![\"DataQuant\"](\"https://img.shields.io/badge/DataQuant-API-4d8df6?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAxMDAgMTAwIj48dGV4dCB5PSIuOWVtIiBmb250LXNpemU9IjkwIj7wn6SbPC90ZXh0Pjwvc3ZnPg\"){kind=icon}
\n \n AI Agent Skill for Quantitative Market Data & Automated Backtesting\n
\n Daily OHLCV for 6,125+ instruments across A-shares, HK, US equities, crypto, indices, and ETFs. One link installs into your AI assistant — zero config, zero code.\n
\n
\n AI Agent Skill for Quantitative Market Data & Automated Backtesting\n
\n Daily OHLCV for 6,125+ instruments across A-shares, HK, US equities, crypto, indices, and ETFs. One link installs into your AI assistant — zero config, zero code.\n
\n About ·\n Who It's For ·\n Use Cases ·\n Coverage ·\n Install ·\n Pipeline ·\n Structure ·\n CLI ·\n API ·\n 中文版\n
\n\n---\n\n## What Is DataQuant Connector?\n\n**DataQuant Connector** is an AI Agent Skill that equips your assistant with direct access to structured financial market data — daily OHLCV (open, high, low, close, volume, amount) for over 6,125 instruments across six global markets. Built on the [DataQuant](https://app.dataquant.trade/) quantitative data platform, accessible via a simple REST interface.\n\nDesigned for quantitative backtesting workflows: describe a strategy in plain language, and your AI handles data retrieval, script generation, execution, and reporting — end to end.\n\n## Who Is This For?\n\n- **AI-assisted quantitative researchers** who design and validate trading strategies through natural-language interaction with an AI agent\n- **Developers building AI agents** that need a structured, low-latency financial data source with a simple REST interface\n- **Individual traders** who want to backtest ideas without writing data pipelines, web scrapers, or ETL jobs\n\n## Use Cases\n\nAll powered by daily OHLCV plus a per-instrument latest snapshot (valuation, size, momentum, 52-week position) — enough for screening without pulling financial statements.\n\n| Use Case | Example Prompt |\n|----------|---------------|\n| **Rule-based Strategy Backtest** | \"Backtest Kweichow Moutai 2020–2025, buy on MA20/MA60 golden cross, sell on death cross\" |\n| **Event-driven Analysis** | \"Buy CSI 300 ETF the day after a PBoC RRR cut and hold for 30 days — run this for all RRR cuts since 2015\" [^1] |\n| **Multi-asset Portfolio Backtest** | \"Equal-weight the top 10 CSI 300 constituents by volume, rebalance monthly, 2020–2025\" |\n\n[^1]: Event dates (e.g. RRR cut announcements) are resolved by the AI agent through search tools. DataQuant provides the OHLCV price series for the backtest window.\n\n## Financial Data Coverage\n\n| Market | Instruments | Identifiers |\n|--------|-------------|-------------|\n| **A-Shares** | ~3,000 | `sh600519` · `sz000001` |\n| **HK Stocks** | ~1,000 | `hk00700` · `hk09988` |\n| **US Stocks** | ~2,000 | `usAAPL` · `usMSFT` |\n| **Cryptocurrency** | ~100 | `BTCUSDT` · `ETHUSDT` |\n| **Global Indices** | 15 | `sh000001` · `hkHSI` |\n| **ETFs** | 11 | `sh510050` · `sh510300` |\n\n| Metric | Value |\n|--------|-------|\n| Total Instruments | **6,125+** |\n| Update Frequency | **Daily (EOD)** |\n| Data Format | OHLCV + latest snapshot (valuation, size, momentum, 52w position) |\n\n**Macroeconomic indicators** — GDP, CPI/PPI, and PMI — are also available via the `/macro` endpoint.