[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77SFWRGM2DMNDP3AVVD684W":3,"skill-same:01M77SFWRGM2DMNDP3AVVD684W":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M77SFWRGM2DMNDP3AVVD684W","qmt",null,"QMT迅投量化交易终端 - 内置Python策略开发、回测引擎和实盘交易，支持中国证券市场全品种。","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fq\u002Fqmt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: qmt\ndescription: QMT迅投量化交易终端 - 内置Python策略开发、回测引擎和实盘交易，支持中国证券市场全品种。\nversion: 1.2.0\nhomepage: http:\u002F\u002Fdict.thinktrader.net\u002Ffreshman\u002Frookie.html\nmetadata: {\"clawdbot\":{\"emoji\":\"🖥️\",\"requires\":{\"bins\":[\"python3\"]}}}\n---\n\n# QMT（迅投量化交易终端）\n\n[QMT](http:\u002F\u002Fwww.thinktrader.net)（Quant Market Trading）是迅投科技开发的专业量化交易平台。提供完整的桌面客户端，内置Python策略开发、回测引擎和实盘交易功能，支持中国证券市场全品种。\n\n> ⚠️ **需要通过券商开通QMT权限**。QMT仅在Windows上运行。可通过国金、华鑫、中泰、东方财富等券商获取。\n\n## 两种运行模式\n\n| 模式 | 说明 |\n|---|---|\n| **QMT（完整版）** | 完整桌面GUI，内置Python编辑器、图表和回测引擎 |\n| **miniQMT** | 极简模式 — 通过外部Python使用xtquant SDK（参见 `miniqmt` skill） |\n\n## 内置Python策略框架\n\nQMT提供事件驱动策略框架，内置Python运行时（类似聚宽\u002F米筐）。\n\n### 策略生命周期\n\n```python\ndef init(ContextInfo):\n    \"\"\"初始化函数 - 策略启动时调用一次，用于设置股票池和参数\"\"\"\n    ContextInfo.set_universe(['000001.SZ', '600519.SH'])\n\ndef handlebar(ContextInfo):\n    \"\"\"K线处理函数 - 每根K线触发一次（tick\u002F1m\u002F5m\u002F1d等），在此编写交易逻辑\"\"\"\n    close = ContextInfo.get_market_data(['close'], stock_code='000001.SZ', period='1d', count=20)\n    # 在此编写交易逻辑\n\ndef stop(ContextInfo):\n    \"\"\"停止函数 - 策略停止时调用\"\"\"\n    pass\n```\n\n### 获取行情数据（内置）\n\n```python\ndef handlebar(ContextInfo):\n    # 获取最近20根K线的收盘价\n    data = ContextInfo.get_market_data(\n        ['open', 'high', 'low', 'close', 'volume'],\n        stock_code='000001.SZ',\n        period='1d',\n        count=20\n    )\n\n    # 获取历史数据\n    history = ContextInfo.get_history_data(\n        20, '1d', 'close', stock_code='000001.SZ'\n    )\n\n    # 获取板块股票列表\n    stocks = ContextInfo.get_stock_list_in_sector('沪深A股')\n\n    # 获取财务数据\n    fin = ContextInfo.get_financial_data('000001.SZ')\n```\n\n### 下单（内置）\n\n```python\ndef handlebar(ContextInfo):\n    # 限价买入100股，价格11.50\n    order_shares('000001.SZ', 100, 'fix', 11.50, ContextInfo)\n\n    # 限价卖出100股，价格12.00\n    order_shares('000001.SZ', -100, 'fix', 12.00, ContextInfo)\n\n    # 按目标金额买入（10万元）\n    order_target_value('000001.SZ', 100000, 'fix', 11.50, ContextInfo)\n\n    # 撤单\n    cancel('order_id', ContextInfo)\n```\n\n### 查询持仓与账户\n\n```python\ndef handlebar(ContextInfo):\n    # 获取持仓信息\n    positions = get_trade_detail_data('your_account', 'stock', 'position')\n    for pos in positions:\n        print(pos.m_strInstrumentID, pos.m_nVolume, pos.m_dMarketValue)\n\n    # 获取委托信息\n    orders = get_trade_detail_data('your_account', 'stock', 'order')\n\n    # 获取账户资产信息\n    account = get_trade_detail_data('your_account', 'stock', 'account')\n```\n\n## 回测\n\nQMT内置回测引擎：\n\n1. 在内置Python编辑器中编写策略\n2. 设置回测参数（日期范围、初始资金、手续费、滑点）\n3. 点击\"运行回测\"\n4. 查看结果：资金曲线、最大回撤、夏普比率、交易记录\n\n### 回测参数设置\n\n```python\ndef init(ContextInfo):\n    ContextInfo.capital = 1000000          # 初始资金\n    ContextInfo.set_commission(0.0003)     # 手续费率\n    ContextInfo.set_slippage(0.01)         # 滑点\n    ContextInfo.set_benchmark('000300.SH') # 基准指数\n```\n\n## 完整示例：双均线策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '000001.SZ'\n    ContextInfo.set_universe([ContextInfo.stock])\n    ContextInfo.fast = 5    # 快速均线周期\n    ContextInfo.slow = 20   # 慢速均线周期\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    # 获取最近slow+1根K线的收盘价\n    closes = ContextInfo.get_history_data(ContextInfo.slow + 1, '1d', 'close', stock_code=stock)\n\n    if len(closes) \u003C ContextInfo.slow:\n        return  # 数据不足，跳过\n\n    # 计算当前和前一根K线的快慢均线值\n    ma_fast = np.mean(closes[-ContextInfo.fast:])\n    