tencent SkillHub · Productivity

XAUUSD

Institutional Desk-Level Fully Automated Trading OS for XAU/USD and XAG/USD. Event-driven, risk-first, multi-engine architecture that runs as a continuous analysis and execution pipeline inside OpenClaw's trader agent.

skill openclawclawhub Free

0 Downloads

0 Stars

0 Installs

0 Score

High Signal

⬇ 0 downloads ★ 0 stars Unverified but indexed

Install for OpenClaw

Quick setup

Download the package from Yavira.
Extract the archive and review SKILL.md first.
Import or place the package into your OpenClaw setup.

Requirements

Target platform: OpenClaw
Install method: Manual import
Extraction: Extract archive
Prerequisites: OpenClaw
Primary doc: SKILL.md

Package facts

Download mode: Yavira redirect
Package format: ZIP package
Source platform: Tencent SkillHub
What's included: index.js, README.md, package.json, SKILL.md, manifest.json, skill.json

Validation

Use the Yavira download entry.
Review SKILL.md after the package is downloaded.
Confirm the extracted package contains the expected setup assets.

Install with your agent

Agent handoff

Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.

Download the package from Yavira.
Extract it into a folder your agent can access.
Paste one of the prompts below and point your agent at the extracted folder.

New install

I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.

Upgrade existing

I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.

Open Send to Agent page Open JSON manifest Open Markdown brief

Trust & source

Release facts

Source: Tencent SkillHub
Verification: Indexed source record
Version: 1.0.0

Provenance

Publisher: cfilipemt
Source page: View original listing
Canonical URL: Open canonical page

Documentation

ClawHub primary doc Primary doc: SKILL.md 18 sections Open source page

Metals Desk OS

An institutional-grade metals trading operating system for gold (XAU/USD) and silver (XAG/USD). This skill transforms the OpenClaw trader agent into a full prop-desk assistant with real-time analysis, automated execution, risk management, and performance tracking.

When to Use This Skill

Use this skill when: Analyzing gold or silver market structure (ICT/SMC methodology) Generating trade signals with full entry/SL/TP plans Running automated or semi-automated trade execution via MT5 Monitoring real-time risk, drawdown, and position management Tracking trading performance (win rate, expectancy, Sharpe, drawdown) Getting session-aware, macro-aware trading intelligence

Architecture Overview

The system runs as a continuous event-driven pipeline: PRICE FEED → SESSION ENGINE → STRUCTURE ENGINE → LIQUIDITY ENGINE → MACRO ENGINE → BIAS ENGINE → VOLATILITY ENGINE → RISK ENGINE → EXECUTION ENGINE → BROKER → PERFORMANCE ENGINE → DASHBOARD → ALERTS All engines communicate through a central Event Bus (EventEmitter pattern). Every event is logged and can be monitored in real-time via WebSocket.

Core Engines

EnginePurposeKey OutputsStructure EngineDetects HH/HL/LH/LL, BOS, CHoCH, FVG, Order BlocksMarket structure, trend direction, structural shiftsLiquidity EngineFinds equal highs/lows, stop clusters, session levels, sweepsLiquidity pools, sweep confirmationsBias EngineMulti-timeframe directional bias with conviction scoringHTF bias, intraday bias, conviction 0-100, alignment scoreMacro EngineTracks DXY, US10Y yields, risk sentiment, news proximitymacro_bias (bullish/bearish/neutral gold), macro_risk levelVolatility EngineATR calculation, spike detection, regime classificationATR, volatility regime (low/normal/high/extreme)Risk EnginePosition sizing, drawdown monitoring, halt triggersLot size, risk %, pass/fail gate for every tradeExecution EngineCombines all engines to generate trade signalsFull trade plan: entry, SL, TP1/TP2/TP3, position sizePerformance EngineWin rate, expectancy, Sharpe, monthly breakdownComprehensive performance metrics and trade log

System Modes

ModeNameBehavior1AdvisoryFull analysis pipeline runs, signals logged, no execution2Semi-AutomatedSignals generated + automatic TP/SL/trailing management3Fully-AutomatedAutonomous execution: signal → order → manage → close4Risk-OffMonitoring only, no signals generated Set the mode in data/state.json or via WebSocket command. Always start in Mode 1 for validation.

Risk Rules (Non-Negotiable)

These hard rules are enforced by the Risk Engine and cannot be overridden: Max 2% risk per trade — Position sized via (Balance × Risk%) / StopDistance Max 5% daily exposure — Cumulative open risk capped 3 consecutive losses → halt trading for the session Volatility spike → reduce size 50% (extreme = 75% reduction) Spread widening → block entry (symbol-specific thresholds) High-impact news < 20 minutes → block all entries Equity drawdown > 8% → halt trading until manual resume API error on order → cancel, do NOT retry Broker disconnect → close all positions immediately

Trade Management Protocol

TP1 at 1.5R → Partial close 40% → Move SL to break-even TP2 at 2.5R → Partial close 30% → Trail SL under structure TP3 at 4.0R → Close remaining 30% → Log trade to performance

Entry Conditions (All Must Pass)

For the Execution Engine to generate a signal, every condition must be true: Bias conviction ≥ 65/100 Alignment score ≥ 0.6 Liquidity sweep confirmed (aligned with direction) BOS or CHoCH confirmed in trade direction Session = London or New York (kill zones preferred) Macro risk = low or medium Spread within threshold No news block active Daily loss below 80% of limit Consecutive losses < 3