\n\n## Installation Guide\n\n### Step 1 — Register & Get Your API Key\n\nSign up at [app.dataquant.trade](https://app.dataquant.trade/). Copy your API Key from the user dashboard.\n\n### Step 2 — Send the Skill Link to Your AI\n\nPaste the following line into any AI assistant that supports Skill installation:\n\n```\nInstall the skill at: https://app.dataquant.trade/skill\n```\n\nThe AI reads the embedded skill definition from the page, creates the directory structure, and writes all support files — fully automated.\n\n### Step 3 — Provide Your Key & Start\n\n```\nMy DataQuant API Key is dq_xxxxxxxx\n```\n\nYour AI is now connected. Describe any strategy:\n\n```\nBacktest CSI 300 ETF 2020–2025, Bollinger Band mean-reversion,\nbuy on lower band touch, sell on middle band convergence\n```\n\n## Automated Backtesting Pipeline\n\n\n Natural Language Strategy → \n DataQuant Data Fetch → \n Backtest Script Generation → \n Equity Curve Plot → \n Analysis Report\n
\n\nEvery stage is automated. The user provides a strategy description; the AI handles data retrieval, script generation, backtest execution, and final reporting.\n\n## Skill Structure\n\n```\ndataquant-connector/\n├── SKILL.md # Core skill definition\n├── skill.json # Skill metadata\n├── LICENSE\n├── README.md\n└── scripts/\n └── dataquant.py # Python CLI for the DataQuant REST API\n```\n\n### File Roles\n\n| File | Required |\n|------|----------|\n| `SKILL.md` | ✅ |\n| `skill.json` | ✅ |\n| `scripts/dataquant.py` | ✅ |\n| `README.md` | — |\n| `LICENSE` | — |\n\nAPI 参数与字段定义以 [app.dataquant.trade/api-docs](https://app.dataquant.trade/api-docs) 为准，本 Skill 不做二次维护。\n\n## CLI Usage\n\n```bash\n# Single-instrument daily OHLCV (with adjustment)\npython scripts/dataquant.py kline ashare sh600519 \\\n --start 2020-01-01 --end 2025-12-31 --adj qfq --api-key KEY\n\n# Batch fetch (up to 50 instruments depending on plan)\npython scripts/dataquant.py batch ashare sh600519,sz000858 \\\n --start 2025-01-01 --adj bfq --api-key KEY\n\n# Latest snapshot (valuation, size, momentum, 52w)\npython scripts/dataquant.py detail ashare sh600519 --api-key KEY\npython scripts/dataquant.py detail ashare sh600519,sz000858 --api-key KEY\n\n# Screen by criteria\npython scripts/dataquant.py screen ashare \\\n --min-pe-ratio 0 --max-pe-ratio 30 --sort change_percent --api-key KEY\n\n# Symbol search\npython scripts/dataquant.py search ashare 600519 --api-key KEY\n\n# Quota inspection\npython scripts/dataquant.py quota --api-key KEY\n\n# Macroeconomic indicators\npython scripts/dataquant.py macro gdp --start 2020 --end 2025 --api-key KEY\n```\n\nOr set the key once as an environment variable:\n\n```bash\n# Linux / macOS\nexport DATAQUANT_API_KEY=dq_xxxxxxxx\n# Windows (PowerShell)\n$env:DATAQUANT_API_KEY = \"dq_xxxxxxxx\"\n\npython scripts/dataquant.py kline ashare sh600519 --start 2020-01-01\n```\n\n## REST API Reference\n\n| | |\n|---|---|\n| **Base URL** | `https://api.dataquant.trade` |\n| **Authentication** | `X-API-Key` header |\n| **Response Format** | JSON |\n\n### Endpoints\n\n| Method | Path | Description |\n|--------|------|-------------|\n| `GET` | `/{market}/klines/{symbol}?adj=bfq\\|qfq\\|hfq` | Single-instrument daily OHLCV (bfq default; hfq/qfq forward/backward-adjusted) |\n| `GET` | `/{market}/klines?symbols=a,b&adj=...` | Batch OHLCV (comma-separated, same adj support) |\n| `GET` | `/{market}/detail/{symbol}?fields=...