ma_slow = np.mean(closes[-ContextInfo.slow:])\n    prev_fast = np.mean(closes[-ContextInfo.fast-1:-1])\n    prev_slow = np.mean(closes[-ContextInfo.slow-1:-1])\n\n    # 查询当前持仓\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = any(p.m_strInstrumentID == stock and p.m_nVolume > 0 for p in positions)\n\n    # 金叉信号：快速均线上穿慢速均线，买入\n    if prev_fast \u003C= prev_slow and ma_fast > ma_slow and not holding:\n        order_shares(stock, 1000, 'fix', closes[-1], ContextInfo)\n\n    # 死叉信号：快速均线下穿慢速均线，卖出\n    elif prev_fast >= prev_slow and ma_fast \u003C ma_slow and holding:\n        order_shares(stock, -1000, 'fix', closes[-1], ContextInfo)\n```\n\n\n## 数据覆盖范围\n\n| 类别 | 内容 |\n|---|---|\n| **股票** | A股（沪、深、北交所）、港股通 |\n| **指数** | 所有主要指数 |\n| **期货** | 中金所、上期所、大商所、郑商所、能源中心、广期所 |\n| **期权** | ETF期权、股票期权、商品期权 |\n| **ETF** | 所有交易所交易基金 |\n| **债券** | 可转债、国债 |\n| **周期** | Tick、1分钟、5分钟、15分钟、30分钟、1小时、日、周、月 |\n| **Level 2** | 逐笔委托、逐笔成交（取决于券商权限） |\n| **财务** | 资产负债表、利润表、现金流量表、关键指标 |\n\n## QMT vs miniQMT vs Ptrade 对比\n\n| 特性 | QMT | miniQMT | Ptrade |\n|---|---|---|---|\n| **厂商** | 迅投科技 | 迅投科技 | 恒生电子 |\n| **Python** | 内置（版本受限） | 外部（任意版本） | 内置（版本受限） |\n| **界面** | 完整GUI | 极简 | 完整（网页端） |\n| **回测** | 内置 | 需自行实现 | 内置 |\n| **部署** | 本地 | 本地 | 券商服务器（云端） |\n| **外网访问** | 支持 | 支持 | 不支持（仅内网） |\n\n## 使用技巧\n\n- QMT仅在**Windows**上运行。\n- 内置Python版本由QMT固定，无法安装任意pip包。\n- 如需不受限的Python环境，使用**miniQMT**模式配合`xtquant` SDK。\n- 策略文件存储在QMT安装目录中。\n- 文档：http:\u002F\u002Fdict.thinktrader.net\u002Ffreshman\u002Frookie.html\n- 也支持VBA接口用于Excel集成。\n\n---\n\n## 进阶示例\n\n### 多股票轮动策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    # 设置股票池：银行龙头股\n    ContextInfo.stock_pool = ['601398.SH', '601939.SH', '601288.SH', '600036.SH', '601166.SH']\n    ContextInfo.set_universe(ContextInfo.stock_pool)\n    ContextInfo.hold_num = 2  # 最多持有2只股票\n\ndef handlebar(ContextInfo):\n    # 计算每只股票的20日收益率\n    momentum = {}\n    for stock in ContextInfo.stock_pool:\n        closes = ContextInfo.get_history_data(21, '1d', 'close', stock_code=stock)\n        if len(closes) >= 21:\n            ret = (closes[-1] - closes[0]) \u002F closes[0]  # 20日收益率\n            momentum[stock] = ret\n\n    # 按动量排序，选择前N只股票\n    sorted_stocks = sorted(momentum.items(), key=lambda x: x[1], reverse=True)\n    target_stocks = [s[0] for s in sorted_stocks[:ContextInfo.hold_num]]\n\n    # 获取当前持仓\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = {p.m_strInstrumentID: p.m_nVolume for p in positions if p.m_nVolume > 0}\n\n    # 卖出不在目标列表中的股票\n    for stock, vol in holding.items():\n        if stock not in target_stocks:\n            closes = ContextInfo.get_history_data(1, '1d', 'close', stock_code=stock)\n            if len(closes) > 0:\n                order_shares(stock, -vol, 'fix', closes[-1], ContextInfo)\n\n    # 买入目标股票\n    account = get_trade_detail_data(ContextInfo.accID, 'stock', 'account')\n    if account:\n        cash = account[0].m_dAvailable\n        per_stock_cash = cash \u002F ContextInfo.hold_num  # 等权分配\n        for stock in target_stocks:\n            if stock not in holding:\n                closes = ContextInfo.get_history_data(1, '1d', 'close', stock_code=stock)\n                if len(closes) > 0 and closes[-1] > 0:\n                    vol = int(per_stock_cash \u002F closes[-1] \u002F 100) * 100  # 向下取整到整手\n                    if vol >= 100:\n                        order_shares(stock, vol, 'fix', closes[-1], ContextInfo)\n```\n\n\n### RSI策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '000001.SZ'\n    ContextInfo.set_universe([ContextInfo.stock])\n    ContextInfo.rsi_period = 14     # RSI周期\n    ContextInfo.oversold = 30       # 超卖阈值\n    ContextInfo.overbought = 70     # 超买阈值\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    closes = ContextInfo.get_history_data(ContextInfo.rsi_period + 2, '1d', 'close', stock_code=stock)\n\n    if len(closes) \u003C ContextInfo.rsi_period + 1:\n        return\n\n    # 计算RSI\n    deltas = np.diff(closes)\n    gains = np.where(deltas > 0, deltas, 0)\n    losses = np.where(deltas \u003C 0, -deltas, 0)\n    avg_gain = np.mean(gains[-ContextInfo.rsi_period:])\n    avg_loss = np.mean(losses[-ContextInfo.rsi_period:])\n\n    if avg_loss == 0:\n        rsi = 100\n    else:\n        rs = avg_gain \u002F avg_loss\n        rsi = 100 - (100 \u002F (1 + rs))\n\n    # 查询持仓\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = any(p.m_strInstrumentID == stock and p.m_nVolume > 0 for p in positions)\n\n    # RSI超卖 — 买入\n    if rsi \u003C ContextInfo.oversold and not holding:\n        order_shares(stock, 1000, 'fix', closes[-1], ContextInfo)\n\n    # RSI超买 — 卖出\n    elif rsi > ContextInfo.overbought and holding:\n        order_shares(stock, -1000, 'fix', closes[-1], ContextInfo)\n```\n\n### 布林带策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '600519.SH'\n    ContextInfo.set_universe([ContextInfo.stock])\n    ContextInfo.boll_period = 20    # 布林带周期\n    ContextInfo.boll_std = 2        # 标准差倍数\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    closes = ContextInfo.get_history_data(ContextInfo.boll_period + 1, '1d', 'close', stock_code=stock)\n\n    if len(closes) \u003C ContextInfo.boll_period:\n        return\n\n    # 计算布林带\n    recent = closes[-ContextInfo.boll_period:]\n    mid = np.mean(recent)                          # 中轨\n    std = np.std(recent)                           # 标准差\n    upper = mid + ContextInfo.boll_std * std       # 上轨\n    lower = mid - ContextInfo.boll_std * std       # 下轨\n    price = closes[-1]                             # 当前价格\n\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = any(p.m_strInstrumentID == stock and p.m_nVolume > 0 for p in positions)\n\n    # 价格触及下轨 — 买入\n    if price \u003C= lower and not holding:\n        order_shares(stock, 1000, 'fix', price, ContextInfo)\n\n    # 价格触及上轨 — 卖出\n    elif price >= upper and holding:\n        order_shares(stock, -1000, 'fix', price, ContextInfo)\n```\n\n## 定时任务\n\n```python\ndef init(ContextInfo):\n    ContextInfo.stock = '000001.SZ'\n    ContextInfo.set_universe([ContextInfo.stock])\n\ndef handlebar(ContextInfo):\n    import datetime\n    now = ContextInfo.get_bar_timetag(ContextInfo.barpos)\n    dt = datetime.datetime.fromtimestamp(now \u002F 1000)\n    # 仅在每変14:50执行调仓逻辑\n    if dt.hour == 14 and dt.minute == 50:\n        pass  # 执行调仓\n```\n\n## 常见错误处理\n\n| 错误 | 原因 | 解决方法 |\n|------|------|----------|\n| 账户未登录 | QMT未连接券商 | 检查QMT登录状态，确认券商账户已连接 |\n| 委托失败 | 资金不足或超出涨跌停 | 检查可用资金和委托价格 |\n| 数据为空 | 股票代码错误或停牌 | 校验代码格式（如`000001.SZ`），检查是否停牌 |\n| Python版本不兼容 | 内置Python版本受限 | 改用miniQMT模式 |\n| 策略运行缓慢 | 数据量过大 | 减少`get_history_data`的count参数 |\n\n## 内置函数参考\n\n### 行情数据函数\n\n| 函数 | 说明 | 返回值 |\n|------|------|--------|\n| `ContextInfo.get_market_data(fields, stock_code, period, count)` | 获取K线数据 | dict\u002FDataFrame |\n| `ContextInfo.get_history_data(count, period, field, stock_code)` | 获取历史数据序列 | list |\n| `ContextInfo.get_stock_list_in_sector(sector)` | 获取板块成分股 | list |\n| `ContextInfo.get_financial_data(stock_code)` | 获取财务数据 | dict |\n| `ContextInfo.get_instrument_detail(stock_code)` | 获取合约详情 | dict |\n| `ContextInfo.get_full_tick(stock_list)` | 获取全推行情快照 | dict |\n\n### 交易函数\n\n| 函数 | 说明 |\n|------|------|\n| `order_shares(code, volume, style, price, ContextInfo)` | 按股数下单（正买负卖） |\n| `order_target_value(code, value, style, price, ContextInfo)` | 按目标市值下单 |\n| `order_lots(code, lots, style, price, ContextInfo)` | 按手数下单 |\n| `order_percent(code, percent, style, price, ContextInfo)` | 按组合比例下单 |\n| `cancel(order_id, ContextInfo)` | 撤单 |\n| `get_trade_detail_data(account, market, data_type)` | 查询交易数据 |\n\n### 交易数据类型\n\n| data_type | 说明 | 常用字段 |\n|-----------|------|----------|\n| `'position'` | 持仓 | `m_strInstrumentID`（代码）, `m_nVolume`（数量）, `m_dMarketValue`（市值） |\n| `'order'` | 委托 | `m_strOrderSysID`（委托号）, `m_nVolumeTraded`（成交量）, `m_dLimitPrice`（委托价） |\n| `'deal'` | 成交 | `m_strTradeID`（成交号）, `m_dPrice`（成交价）, `m_nVolume`（成交量） |\n| `'account'` | 账户 | `m_dAvailable`（可用资金）, `m_dBalance`（总资产）, `m_dMarketValue`（持仓市值） |\n\n## 进阶示例：MACD策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '600519.SH'\n    ContextInfo.set_universe([ContextInfo.stock])\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    closes = ContextInfo.get_history_data(60, '1d', 'close', stock_code=stock)\n    if len(closes) \u003C 35:\n        return\n    closes = np.array(closes, dtype=float)\n\n    def ema(data, period):\n        result = np.zeros_like(data)\n        result[0] = data[0]\n        k = 2 \u002F (period + 1)\n        for i in range(1, len(data)):\n            result[i] = data[i] * k + result[i-1] * (1 - k)\n        return result\n\n    ema12 = ema(closes, 12)\n    ema26 = ema(closes, 26)\n    dif = ema12 - ema26\n    dea = ema(dif, 9)\n\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = any(p.m_strInstrumentID == stock and p.m_nVolume > 0 for p in positions)\n\n    # 金叉：DIF上穿DEA\n    if dif[-2] \u003C= dea[-2] and dif[-1] > dea[-1] and not holding:\n        order_shares(stock, 1000, 'fix', closes[-1], ContextInfo)\n    # 死叉：DIF下穿DEA\n    elif dif[-2] >= dea[-2] and dif[-1] \u003C dea[-1] and holding:\n        order_shares(stock, -1000, 'fix', closes[-1], ContextInfo)\n```\n\n## 进阶示例：止盈止损策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '000001.SZ'\n    ContextInfo.set_universe([ContextInfo.stock])\n    ContextInfo.entry_price = 0\n    ContextInfo.stop_loss = 0.05      # 止损5%\n    ContextInfo.take_profit = 0.10    # 止盈10%\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    closes = ContextInfo.get_history_data(21, '1d', 'close', stock_code=stock)\n    if len(closes) \u003C 21:\n        return\n    price = closes[-1]\n    ma20 = np.mean(closes[-20:])\n\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    pos = None\n    for p in positions:\n        if p.m_strInstrumentID == stock and p.m_nVolume > 0:\n            pos = p\n            break\n\n    if pos is None:\n        if price > ma20:\n            order_shares(stock, 1000, 'fix', price, ContextInfo)\n            ContextInfo.entry_price = price\n    else:\n        if ContextInfo.entry_price > 0:\n            pnl = (price - ContextInfo.entry_price) \u002F ContextInfo.entry_price\n            if pnl \u003C= -ContextInfo.stop_loss:\n                order_shares(stock, -pos.m_nVolume, 'fix', price, ContextInfo)\n                ContextInfo.entry_price = 0\n            elif pnl >= ContextInfo.take_profit:\n                order_shares(stock, -pos.m_nVolume, 'fix', price, ContextInfo)\n                ContextInfo.entry_price = 0\n```\n\n---\n\n---\n\n## 🤖 AI Agent 高阶使用指南\n\n对于 AI Agent，在使用该量化\u002F数据工具时应遵循以下高阶策略和最佳实践，以确保任务的高效完成：\n\n### 1. 数据校验与错误处理\n在获取数据或执行操作后，AI 应当主动检查返回的结果格式是否符合预期，以及是否存在缺失值（NaN）或空数据。\n* **示例策略**：在通过 API 获取数据框（DataFrame）后，使用 `if df.empty:` 进行校验；捕获 `Exception` 以防网络或接口错误导致进程崩溃。\n\n### 2. 多步组合分析\nAI 经常需要进行宏观经济分析或跨市场对比。应善于将当前接口与其他数据源或工具组合使用。\n* **示例策略**：先获取板块或指数的宏观数据，再筛选成分股，最后对具体标的进行深入的财务或技术面分析，形成完整的决策链条。\n\n### 3. 构建动态监控与日志\n对于交易和策略类任务，AI 可以定期拉取数据并建立监控机制。\n* **示例策略**：使用循环或定时任务检查特定标的的异动（如涨跌停、放量），并在发现满足条件的信号时输出结构化日志或触发预警。\n\n---\n\n## 社区与支持\n\n由 **大佬量化** 维护 — 量化交易教学与策略研发团队。\n\n微信客服: **bossquant1** · [Bilibili](https:\u002F\u002Fspace.bilibili.com\u002F48693330) · 搜索 **大佬量化** — 微信公众号 \u002F Bilibili \u002F 抖音\n","# QMT（迅投量化交易终端）\n\n[QMT](http:\u002F\u002Fwww.thinktrader.net)（Quant Market Trading）是迅投科技开发的专业量化交易平台。