菜单
Use when running MetaTrader 5 Strategy Tester backtests from the terminal in this workspace. Ask the user for the test configuration field by field before launching the test, using the current project defaults unless the user changes them.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | run-backtests |
| description | Use when running MetaTrader 5 Strategy Tester backtests from the terminal in this workspace. Ask the user for the test configuration field by field before launching the test, using the current project defaults unless the user changes them. |
Use this skill when the user wants to run a MetaTrader 5 backtest from the terminal.
Run the main MetaTrader 5 installation with a tester .ini file:
Start-Process -FilePath 'C:\Program Files\MetaTrader 5\terminal64.exe' -ArgumentList '/config:C:\Users\<user>\AppData\Roaming\MetaQuotes\Terminal\<terminal-id>\config\codex-fvgtrader-gbpusd-lastmonth-v2.ini' -Wait
Use that command pattern for backtests in this workspace.
Before running the test, ask the user for the configuration field by field. Do not assume the final setup without confirming each field first. When asking for a field, use JSON Schema style notation like this:
{
"type": "object",
"properties": {
"risk_level": {
"type": "string",
"description": "Select your preferred risk level",
"enum": ["low", "medium", "high"]
}
},
"required": ["risk_level"]
}
Use the same notation for backtest questions. Add enum options whenever the field has a bounded set of valid choices.
Ask in this order:
Use these question shapes:
{
"type": "object",
"properties": {
"expert": {
"type": "string",
"description": "Select the Expert Advisor or strategy file to run",
"enum": ["Experts\\\\codex\\\\FVGTrader.ex5"]
}
},
"required": ["expert"]
}
{
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "Select the symbol to backtest",
"enum": ["GBPUSD"]
}
},
"required": ["symbol"]
}
{
"type": "object",
"properties": {
"timeframe": {
"type": "string",
"description": "Select the chart timeframe",
"enum": ["M1", "M5", "M15", "M30", "H1", "H4", "D1"]
}
},
"required": ["timeframe"]
}
{
"type": "object",
"properties": {
"date_range": {
"type": "string",
"description": "Select the date range preset or provide a custom range",
"enum": ["last_week", "last_month", "last_3_months", "custom"]
}
},
"required": ["date_range"]
}
{
"type": "object",
"properties": {
"deposit": {
"type": "number",
"description": "Enter the starting deposit amount"
}
},
"required": ["deposit"]
}
{
"type": "object",
"properties": {
"currency": {
"type": "string",
"description": "Select the deposit currency",
"enum": ["USD", "EUR", "GBP"]
}
},
"required": ["currency"]
}
{
"type": "object",
"properties": {
"leverage": {
"type": "string",
"description": "Select the leverage",
"enum": ["1:30", "1:50", "1:100", "1:200", "1:500"]
}
},
"required": ["leverage"]
}
{
"type": "object",
"properties": {
"tick_model": {
"type": "string",
"description": "Select the tick generation model",
"enum": ["open_prices", "control_points", "every_tick", "real_ticks"]
}
},
"required": ["tick_model"]
}
{
"type": "object",
"properties": {
"optimization": {
"type": "string",
"description": "Select whether optimization is enabled",
"enum": ["off", "on"]
}
},
"required": ["optimization"]
}
{
"type": "object",
"properties": {
"visualization": {
"type": "string",
"description": "Select whether visualization is enabled",
"enum": ["off", "on"]
}
},
"required": ["visualization"]
}
Use these values as defaults unless the user changes them:
Experts\codex\FVGTrader.ex5GBPUSDM15100000USD1:100Create or update a tester .ini with the confirmed values.
Use this structure:
[Tester]
Expert=<ask_user_expert>
Symbol=GBPUSD
Period=M15
Model=4
Optimization=0
FromDate=2026.02.28
ToDate=2026.03.28
ForwardMode=0
Deposit=100000
Currency=USD
Leverage=1:100
ExecutionMode=0
Visual=0
Report=<ask_user_report>
ReplaceReport=1
ShutdownTerminal=1
UseLocal=1
UseRemote=0
UseCloud=0
After launching the test:
If the terminal opens but the test does not run, do not invent results. State clearly that the launch failed and inspect the tester log before trying again.
Orquestar cuentas MetaTrader 5 del workspace actual usando MQL5\Scripts\interface.py, archivos accounts/account_id/info.md, accounts/account_id/bots.ini y notificaciones Telegram. Use when Codex is asked to orchestrate accounts, coordinate account-specific bots, prepare or inspect bots.ini for an MT5 account, or notify the configured Telegram chat/channel about account orchestration status.
Use the local MetaTrader 5 Python trading CLI at MQL5\Scripts\interface.py. Use when Codex needs to explain, run, validate, or troubleshoot command-line trading operations such as opening market or pending orders, setting or editing SL/TP, closing positions, canceling pending orders, listing opened trades or pending orders, reading recent trade history, or checking account and symbol details.
Analyze market regime and session structure in this MQL5 workspace using reusable CSV exports from an MQL5 script. Use when Codex needs to classify a market as Tendencial or Lateral with moving average and ATR, export per-session data to Terminal Common Files for M15, H1, and D1, and then read those CSV files directly to summarize insights and recommendations by session without recreating scripts that already exist.
Use when compiling MQL5 experts, indicators, scripts, or include-dependent code in this workspace from the terminal. Follow the local MetaEditor command pattern and always inspect the compilation log after running it.
Run MetaTrader 5 parameter optimizations in this workspace and summarize real results from exported optimization reports. Use when Codex needs to optimize EA inputs such as SL, TP, RSI values, or other inputs for experts under MQL5\Experts, by generating a tester .ini with [TesterInputs], launching MT5 from the terminal, and reading the resulting XML ranking.
Work with Forge-hosted Git repositories from this workspace, including login, staged commits, and push workflows. Use when Codex needs to prepare or send commits to Forge or Forgejo remotes such as forge.mql5.io, refresh credentials, inspect Git status, or write commit messages that follow Conventional Commits like feat(rsi): summary.