` | Single-instrument latest snapshot (valuation / size / momentum / 52w) |\n| `GET` | `/{market}/detail?symbols=a,b` | Batch latest snapshot (comma-separated) |\n| `GET` | `/{market}/screen?min_pe_ratio=...&max_pe_ratio=...` | Filter latest snapshot by valuation / size / momentum |\n| `GET` | `/{market}/symbols?search=` | Fuzzy search by name or code |\n| `GET` | `/macro?indicator=gdp\\|cpi_ppi\\|pmi` | Macroeconomic data — GDP, CPI&PPI, PMI (indicator optional; returns all when omitted) |\n| `GET` | `/quota` | Current usage and remaining daily quota |\n\n### Markets\n\n```\nashare A-Shares\nhkstock Hong Kong Stocks\nusstock US Stocks\ncrypto Cryptocurrency\nindices Global Indices\netfs ETFs\n```\n\n### Query Parameters\n\n| Parameter | Type | Description |\n|-----------|------|-------------|\n| `start` | `YYYY-MM-DD` | Start date — inclusive (klines/detail: YYYY-MM-DD; macro: YYYY year only) |\n| `end` | `YYYY-MM-DD` | End date — inclusive (klines/detail: YYYY-MM-DD; macro: YYYY year only) |\n| `fields` | `o,h,l,c,v,a` | Field selection for klines (short codes or full names, default: `*` for all); detail columns for /detail (e.g. `pe_ratio,pb_ratio,chg_20d`). symbol, date, and adj_factor are always returned regardless of fields |\n| `adj` | `bfq\\|qfq\\|hfq` | Adjustment method — klines only: bfq unadjusted (default), qfq forward-adjusted, hfq backward-adjusted |\n| `limit` | `integer` | Max rows per page |\n| `offset` | `integer` | Pagination offset |\n| `sort` | `string` | Screen sort column (default: `change_percent`), must be in filter whitelist |\n| `order` | `asc\\|desc` | Screen sort order (default: `desc`) |\n| `min_*` / `max_*` | `float` | Screen filter bounds — prefix with column name, e.g. `min_pe_ratio=0`, `max_total_market_cap=1000` |\n\n### OHLCV Fields\n\n| Code | Name | Description |\n|------|------|-------------|\n| `o` | open | Opening price |\n| `h` | high | Session high |\n| `l` | low | Session low |\n| `c` | close | Closing price |\n| `v` | volume | Volume (lots for equities) |\n| `a` | amount | Turnover / notional amount |\n\nsymbol, date, and adj_factor are always returned in every kline row regardless of the `fields` parameter.\nsymbol and date are always returned in every detail row.\n\n## Links\n\n- [DataQuant Homepage](https://app.dataquant.trade/)\n- [Skill Installation Page](https://app.dataquant.trade/skill)\n- [Interactive API Documentation](https://app.dataquant.trade/api-docs)\n\n## License\n\nMIT\n\n---\n\n\n 自然语言策略描述 → \n DataQuant 数据获取 → \n 回测脚本生成 → \n 权益曲线绘制 → \n 分析报告输出\n
\n\n全链路自动化。用户提供策略描述，AI 完成数据检索、脚本生成、回测执行和最终报告。\n\n## Skill 目录结构\n\n```\ndataquant-connector/\n├── SKILL.md # 核心 Skill 定义\n├── skill.json # Skill 元数据\n├── LICENSE\n├── README.md\n└── scripts/\n └── dataquant.py # DataQuant REST API 的 Python CLI\n```\n\n### 文件分工\n\n| 文件 | 必须 |\n|------|------|\n| `SKILL.md` | ✅ |\n| `skill.json` | ✅ |\n| `scripts/dataquant.py` | ✅ |\n| `README.md` | — |\n| `LICENSE` | — |\n\nAPI 参数与字段定义以 [app.dataquant.trade/api-docs](https://app.dataquant.trade/api-docs) 为准，本 Skill 不做二次维护。