提供完整的桌面客户端，内置Python策略开发、回测引擎和实盘交易功能，支持中国证券市场全品种。\n\n> ⚠️ **需要通过券商开通QMT权限**。QMT仅在Windows上运行。可通过国金、华鑫、中泰、东方财富等券商获取。\n\n## 两种运行模式\n\n| 模式 | 说明 |\n|---|---|\n| **QMT（完整版）** | 完整桌面GUI，内置Python编辑器、图表和回测引擎 |\n| **miniQMT** | 极简模式 — 通过外部Python使用xtquant SDK（参见 `miniqmt` skill） |\n\n## 内置Python策略框架\n\nQMT提供事件驱动策略框架，内置Python运行时（类似聚宽\u002F米筐）。\n\n### 策略生命周期\n\n```python\ndef init(ContextInfo):\n    \"\"\"初始化函数 - 策略启动时调用一次，用于设置股票池和参数\"\"\"\n    ContextInfo.set_universe(['000001.SZ', '600519.SH'])\n\ndef handlebar(ContextInfo):\n    \"\"\"K线处理函数 - 每根K线触发一次（tick\u002F1m\u002F5m\u002F1d等），在此编写交易逻辑\"\"\"\n    close = ContextInfo.get_market_data(['close'], stock_code='000001.SZ', period='1d', count=20)\n    # 在此编写交易逻辑\n\ndef stop(ContextInfo):\n    \"\"\"停止函数 - 策略停止时调用\"\"\"\n    pass\n```\n\n### 获取行情数据（内置）\n\n```python\ndef handlebar(ContextInfo):\n    # 获取最近20根K线的收盘价\n    data = ContextInfo.get_market_data(\n        ['open', 'high', 'low', 'close', 'volume'],\n        stock_code='000001.SZ',\n        period='1d',\n        count=20\n    )\n\n    # 获取历史数据\n    history = ContextInfo.get_history_data(\n        20, '1d', 'close', stock_code='000001.SZ'\n    )\n\n    # 获取板块股票列表\n    stocks = ContextInfo.get_stock_list_in_sector('沪深A股')\n\n    # 获取财务数据\n    fin = ContextInfo.get_financial_data('000001.SZ')\n```\n\n### 下单（内置）\n\n```python\ndef handlebar(ContextInfo):\n    # 限价买入100股，价格11.50\n    order_shares('000001.SZ', 100, 'fix', 11.50, ContextInfo)\n\n    # 限价卖出100股，价格12.00\n    order_shares('000001.SZ', -100, 'fix', 12.00, ContextInfo)\n\n    # 按目标金额买入（10万元）\n    order_target_value('000001.SZ', 100000, 'fix', 11.50, ContextInfo)\n\n    # 撤单\n    cancel('order_id', ContextInfo)\n```\n\n### 查询持仓与账户\n\n```python\ndef handlebar(ContextInfo):\n    # 获取持仓信息\n    positions = get_trade_detail_data('your_account', 'stock', 'position')\n    for pos in positions:\n        print(pos.m_strInstrumentID, pos.m_nVolume, pos.m_dMarketValue)\n\n    # 获取委托信息\n    orders = get_trade_detail_data('your_account', 'stock', 'order')\n\n    # 获取账户资产信息\n    account = get_trade_detail_data('your_account', 'stock', 'account')\n```\n\n## 回测\n\nQMT内置回测引擎：\n\n1. 在内置Python编辑器中编写策略\n2. 设置回测参数（日期范围、初始资金、手续费、滑点）\n3. 点击\"运行回测\"\n4. 查看结果：资金曲线、最大回撤、夏普比率、交易记录\n\n### 回测参数设置\n\n```python\ndef init(ContextInfo):\n    ContextInfo.capital = 1000000          # 初始资金\n    ContextInfo.set_commission(0.0003)     # 手续费率\n    ContextInfo.set_slippage(0.01)         # 滑点\n    ContextInfo.set_benchmark('000300.SH') # 基准指数\n```\n\n## 完整示例：双均线策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '000001.SZ'\n    ContextInfo.set_universe([ContextInfo.stock])\n    ContextInfo.fast = 5    # 快速均线周期\n    ContextInfo.slow = 20   # 慢速均线周期\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    # 获取最近slow+1根K线的收盘价\n    closes = ContextInfo.get_history_data(ContextInfo.slow + 1, '1d', 'close', stock_code=stock)\n\n    if len(closes) \u003C ContextInfo.slow:\n        return  # 数据不足，跳过\n\n    # 计算当前和前一根K线的快慢均线值\n    ma_fast = np.mean(closes[-ContextInfo.fast:])\n    ma_slow = np.mean(closes[-ContextInfo.slow:])\n    prev_fast = np.mean(closes[-ContextInfo.fast-1:-1])\n    prev_slow = np.mean(closes[-ContextInfo.slow-1:-1])\n\n    # 查询当前持仓\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = any(p.m_strInstrumentID == stock and p.m_nVolume > 0 for p in positions)\n\n    # 金叉信号：快速均线上穿慢速均线，买入\n    if prev_fast \u003C= prev_slow and ma_fast > ma_slow and not holding:\n        order_shares(stock, 1000, 'fix', closes[-1], ContextInfo)\n\n    # 死叉信号：快速均线下穿慢速均线，卖出\n    elif prev_fast >= prev_slow and ma_fast \u003C ma_slow and holding:\n        order_shares(stock, -1000, 'fix', closes[-1], ContextInfo)\n```\n\n\n## 数据覆盖范围\n\n| 类别 | 内容 |\n|---|---|\n| **股票** | A股（沪、深、北交所）、港股通 |\n| **指数** | 所有主要指数 |\n| **期货** | 中金所、上期所、大商所、郑商所、能源中心、广期所 |\n| **期权** | ETF期权、股票期权、商品期权 |\n| **ETF** | 所有交易所交易基金 |\n| **债券** | 可转债、国债 |\n| **周期** | Tick、1分钟、5分钟、15分钟、30分钟、1小时、日、周、月 |\n| **Level 2** | 逐笔委托、逐笔成交（取决于券商权限） |\n| **财务** | 资产负债表、利润表、现金流量表、关键指标 |\n\n## QMT vs miniQMT vs Ptrade 对比\n\n| 特性 | QMT | miniQMT | Ptrade |\n|---|---|---|---|\n| **厂商** | 迅投科技 | 迅投科技 | 恒生电子 |\n| **Python** | 内置（版本受限） | 外部（任意版本） | 内置（版本受限） |\n| **界面** | 完整GUI | 极简 | 完整（网页端） |\n| **回测** | 内置 | 需自行实现 | 内置 |\n| **部署** | 本地 | 本地 | 券商服务器（云端） |\n| **外网访问** | 支持 | 支持 | 不支持（仅内网） |\n\n## 使用技巧\n\n- QMT仅在**Windows**上运行。\n- 内置Python版本由QMT固定，无法安装任意pip包。\n- 如需不受限的Python环境，使用**miniQMT**模式配合`xtquant` SDK。\n- 策略文件存储在QMT安装目录中。\n- 文档：http:\u002F\u002Fdict.thinktrader.net\u002Ffreshman\u002Frookie.html\n- 也支持VBA接口用于Excel集成。\n\n---\n\n## 进阶示例\n\n### 多股票轮动策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    # 设置股票池：银行龙头股\n    ContextInfo.stock_pool = ['601398.SH', '601939.SH', '601288.SH', '600036.SH', '601166.SH']\n    ContextInfo.set_universe(ContextInfo.stock_pool)\n    ContextInfo.hold_num = 2  # 最多持有2只股票\n\ndef handlebar(ContextInfo):\n    # 计算每只股票的20日收益率\n    momentum = {}\n    for stock in ContextInfo.stock_pool:\n        closes = ContextInfo.get_history_data(21, '1d', 'close', stock_code=stock)\n        if len(closes) >= 21:\n            ret = (closes[-1] - closes[0]) \u002F closes[0]  # 20日收益率\n            momentum[stock] = ret\n\n    # 按动量排序，选择前N只股票\n    sorted_stocks = sorted(momentum.items(), key=lambda x: x[1], reverse=True)\n    target_stocks = [s[0] for s in sorted_stocks[:ContextInfo.hold_num]]\n\n    # 获取当前持仓\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = {p.m_strInstrumentID: p.m_nVolume for p in positions if p.m_nVolume > 0}\n\n    # 卖出不在目标列表中的股票\n    for stock, vol in holding.items():\n        if stock not in target_stocks:\n            closes = ContextInfo.get_history_data(1, '1d', 'close', stock_code=stock)\n            if len(closes) > 0:\n                order_shares(stock, -vol, 'fix', closes[-1], ContextInfo)\n\n    # 买入目标股票\n    account = get_trade_detail_data(ContextInfo.accID, 'stock', 'account')\n    if account:\n        cash = account[0].m_dAvailable\n        per_stock_cash = cash \u002F ContextInfo.hold_num  # 等权分配\n        for stock in target_stocks:\n            if stock not in holding:\n                closes = ContextInfo.get_history_data(1, '1d', 'close', stock_code=stock)\n                if len(closes) > 0 and closes[-1] > 0:\n                    vol = int(per_stock_cash \u002F closes[-1] \u002F 100) * 100  # 向下取整到整手\n                    if vol >= 100:\n                        order_shares(stock, vol, 'fix', closes[-1], ContextInfo)\n```\n\n\n### RSI策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '000001.SZ'\n    ContextInfo.set_universe([ContextInfo.stock])\n    ContextInfo.rsi_period = 14     # RSI周期\n    ContextInfo.oversold = 30       # 超卖阈值\n    ContextInfo.overbought = 70     # 超买阈值\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    closes = ContextInfo.get_history_data(ContextInfo.rsi_period + 2, '1d', 'close', stock_code=stock)\n\n    if len(closes) \u003C ContextInfo.rsi_period + 1:\n        return\n\n    # 计算RSI\n    deltas = np.diff(closes)\n    gains = np.where(deltas > 0, deltas, 0)\n    losses = np.where(deltas \u003C 0, -deltas, 0)\n    avg_gain = np.mean(gains[-ContextInfo.rsi_period:])\n    avg_loss = np.mean(losses[-ContextInfo.rsi_period:])\n\n    if avg_loss == 0:\n        rsi = 100\n    else:\n        rs = avg_gain \u002F avg_loss\n        rsi = 100 - (100 \u002F (1 + rs))\n\n    # 查询持仓\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = any(p.m_strInstrumentID == stock and p.m_nVolume > 0 for p in