{
  "schemaVersion": "1.0",
  "item": {
    "slug": "quant-trading-cn",
    "name": "Quant Trading CN",
    "source": "tencent",
    "type": "skill",
    "category": "数据分析",
    "sourceUrl": "https://clawhub.ai/guohongbin-git/quant-trading-cn",
    "canonicalUrl": "https://clawhub.ai/guohongbin-git/quant-trading-cn",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/quant-trading-cn",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=quant-trading-cn",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "package.json",
      "references/KNOWLEDGE_en.md",
      "references/NUANCES_en.md",
      "references/README_en.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "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."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "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."
        },
        {
          "label": "Upgrade existing",
          "body": "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."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/quant-trading-cn"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/quant-trading-cn",
    "agentPageUrl": "https://openagent3.xyz/skills/quant-trading-cn/agent",
    "manifestUrl": "https://openagent3.xyz/skills/quant-trading-cn/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/quant-trading-cn/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "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."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "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."
      },
      {
        "label": "Upgrade existing",
        "body": "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."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "量化交易专家",
        "body": "基于 1780 行印度股市实战经验的量化交易系统。"
      },
      {
        "title": "🎯 交互式机器人生成向导",
        "body": "# 启动向导\n./scripts/wizard.sh\n\n# 选择：\n# 1. 从头生成交易机器人\n# 2. 增强现有代码（修复问题、优化）\n# 3. 从实时指数数据创建股票池\n# 4. 运行回测对比\n# 5. 分析表现"
      },
      {
        "title": "📊 16 个知识领域",
        "body": "Zerodha 集成 - Tick size 四舍五入、仓位对账、止损生命周期\n回测-实盘一致性 - 数据缓存、T vs T-1 对齐、VWAP 重置\n信号生成 - Fortress 信号（65% 胜率）、多因子确认\n调仓逻辑 - 周频 vs 日频、交易成本建模\n股票池选择 - 流动性过滤、动量评分\n性能优化 - Parquet（28x）、Polars 向量化（37x）\n印度市场特性 - 交易时段、熔断机制、T+1 结算\n失败模式 - 5 个生产问题 + 修复\n指标公式 - RSI、MACD、ATR、ADX、VWAP、EMA\n多时间框架 - 日内 vs 波段、MTF 对齐\n日志可观测 - 结构化日志、实时监控\n交易后分析 - P&L 分解、夏普比率、回撤分析\n信号归因 - 追踪哪个指标触发\n退出策略 - 时间衰减、追踪止损、部分退出\n风险管理 - Kelly Criterion、组合热度\n资金复利 - 市场状态检测、牛市放大"
      },
      {
        "title": "⚠️ 30+ 常见陷阱",
        "body": "🔥 关键：Tick Size 四舍五入\n错误：kite.place_order(price=1847.35, ...)\n报错：\"Tick size for this script is 5.00\"\n修复：price = round(price / tick_size) * tick_size  # 1847.35 → 1850.00\n影响：90% 订单拒绝是 tick size 错误\n\n🔥 关键：VWAP 必须每日重置\n错误：跨天累计 VWAP\n症状：回测 65% 胜率，实盘 40%\n修复：开盘时重置（9:15）\n影响：回测-实盘不一致的第一大原因"
      },
      {
        "title": "生成第一个交易机器人",
        "body": "./scripts/wizard.sh\n\n向导会问：\n\n交易风格：日内、波段、持仓\n股票池：Nifty 50、中盘、自定义\n策略：动量、VWAP 回调、开盘突破\n资金：起始资金和单笔风险\n风险偏好：保守（0.5%）、平衡（1%）、激进（2%）"
      },
      {
        "title": "获取股票池",
        "body": "# 从 NSE 获取最新成分股\n./scripts/universe-fetch.sh --indices nifty50,nifty100,midcap150"
      },
      {
        "title": "分析现有代码",
        "body": "./scripts/check-code.sh ./my_trading_bot.py\n\n# 输出：\n⚠️ 发现 3 个问题：\n1. Tick size 未四舍五入（第 45 行）- 会导致订单拒绝\n2. VWAP 未每日重置（第 89 行）- 回测实盘不一致\n3. 无股票冷却期（第 120 行）- 报复交易风险"
      },
      {
        "title": "性能基准",