\n\n## CLI 使用\n\n```bash\n# 单标的日线（支持复权）\npython scripts/dataquant.py kline ashare sh600519 \\\n --start 2020-01-01 --end 2025-12-31 --adj qfq --api-key KEY\n\n# 批量取数（批量上限取决于套餐）\npython scripts/dataquant.py batch ashare sh600519,sz000858 \\\n --start 2025-01-01 --adj bfq --api-key KEY\n\n# 最新快照（估值/规模/动量/52周）\npython scripts/dataquant.py detail ashare sh600519 --api-key KEY\npython scripts/dataquant.py detail ashare sh600519,sz000858 --api-key KEY\n\n# 条件筛选\npython scripts/dataquant.py screen ashare \\\n --min-pe-ratio 0 --max-pe-ratio 30 --sort change_percent --api-key KEY\n\n# 标的搜索\npython scripts/dataquant.py search ashare 600519 --api-key KEY\n\n# 配额查询\npython scripts/dataquant.py quota --api-key KEY\n\n# 宏观经济指标\npython scripts/dataquant.py macro gdp --start 2020 --end 2025 --api-key KEY\n```\n\n也可通过环境变量设置 Key：\n\n```bash\n# Linux / macOS\nexport DATAQUANT_API_KEY=dq_xxxxxxxx\n# Windows (PowerShell)\n$env:DATAQUANT_API_KEY = \"dq_xxxxxxxx\"\n\npython scripts/dataquant.py kline ashare sh600519 --start 2020-01-01\n```\n\n## REST API 参考\n\n| | |\n|---|---|\n| **Base URL** | `https://api.dataquant.trade` |\n| **认证方式** | `X-API-Key` Header |\n| **响应格式** | JSON |\n\n### 端点\n\n| 方法 | 路径 | 说明 |\n|------|------|------|\n| `GET` | `/{market}/klines/{symbol}?adj=bfq\\|qfq\\|hfq` | 单标的日线 OHLCV（bfq 默认不复权；qfq/hfq 前/后复权） |\n| `GET` | `/{market}/klines?symbols=a,b&adj=...` | 批量日线（逗号分隔，同样支持 adj） |\n| `GET` | `/{market}/detail/{symbol}?fields=...` | 单标的最新快照（估值 / 规模 / 动量 / 52 周） |\n| `GET` | `/{market}/detail?symbols=a,b` | 批量最新快照（逗号分隔） |\n| `GET` | `/{market}/screen?min_pe_ratio=...&max_pe_ratio=...` | 按估值 / 规模 / 动量筛选最新快照 |\n| `GET` | `/{market}/symbols?search=` | 按名称或代码模糊搜索 |\n| `GET` | `/macro?indicator=gdp\\|cpi_ppi\\|pmi` | 宏观经济数据（GDP / CPI&PPI / PMI，indicator 可选，不传返回全部） |\n| `GET` | `/quota` | 查询当日用量与剩余配额 |\n\n### 市场代码\n\n```\nashare A 股\nhkstock 港股\nusstock 美股\ncrypto 加密货币\nindices 全球指数\netfs ETF\n```\n\n### 查询参数\n\n| 参数 | 类型 | 说明 |\n|------|------|------|\n| `start` | `YYYY-MM-DD` | 起始日期 — 含当日（K线/快照：YYYY-MM-DD；宏观：YYYY 年份） |\n| `end` | `YYYY-MM-DD` | 结束日期 — 含当日（K线/快照：YYYY-MM-DD；宏观：YYYY 年份） |\n| `fields` | `o,h,l,c,v,a` | K 线字段选择（短码或全名均可）：单标的默认 `*`(全字段)，批量默认 `close,volume`；detail 快照字段（如 `pe_ratio,pb_ratio,chg_20d`）。kline 行始终含 symbol/date/adj_factor；detail 行始终含 symbol/date |\n| `adj` | `bfq\\|qfq\\|hfq` | 复权方式 — 仅 K 线：bfq 不复权（默认），qfq 前复权，hfq 后复权 |\n| `limit` | `integer` | 每页最大返回行数 |\n| `offset` | `integer` | 分页偏移 |\n| `sort` | `string` | Screen 排序字段（默认 `change_percent`），须在白名单内 |\n| `order` | `asc\\|desc` | Screen 排序方向（默认 `desc`） |\n| `min_*` / `max_*` | `float` | Screen 筛选上下界 — 前缀加列名，如 `min_pe_ratio=0`、`max_total_market_cap=1000` |\n\n### OHLCV 字段\n\n| 代码 | 名称 | 说明 |\n|------|------|------|\n| `o` | open | 开盘价 |\n| `h` | high | 当日最高价 |\n| `l` | low | 当日最低价 |\n| `c` | close | 收盘价 |\n| `v` | volume | 成交量（股/手） |\n| `a` | amount | 成交额 |\n\n每行 K 线始终返回 symbol、date、adj_factor，不受 fields 参数影响。\n每行 detail 快照始终返回 symbol、date。\n\n## 相关链接\n\n- [DataQuant 主页](https://app.dataquant.trade/)\n- [Skill 安装页面](https://app.dataquant.trade/skill)\n- [交互式 API 文档](https://app.dataquant.trade/api-docs)\n\n## 许可证\n\nMIT\n\nFile v0.1.0:_meta.json\n\n{\n \"ownerId\": \"kn7b3zgpkdg237k84q5gk786858bzfhj\",\n \"slug\": \"dataquant-connector\",\n \"version\": \"0.1.0\",\n \"publishedAt\": 1785997899949\n}\n\nFile v0.1.0:references/api-reference.md\n\n# DataQuant Connector — 详细参考\n\n> 本文件是 `SKILL.md` 的外置参考，承载篇幅较大的字段表与参数表，避免占满调用上下文（progressive disclosure）。\n> 所有接口、参数、默认值、字段均核对自线上 api-docs（https://app.dataquant.trade/api-docs）及平台后端源码，确保与线上服务一致。\n\n## 市场代码\n\n| 代码 | 市场 |\n|------|------|\n| ashare | A 股 |\n| hkstock | 港股 |\n| usstock | 美股 |\n| crypto | 加密货币 |\n| indices | 全球指数 |\n| etfs | ETF |\n\nCoverage：A 股 ~3000 / 港股 ~1000 / 美股 ~2000 / 加密 ~100 / 指数 15 / ETF 11。