File Structure

metals-desk-os/ ├── SKILL.md # This file ├── index.js # Main orchestrator & entry point ├── package.json # npm dependencies ├── skill.json # OpenClaw registration manifest ├── manifest.json # Runtime configuration ├── core/ # 8 trading engines │ ├── structure-engine.js # HH/HL/LH/LL, BOS, CHoCH, FVG, OB │ ├── liquidity-engine.js # Pools, sweeps, equal levels │ ├── bias-engine.js # MTF bias, conviction scoring │ ├── macro-engine.js # DXY, yields, sentiment, news │ ├── volatility-engine.js # ATR, regime, spikes │ ├── risk-engine.js # Position sizing, halts │ ├── execution-engine.js # Signal generation │ └── performance-engine.js # Metrics tracking ├── automation/ # System automation layer │ ├── event-bus.js # Central event system │ ├── price-feed.js # MT5/MetaAPI price data │ ├── session-engine.js # London/NY/Asian sessions │ ├── scheduler.js # Cron tasks │ └── news-monitor.js # Economic calendar ├── broker/ # MT5 broker integration │ ├── mt5-connector.js # Order execution via MetaAPI │ ├── risk-guard.js # Position monitoring & trailing │ └── order-manager.js # Order lifecycle management ├── dashboard/ # Real-time monitoring │ ├── websocket-feed.js # WebSocket broadcaster (port 3078) │ ├── desk-dashboard.json # Widget layout config │ └── metrics.json # Metrics template ├── alerts/ # Notification channels │ ├── whatsapp-alert.js # WhatsApp Business API │ ├── telegram-alert.js # Telegram Bot │ └── risk-alert.js # Centralized dispatcher ├── data/ # Persistent state files │ ├── state.json # System mode & connections │ ├── trade-log.json # Trade history │ ├── performance.json # Performance metrics │ └── bias-memory.json # Bias state persistence └── prompts/ # AI agent prompts ├── system.txt # Main system prompt ├── intraday.txt # Intraday trading protocol ├── swing.txt # Swing trading protocol └── execution.txt # Execution protocol

Step 1: Deploy to OpenClaw

cp -r metals-desk-os/ ~/.openclaw/agents/trader/agent/metals-desk-os/ cd ~/.openclaw/agents/trader/agent/metals-desk-os/

Step 2: Install Dependencies

npm install

Step 3: Configure Environment

Create a .env file in the skill root with the following variables: # MetaAPI / MT5 Connection METAAPI_TOKEN=your_metaapi_token_here MT5_ACCOUNT_ID=your_mt5_account_id_here # WhatsApp Business API (optional) WHATSAPP_API_URL=https://graph.facebook.com/v18.0/YOUR_PHONE_NUMBER_ID/messages WHATSAPP_TOKEN=your_whatsapp_token_here WHATSAPP_PHONE=your_phone_number_with_country_code # Telegram Bot (optional) TELEGRAM_BOT_TOKEN=your_telegram_bot_token_here TELEGRAM_CHAT_ID=your_telegram_chat_id_here # News API (optional) NEWS_API_KEY= # AI Keys (optional, for enhanced analysis) OPENROUTER_API_KEY= ANTHROPIC_API_KEY= MetaAPI: Sign up at https://metaapi.cloud and connect your Fusion Markets MT5 account. Telegram: Create a bot via @BotFather, get chat ID from @userinfobot. WhatsApp: Configure via Meta Business API dashboard.

Step 4: Set Initial Mode

Edit data/state.json and set "mode": 1 (Advisory) to start safely.

Step 5: Start

# Direct node index.js # Or with PM2 for production pm2 start index.js --name metals-desk-os pm2 save pm2 startup

Dashboard

Connect any WebSocket client to ws://localhost:3078 to receive real-time JSON payloads containing: Live prices and spread statistics HTF and intraday bias with conviction scores Active positions with live P&L and R:R Liquidity map (equal highs/lows, sweep markers) Macro panel (DXY, yields, news countdown) Performance metrics (win rate, expectancy, drawdown, Sharpe) Risk status (halt state, daily P&L, exposure) Event log (all system events)

Alert Formats

Trade opened: TRADE OPENED Pair: XAUUSD Direction: Long Entry: 5024.50 SL: 5010.00 TP1: 5046.25 Risk: 1.5% Session: London Conviction: 82/100 Risk halt: RISK HALT ACTIVATED Reason: 3 consecutive losses Trading paused for session

Key Events

The Event Bus broadcasts these events that external systems can subscribe to: price.update — New price tick with candle data structure.shift — BOS or CHoCH detected liquidity.sweep — Liquidity pool swept bias.update — Bias recalculated bias.flip — HTF bias direction changed execution.signal — Valid trade signal generated risk.halt / risk.resume — Trading halted or resumed order.filled / order.closed — Order lifecycle events performance.update — New trade recorded to performance macro.news.block — News event blocking execution

Validation Checklist

Before moving beyond Mode 1: Price feed produces ticks (live or simulated) Structure engine detects swing points and BOS/CHoCH Liquidity engine identifies pools and sweeps Bias engine produces conviction scores > 0 Session engine correctly identifies current session Risk engine validates and rejects test scenarios Execution engine generates signals with full entry plans Alerts arrive on configured channels WebSocket feed broadcasts state updates Once all pass, move to Mode 2 (Semi-Auto) to test position management, then Mode 3 (Full-Auto) for live execution.

Category context

Workflow acceleration for inboxes, docs, calendars, planning, and execution loops.

Source: Tencent SkillHub

Largest current source with strong distribution and engagement signals.

Package contents

Included in package

3 Config2 Docs1 Scripts

SKILL.md Primary doc
README.md Docs
index.js Scripts
manifest.json Config
package.json Config
skill.json Config