        "body": "优化之前之后提升Parquet 缓存2.3s0.08s28.7xPolars 向量化450ms12ms37.5xAPI 批量请求15 次1 次15x预计算指标180ms90ms2x总回测时间5 min12 sec25x"
      },
      {
        "title": "文件结构",
        "body": "quant-trading-cn/\n├── SKILL.md           # 本文件\n├── KNOWLEDGE.md       # 16 个领域（1780 行）\n├── NUANCES.md         # 30+ 陷阱\n├── scripts/\n│   ├── wizard.sh      # 交互式向导\n│   ├── universe-fetch.sh  # 股票池获取\n│   └── check-code.sh  # 代码检查\n└── references/\n    ├── KNOWLEDGE_en.md   # 原始英文版\n    └── NUANCES_en.md     # 原始英文版"
      },
      {
        "title": "A 股适配",
        "body": "本项目基于印度市场，但可适配 A 股：\n\n印度A 股Zerodha雪球/同花顺Nifty 50沪深 300Nifty Midcap中证 500T+1 结算T+1 结算9:15-15:309:30-15:00"
      },
      {
        "title": "注意事项",
        "body": "⚠️ 本 skill 提供教育性指导，不保证盈利。交易有风险，仅用可承受资金。\n\n版本: 1.0.0\n来源: skill-algotrader"
      }
    ],
    "body": "量化交易专家\n\n基于 1780 行印度股市实战经验的量化交易系统。\n\n功能\n🎯 交互式机器人生成向导\n# 启动向导\n./scripts/wizard.sh\n\n# 选择：\n# 1. 从头生成交易机器人\n# 2. 增强现有代码（修复问题、优化）\n# 3. 从实时指数数据创建股票池\n# 4. 运行回测对比\n# 5. 分析表现\n\n📊 16 个知识领域\nZerodha 集成 - Tick size 四舍五入、仓位对账、止损生命周期\n回测-实盘一致性 - 数据缓存、T vs T-1 对齐、VWAP 重置\n信号生成 - Fortress 信号（65% 胜率）、多因子确认\n调仓逻辑 - 周频 vs 日频、交易成本建模\n股票池选择 - 流动性过滤、动量评分\n性能优化 - Parquet（28x）、Polars 向量化（37x）\n印度市场特性 - 交易时段、熔断机制、T+1 结算\n失败模式 - 5 个生产问题 + 修复\n指标公式 - RSI、MACD、ATR、ADX、VWAP、EMA\n多时间框架 - 日内 vs 波段、MTF 对齐\n日志可观测 - 结构化日志、实时监控\n交易后分析 - P&L 分解、夏普比率、回撤分析\n信号归因 - 追踪哪个指标触发\n退出策略 - 时间衰减、追踪止损、部分退出\n风险管理 - Kelly Criterion、组合热度\n资金复利 - 市场状态检测、牛市放大\n⚠️ 30+ 常见陷阱\n🔥 关键：Tick Size 四舍五入\n错误：kite.place_order(price=1847.35, ...)\n报错：\"Tick size for this script is 5.00\"\n修复：price = round(price / tick_size) * tick_size  # 1847.35 → 1850.00\n影响：90% 订单拒绝是 tick size 错误\n\n🔥 关键：VWAP 必须每日重置\n错误：跨天累计 VWAP\n症状：回测 65% 胜率，实盘 40%\n修复：开盘时重置（9:15）\n影响：回测-实盘不一致的第一大原因\n\n使用方法\n生成第一个交易机器人\n./scripts/wizard.sh\n\n\n向导会问：\n\n交易风格：日内、波段、持仓\n股票池：Nifty 50、中盘、自定义\n策略：动量、VWAP 回调、开盘突破\n资金：起始资金和单笔风险\n风险偏好：保守（0.5%）、平衡（1%）、激进（2%）\n获取股票池\n# 从 NSE 获取最新成分股\n./scripts/universe-fetch.sh --indices nifty50,nifty100,midcap150\n\n分析现有代码\n./scripts/check-code.sh ./my_trading_bot.py\n\n# 输出：\n⚠️ 发现 3 个问题：\n1. Tick size 未四舍五入（第 45 行）- 会导致订单拒绝\n2. VWAP 未每日重置（第 89 行）- 回测实盘不一致\n3. 无股票冷却期（第 120 行）- 报复交易风险\n\n性能基准\n优化\t之前\t之后\t提升\nParquet 缓存\t2.3s\t0.08s\t28.7x\nPolars 向量化\t450ms\t12ms\t37.5x\nAPI 批量请求\t15 次\t1 次\t15x\n预计算指标\t180ms\t90ms\t2x\n总回测时间\t5 min\t12 sec\t25x\n文件结构\nquant-trading-cn/\n├── SKILL.md           # 本文件\n├── KNOWLEDGE.md       # 16 个领域（1780 行）\n├── NUANCES.md         # 30+ 陷阱\n├── scripts/\n│   ├── wizard.sh      # 交互式向导\n│   ├── universe-fetch.sh  # 股票池获取\n│   └── check-code.sh  # 代码检查\n└── references/\n    ├── KNOWLEDGE_en.md   # 原始英文版\n    └── NUANCES_en.md     # 原始英文版\n\nA 股适配\n\n本项目基于印度市场，但可适配 A 股：\n\n印度\tA 股\nZerodha\t雪球/同花顺\nNifty 50\t沪深 300\nNifty Midcap\t中证 500\nT+1 结算\tT+1 结算\n9:15-15:30\t9:30-15:00\n注意事项\n\n⚠️ 本 skill 提供教育性指导，不保证盈利。交易有风险，仅用可承受资金。\n\n版本: 1.0.0 来源: skill-algotrader"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/guohongbin-git/quant-trading-cn",
    "publisherUrl": "https://clawhub.ai/guohongbin-git/quant-trading-cn",
    "owner": "guohongbin-git",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/quant-trading-cn",
    "downloadUrl": "https://openagent3.xyz/downloads/quant-trading-cn",
    "agentUrl": "https://openagent3.xyz/skills/quant-trading-cn/agent",
    "manifestUrl": "https://openagent3.xyz/skills/quant-trading-cn/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/quant-trading-cn/agent.md"
  }
}