\n\n## /screen 字段白名单（后端 `DETAIL_FILTERABLE`，完整列表）\n\n任意 `min_<列>` / `max_<列>` 或 `sort=<列>` 都必须是下列字段之一；不在白名单的列被服务端静默忽略。\n\n| 分组 | 字段 |\n|------|------|\n| 估值 | `pe_ratio` `pe_lyr` `pb_ratio` `dividend_ratio_ttm` `eps_ttm` |\n| 规模 | `total_market_cap` `circulating_market_cap` `total_shares` `float_shares` |\n| 活跃度 | `turnover_rate` `volume_ratio` `range_pct` |\n| 动量 | `change_percent` `chg_5d` `chg_10d` `chg_20d` `chg_60d` `chg_ytd` |\n| 位置/均线 | `close_vs_ma20` `close_vs_52w_high` `ma5` `ma10` `ma20` `ma60` `high_52week` `low_52week` |\n| 行情 | `volume` `amount` `open` `high` `low` `close` |\n\nscreen 返回列固定为服务端 `_SCREEN_COLUMNS`（23 列：symbol / name / market_name / date / close + 估值 / 规模 / 动量 / 均线 等）。\n\n## 常用 detail 字段（后端 `DETAIL_COLUMNS`）\n\n| 分组 | 字段 |\n|------|------|\n| 标识 | `symbol` `date` `name` `market_name` |\n| 行情 | `open` `high` `low` `close` `pre_close` `avg_price` `volume` `amount` `change` `change_percent` |\n| 估值 | `pe_ratio` `pe_fwd` `pe_lyr` `pb_ratio` `dividend_ratio_ttm` `dividend_ttm` `eps_ttm` `wb_ratio`(港股特有) |\n| 规模 | `total_market_cap`(亿元·本币) `circulating_market_cap` `total_shares` `float_shares` |\n| 动量 | `chg_5d` `chg_10d` `chg_20d` `chg_60d` `chg_ytd` |\n| 52 周 | `high_52week` `low_52week` `close_vs_52w_high` |\n| 均线 | `ma5` `ma10` `ma20` `ma60` `close_vs_ma20` |\n\n`detail` 接口默认返回全部字段；`symbol`、`date` 始终返回，不受 `fields` 过滤；detail 不含 `adj_factor`。\n\n## 套餐与配额（后端 `PLANS_DEFINITION`）\n\n| | 免费版 | 专业版 | 企业版 |\n|---|---|---|---|\n| 日配额（行） | 5,000 | 200,000 | 2,000,000 |\n| 速率（rpm，文档值） | 30 | 120 | 600 |\n| 批量标的 | 5 | 50 | 50 |\n| 单次行数 | 100 | 500 | 500 |\n\n- 配额按「返回行数」计：kline 按行数、detail 按标的数、screen 按 `limit`。\n- 速率：api-docs 文档值为上表；**服务端另设全局 `200/min` 硬上限**，超限返回 429。\n- 建议：批量请求之间留 ≥ 0.5s 间隔；先用 `/quota` 看剩余再决定分批或缩减时间跨度。\n\n## 错误码（HTTP 状态）\n\n| HTTP | 含义 | 处理 |\n|------|------|------|\n| 400 | 参数错误 | `fields` 非法 / `symbols` 超套餐上限 / `market` 不存在 / `indicator` 未知 |\n| 401 | 认证失败 | `X-API-Key` 缺失、无效或已禁用 → 让用户检查 Key |\n| 403 | 禁止访问 | 仅 dashboard 写操作的 CSRF 校验；本 Skill 只做 GET 查询，正常不会触发 |\n| 404 | 资源不存在 | 标的代码不存在 / `macro` 库未就绪 |\n| 429 | 速率或配额耗尽 | 退避后重试；仍失败则告知用户配额用尽 |\n| 503 | 服务暂不可用 | 优雅关闭中；稍后重试 |\n\nFile v0.1.0:skill-card.md\n\n## Description:\n\nDataQuant Connector gives agents REST API access to DataQuant market data for OHLCV and K-line retrieval, valuation snapshots, conditional screening, macro data, and quota checks across A-shares, Hong Kong stocks, U.S. stocks, crypto, indices, and ETFs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ai-ip](https://clawhub.ai/user/ai-ip)\n\n### License/Terms of Use:\n\nMIT\n\n## Use Case:\n\nExternal developers, AI-assisted quantitative researchers, and individual traders use this skill to retrieve structured DataQuant market data and guide agent-assisted backtesting, screening, and analysis workflows.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: API keys can leak if pasted into chat or passed on the command line.\n\nMitigation: Set DATAQUANT_API_KEY through a protected environment variable or secret store, and avoid sharing real keys in chat or shell history.\n\nRisk: Generated backtest code or trading analysis may be incorrect or misleading if run without review.\n\nMitigation: Review generated code and outputs before execution or investment decisions, and consider using a virtual environment with pinned dependencies.