positions)\n\n    # RSI超卖 — 买入\n    if rsi \u003C ContextInfo.oversold and not holding:\n        order_shares(stock, 1000, 'fix', closes[-1], ContextInfo)\n\n    # RSI超买 — 卖出\n    elif rsi > ContextInfo.overbought and holding:\n        order_shares(stock, -1000, 'fix', closes[-1], ContextInfo)\n```\n\n### 布林带策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '600519.SH'\n    ContextInfo.set_universe([ContextInfo.stock])\n    ContextInfo.boll_period = 20    # 布林带周期\n    ContextInfo.boll_std = 2        # 标准差倍数\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    closes = ContextInfo.get_history_data(ContextInfo.boll_period + 1, '1d', 'close', stock_code=stock)\n\n    if len(closes) \u003C ContextInfo.boll_period:\n        return\n\n    # 计算布林带\n    recent = closes[-ContextInfo.boll_period:]\n    mid = np.mean(recent)                          # 中轨\n    std = np.std(recent)                           # 标准差\n    upper = mid + ContextInfo.boll_std * std       # 上轨\n    lower = mid - ContextInfo.boll_std * std       # 下轨\n    price = closes[-1]                             # 当前价格\n\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = any(p.m_strInstrumentID == stock and p.m_nVolume > 0 for p in positions)\n\n    # 价格触及下轨 — 买入\n    if price \u003C= lower and not holding:\n        order_shares(stock, 1000, 'fix', price, ContextInfo)\n\n    # 价格触及上轨 — 卖出\n    elif price >= upper and holding:\n        order_shares(stock, -1000, 'fix', price, ContextInfo)\n```\n\n## 定时任务\n\n```python\ndef init(ContextInfo):\n    ContextInfo.stock = '000001.SZ'\n    ContextInfo.set_universe([ContextInfo.stock])\n\ndef handlebar(ContextInfo):\n    import datetime\n    now = ContextInfo.get_bar_timetag(ContextInfo.barpos)\n    dt = datetime.datetime.fromtimestamp(now \u002F 1000)\n    # 仅在每変14:50执行调仓逻辑\n    if dt.hour == 14 and dt.minute == 50:\n        pass  # 执行调仓\n```\n\n## 常见错误处理\n\n| 错误 | 原因 | 解决方法 |\n|------|------|----------|\n| 账户未登录 | QMT未连接券商 | 检查QMT登录状态，确认券商账户已连接 |\n| 委托失败 | 资金不足或超出涨跌停 | 检查可用资金和委托价格 |\n| 数据为空 | 股票代码错误或停牌 | 校验代码格式（如`000001.SZ`），检查是否停牌 |\n| Python版本不兼容 | 内置Python版本受限 | 改用miniQMT模式 |\n| 策略运行缓慢 | 数据量过大 | 减少`get_history_data`的count参数 |\n\n## 内置函数参考\n\n### 行情数据函数\n\n| 函数 | 说明 | 返回值 |\n|------|------|--------|\n| `ContextInfo.get_market_data(fields, stock_code, period, count)` | 获取K线数据 | dict\u002FDataFrame |\n| `ContextInfo.get_history_data(count, period, field, stock_code)` | 获取历史数据序列 | list |\n| `ContextInfo.get_stock_list_in_sector(sector)` | 获取板块成分股 | list |\n| `ContextInfo.get_financial_data(stock_code)` | 获取财务数据 | dict |\n| `ContextInfo.get_instrument_detail(stock_code)` | 获取合约详情 | dict |\n| `ContextInfo.get_full_tick(stock_list)` | 获取全推行情快照 | dict |\n\n### 交易函数\n\n| 函数 | 说明 |\n|------|------|\n| `order_shares(code, volume, style, price, ContextInfo)` | 按股数下单（正买负卖） |\n| `order_target_value(code, value, style, price, ContextInfo)` | 按目标市值下单 |\n| `order_lots(code, lots, style, price, ContextInfo)` | 按手数下单 |\n| `order_percent(code, percent, style, price, ContextInfo)` | 按组合比例下单 |\n| `cancel(order_id, ContextInfo)` | 撤单 |\n| `get_trade_detail_data(account, market, data_type)` | 查询交易数据 |\n\n### 交易数据类型\n\n| data_type | 说明 | 常用字段 |\n|-----------|------|----------|\n| `'position'` | 持仓 | `m_strInstrumentID`（代码）, `m_nVolume`（数量）, `m_dMarketValue`（市值） |\n| `'order'` | 委托 | `m_strOrderSysID`（委托号）, `m_nVolumeTraded`（成交量）, `m_dLimitPrice`（委托价） |\n| `'deal'` | 成交 | `m_strTradeID`（成交号）, `m_dPrice`（成交价）, `m_nVolume`（成交量） |\n| `'account'` | 账户 | `m_dAvailable`（可用资金）, `m_dBalance`（总资产）, `m_dMarketValue`（持仓市值） |\n\n## 进阶示例：MACD策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '600519.SH'\n    ContextInfo.set_universe([ContextInfo.stock])\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    closes = ContextInfo.get_history_data(60, '1d', 'close', stock_code=stock)\n    if len(closes) \u003C 35:\n        return\n    closes = np.array(closes, dtype=float)\n\n    def ema(data, period):\n        result = np.zeros_like(data)\n        result[0] = data[0]\n        k = 2 \u002F (period + 1)\n        for i in range(1, len(data)):\n            result[i] = data[i] * k + result[i-1] * (1 - k)\n        return result\n\n    ema12 = ema(closes, 12)\n    ema26 = ema(closes, 26)\n    dif = ema12 - ema26\n    dea = ema(dif, 9)\n\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    holding = any(p.m_strInstrumentID == stock and p.m_nVolume > 0 for p in positions)\n\n    # 金叉：DIF上穿DEA\n    if dif[-2] \u003C= dea[-2] and dif[-1] > dea[-1] and not holding:\n        order_shares(stock, 1000, 'fix', closes[-1], ContextInfo)\n    # 死叉：DIF下穿DEA\n    elif dif[-2] >= dea[-2] and dif[-1] \u003C dea[-1] and holding:\n        order_shares(stock, -1000, 'fix', closes[-1], ContextInfo)\n```\n\n## 进阶示例：止盈止损策略\n\n```python\nimport numpy as np\n\ndef init(ContextInfo):\n    ContextInfo.stock = '000001.SZ'\n    ContextInfo.set_universe([ContextInfo.stock])\n    ContextInfo.entry_price = 0\n    ContextInfo.stop_loss = 0.05      # 止损5%\n    ContextInfo.take_profit = 0.10    # 止盈10%\n\ndef handlebar(ContextInfo):\n    stock = ContextInfo.stock\n    closes = ContextInfo.get_history_data(21, '1d', 'close', stock_code=stock)\n    if len(closes) \u003C 21:\n        return\n    price = closes[-1]\n    ma20 = np.mean(closes[-20:])\n\n    positions = get_trade_detail_data(ContextInfo.accID, 'stock', 'position')\n    pos = None\n    for p in positions:\n        if p.m_strInstrumentID == stock and p.m_nVolume > 0:\n            pos = p\n            break\n\n    if pos is None:\n        if price > ma20:\n            order_shares(stock, 1000, 'fix', price, ContextInfo)\n            ContextInfo.entry_price = price\n    else:\n        if ContextInfo.entry_price > 0:\n            pnl = (price - ContextInfo.entry_price) \u002F ContextInfo.entry_price\n            if pnl \u003C= -ContextInfo.stop_loss:\n                order_shares(stock, -pos.m_nVolume, 'fix', price, ContextInfo)\n                ContextInfo.entry_price = 0\n            elif pnl >= ContextInfo.take_profit:\n                order_shares(stock, -pos.m_nVolume, 'fix', price, ContextInfo)\n                ContextInfo.entry_price = 0\n```\n\n---\n\n---\n\n## 🤖 AI Agent 高阶使用指南\n\n对于 AI Agent，在使用该量化\u002F数据工具时应遵循以下高阶策略和最佳实践，以确保任务的高效完成：\n\n### 1. 数据校验与错误处理\n在获取数据或执行操作后，AI 应当主动检查返回的结果格式是否符合预期，以及是否存在缺失值（NaN）或空数据。\n* **示例策略**：在通过 API 获取数据框（DataFrame）后，使用 `if df.empty:` 进行校验；捕获 `Exception` 以防网络或接口错误导致进程崩溃。\n\n### 2. 多步组合分析\nAI 经常需要进行宏观经济分析或跨市场对比。应善于将当前接口与其他数据源或工具组合使用。\n* **示例策略**：先获取板块或指数的宏观数据，再筛选成分股，最后对具体标的进行深入的财务或技术面分析，形成完整的决策链条。\n\n### 3. 构建动态监控与日志\n对于交易和策略类任务，AI 可以定期拉取数据并建立监控机制。\n* **示例策略**：使用循环或定时任务检查特定标的的异动（如涨跌停、放量），并在发现满足条件的信号时输出结构化日志或触发预警。\n\n---\n\n## 社区与支持\n\n由 **大佬量化** 维护 — 量化交易教学与策略研发团队。\n\n微信客服: **bossquant1** · [Bilibili](https:\u002F\u002Fspace.bilibili.com\u002F48693330) · 搜索 **大佬量化** — 微信公众号 \u002F Bilibili \u002F 抖音\n",{"name":5,"version":24,"homepage":25,"metadata":26,"description":7},"1.2.0","http:\u002F\u002Fdict.thinktrader.net\u002Ffreshman\u002Frookie.html",{"clawdbot":27},{"emoji":28,"requires":29},"🖥️",{"bins":30},[31],"python3","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fq\u002Fqmt",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill qmt",{"tool":47,"command":48},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill qmt",{"tool":50,"command":51},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill qmt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fq\u002Fqmt\u002FSKILL.md",true,[],[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]