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/ai-ip/skills/dataquant-connector)\n- [Server-Resolved GitHub Repository](https://github.com/ai-ip/dataquant-connector)\n- [DataQuant API Reference](references/api-reference.md)\n- [Interactive DataQuant API Documentation](https://app.dataquant.trade/api-docs)\n- [DataQuant Homepage](https://app.dataquant.trade/)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]\n\n**Output Format:** [Markdown guidance with shell commands and JSON API output]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires a valid DataQuant API key; CLI calls return JSON from DataQuant REST endpoints.]\n\n## Skill Version(s):\n\n0.1.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v0.1.0:skill.json\n\n{\n \"name\": \"dataquant-connector\",\n \"version\": \"1.1.0\",\n \"description\": \"DataQuant 量化数据平台对接 Skill，覆盖 A股/港股/美股/加密货币/指数/ETF 六大市场，支持 K线（日线 OHLCV，含 adj_factor 复权因子）、最新快照（估值/规模/动量/52 周）、条件筛选、宏观数据。DataQuant 取数、dataquant kline、dataquant detail。\"\n}\n\nFile v0.1.0:LICENSE\n\nMIT License\n\nCopyright (c) 2026 DataQuant\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.","readmeExcerpt":"Skill: Dataquant Connector 量化数据通道 Owner: ai-ip Summary: 对接 DataQuant 量化数据平台，为回测与选股提供 REST API 取数通道，覆盖 A股/港股/美股/加密货币/指数/ETF 六大市场，支持 K线、估值快照、条件筛选与宏观数据。 当用户需要从 DataQuant 查询行情、K线、估值快照、条件选股或宏观数据，或消息中出现 \"DataQuant\" / \"dataquant kline\" / \"dataquant screen\" 等取数指令时启用本 Skill。 Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-06T06:31:39.949Z | auto - Initial release of dataquant-connector skill. - Provides REST API access t","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"ashare A 股\nhkstock 港股\nusstock 美股\ncrypto 加密货币\nindices 全球指数\netfs ETF"},{"language":"bash","snippet":"# 单标的日线（前复权）\npython scripts/dataquant.py kline ashare sh600519 --start 2020-01-01 --end 2025-12-31 --adj qfq --api-key KEY\n# 批量日线（默认 close,volume）\npython scripts/dataquant.py batch ashare sh600519,sz000858 --start 2025-01-01 --adj bfq --api-key KEY\n# 最新快照（单 / 多）\npython scripts/dataquant.py detail ashare sh600519 --api-key KEY\npython scripts/dataquant.py detail ashare sh600519,sz000858 --api-key KEY\n# 条件筛选（列名取白名单）\npython scripts/dataquant.py screen ashare --min-pe-ratio 0 --max-pe-ratio 30 --min-total-market-cap 1000 --sort chg_20d --api-key KEY\n# 标的搜索（按代码子串，非名称！）\npython scripts/dataquant.py search ashare 600519 --api-key KEY\n# 宏观\npython scripts/dataquant.py macro gdp --start 2020 --end 2025 --api-key KEY\n# 配额\npython scripts/dataquant.py quota --api-key KEY"},{"language":"text","snippet":"Install the skill at: https://app.dataquant.trade/skill"},{"language":"text","snippet":"My DataQuant API Key is dq_xxxxxxxx"},{"language":"text","snippet":"Backtest CSI 300 ETF 2020–2025, Bollinger Band mean-reversion,\nbuy on lower band touch, sell on middle band convergence"},{"language":"text","snippet":"dataquant-connector/\n├── SKILL.md # Core skill definition\n├── skill.json # Skill metadata\n├── LICENSE\n├── README.md\n└── scripts/\n └── dataquant.py # Python CLI for the DataQuant REST API"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: dataquant-connector\ndescription: >-\n 对接 DataQuant 量化数据平台，为回测与选股提供 REST API 取数通道，覆盖 A股/港股/美股/加密货币/指数/ETF 六大市场，支持 K线、估值快照、条件筛选与宏观数据。\n 当用户需要从 DataQuant 查询行情、K线、估值快照、条件选股或宏观数据，或消息中出现 \"DataQuant\" / \"dataquant kline\" / \"dataquant screen\" 等取数指令时启用本 Skill。\n---\n\n# DataQuant Connector\n\n## 触发条件\n\n当用户消息包含以下任一模式时启动本 Skill：\n\n| 类别 | 触发词（含中文/英文） |\n|------|----------------------|\n| 取数指令 | \"用 DataQuant 取\"、\"DataQuant 查\"、\"dataquant kline\"、\"dataquant batch\"、\"dataquant detail\"、\"dataquant screen\"、\"dataquant search\"、\"dataquant macro\"、\"dataquant quota\" |\n| API Key 提供 | \"DataQuant API Key 是\"、\"DQ_API_KEY=\"、\"DATAQUANT_API_KEY\" |\n\n## 前置依赖\n\n- **必装**：Python 3.8+，`requests`（`pip install requests`）\n- **必填**：DataQuant API Key（注册地址：https://app.dataquant.trade）。优先读环境变量 `DATAQUANT_API_KEY`，缺失时向用户索取，不要自己编造。\n- **Base URL**：`https://api.dataquant.trade`，认证方式 `X-API-Key` Header（CLI 已封装）。\n\n## 市场代码（固定 6 个）\n\n```\nashare A 股\nhkstock 港股\nusstock 美股\ncrypto 加密货币\nindices 全球指数\netfs ETF\n```\n\nCoverage：A 股 ~3000 / 港股 ~1000 / 美股 ~2000 / 加密 ~100 / 指数 15 / ETF 11。\n\n## 端点总览\n\n| 命令 | 方法 + 路径 | CLI 子命令 |\n|------|------------|-----------|\n| 单标的日线 | `GET /{market}/klines/{symbol}` | `kline` |\n| 批量日线 | `GET /{market}/klines`（`symbols=` 逗号分隔，必填） | `batch` |\n| 单标的最新快照 | `GET /{market}/detail/{symbol}` | `detail`（单代码） |\n| 批量最新快照 | `GET /{market}/detail`（`symbols=` 逗号分隔） | `detail`（多代码） |\n| 条件筛选 | `GET /{market}/screen` | `screen` |\n| 标的搜索 | `GET /{market}/symbols` | `search` |\n| 宏观数据 | `GET /macro` | `macro` |\n| 配额查询 | `GET /quota` | `quota` |\n\n## 参数与默认值\n\n**K 线 fields**\n- 单标的 `/klines/{symbol}`：默认 `*`（全字段）。\n- 批量 `/klines`：默认 `close,volume`。\n- `fields` 支持短码或全名：`o,h,l,c,v,a` / `open,high,low,close,volume,amount`；非法列返回 400。\n- `adj`：`bfq`（不复权，默认）/ `qfq` / `hfq`。\n- `limit`：单标的默认 100；批量默认 100。服务端按套餐 `max_single_rows` 截断（free=100，pro/ent=500）。\n- `offset`：默认 0。\n- 批量额外支持 `date=YYYY-MM-DD`（与 `start`/`end` 互斥，取该日快照）。\n\n**detail fields**：默认 `*` 全字段。`symbol`、`date` 始终返回，不受 `fields` 过滤。detail 接口不含 `adj_factor`。\n\n**screen**\n- `sort` 默认 `change_percent`；`order` 默认 `desc`。\n- `limit` 默认 50；`offset` 默认 0。返回列固定为服务端 `_SCREEN_COLUMNS`（23 列：symbol/name/market_name/date/close + 估值/规模/动量/均线 等）。\n- 过滤语法：`min_<列>` / `max_<列>`，列名必须在白名单内（见 `references/api-reference.md`）；不在白名单的列被服务端静默忽略。\n\n**search（`/{market}/symbols`）**\n- `search`：对 symbol 代码做子串匹配（例如 `600519`、`sh600519`、`BTC`）。不支持中文名称搜索——服务端仅按代码匹配，传 `贵州茅台`/`茅台` 返回空。\n- `limit` 默认 50，最大 100；`offset` 默认 0。\n- 返回结构：`{\"market\",\"total\",\"count\",\"offset\",\"symbols\":[...]}`，`symbols` 是代码字符串列表（不含名称）。\n\n**macro**\n- `indicator`：`gdp` / `cpi_ppi` / `pmi`，不传返回全部。\n- `start` / `end`：年份 `YYYY`（可选）。⚠️ 服务端按字符串比较 `date`，若想包含末年数据，建议 `end` 用年末日期（如 `2025-12-31`）或省略 `end`。\n- `limit` 默认 100；`offset` 默认 0。返回 `data[]` 中 `data` 字段已由服务端解析为对象，调用方无需二次 `json.loads`。\n\n## /screen 可筛选 / 可排序字段\n\n完整白名单（分组）见 **`references/api-reference.md` → 「/screen 字段白名单」**。筛选/排序的列名必须取自该表，否则被服务端静默忽略。\n\n## 常用 detail 字段\n\n完整字段（分组）见 **`references/api-reference.md` → 「常用 detail 字段」**。响应示例与完整定义以线上 api-docs 为准。\n\n## K 线复权（adj"},{"path":"README.md","content":"# DataQuant Connector\n\n\n
\n AI Agent Skill for Quantitative Market Data & Automated Backtesting\n
\n Daily OHLCV for 6,125+ instruments across A-shares, HK, US equities, crypto, indices, and ETFs. One link installs into your AI assistant — zero config, zero code.\n
\n About ·\n Who It's For ·\n Use Cases ·\n Coverage ·\n Install ·\n Pipeline ·\n Structure ·\n CLI ·\n API ·\n 中文版\n
\n\n---\n\n## What Is DataQuant Connector?\n\n**DataQuant Connector** is an AI Agent Skill that equips your assistant with direct access to structured financial market data — daily OHLCV (open, high, low, close, volume, amount) for over 6,125 instruments across six global markets. Built on the [DataQuant](https://app.dataquant.trade/) quantitative data platform, accessible via a simple REST interface.\n\nDesigned for quantitative backtesting workflows: describe a strategy in plain language, and your AI handles data retrieval, script generation, execution, and reporting — end to end.\n\n## Who Is This For?\n\n- **AI-assisted quantitative researchers** who design and validate trading strategies through natural-language interaction with an AI agent\n- **Developers building AI agents** that need a structured, low-latency financial data source with a simple REST interface\n- **Individual traders** who want to backtest ideas without writing data pipelines, web scrapers, or ETL jobs\n\n## Use Cases\n\nAll powered by daily OHLCV plus a per-instrument latest snapshot (valuation, size, momentum, 52-week position) — enough for screening without pulling financial statements.\n\n| Use Case | Example Prompt |\n|----------|---------------|\n| **Rule-based Strategy Backtest** | \"Backtest Kweichow Moutai 2020–2025, buy on MA20/MA60 golden cross, sell on death cross\" |\n| **Event-driven Analysis** | \"Buy CSI 300 ETF the day after a PBoC RRR cut and hold for 30 days — run this for all RRR cuts since 2015\" [^1] |\n| **Multi-asset Portfolio Backtest** | \"Equal-weight the top 10 CSI 300 constituents by volume, rebalance monthly, 2020–2025\" |\n\n[^1]: Event dates (e.g. RRR cut announcements) are resolved by the AI agent through s"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7b3zgpkdg237k84q5gk786858bzfhj\",\n \"slug\": \"dataquant-connector\",\n \"version\": \"0.1.0\",\n \"publishedAt\": 1785997899949\n}"},{"path":"references/api-reference.md","content":"# DataQuant Connector — 详细参考\n\n> 本文件是 `SKILL.md` 的外置参考，承载篇幅较大的字段表与参数表，避免占满调用上下文（progressive disclosure）。\n> 所有接口、参数、默认值、字段均核对自线上 api-docs（https://app.dataquant.trade/api-docs）及平台后端源码，确保与线上服务一致。\n\n## 市场代码\n\n| 代码 | 市场 |\n|------|------|\n| ashare | A 股 |\n| hkstock | 港股 |\n| usstock | 美股 |\n| crypto | 加密货币 |\n| indices | 全球指数 |\n| etfs | ETF |\n\nCoverage：A 股 ~3000 / 港股 ~1000 / 美股 ~2000 / 加密 ~100 / 指数 15 / ETF 11。\n\n## /screen 字段白名单（后端 `DETAIL_FILTERABLE`，完整列表）\n\n任意 `min_<列>` / `max_<列>` 或 `sort=<列>` 都必须是下列字段之一；不在白名单的列被服务端静默忽略。\n\n| 分组 | 字段 |\n|------|------|\n| 估值 | `pe_ratio` `pe_lyr` `pb_ratio` `dividend_ratio_ttm` `eps_ttm` |\n| 规模 | `total_market_cap` `circulating_market_cap` `total_shares` `float_shares` |\n| 活跃度 | `turnover_rate` `volume_ratio` `range_pct` |\n| 动量 | `change_percent` `chg_5d` `chg_10d` `chg_20d` `chg_60d` `chg_ytd` |\n| 位置/均线 | `close_vs_ma20` `close_vs_52w_high` `ma5` `ma10` `ma20` `ma60` `high_52week` `low_52week` |\n| 行情 | `volume` `amount` `open` `high` `low` `close` |\n\nscreen 返回列固定为服务端 `_SCREEN_COLUMNS`（23 列：symbol / name / market_name / date / close + 估值 / 规模 / 动量 / 均线 等）。\n\n## 常用 detail 字段（后端 `DETAIL_COLUMNS`）\n\n| 分组 | 字段 |\n|------|------|\n| 标识 | `symbol` `date` `name` `market_name` |\n| 行情 | `open` `high` `low` `close` `pre_close` `avg_price` `volume` `amount` `change` `change_percent` |\n| 估值 | `pe_ratio` `pe_fwd` `pe_lyr` `pb_ratio` `dividend_ratio_ttm` `dividend_ttm` `eps_ttm` `wb_ratio`(港股特有) |\n| 规模 | `total_market_cap`(亿元·本币) `circulating_market_cap` `total_shares` `float_shares` |\n| 动量 | `chg_5d` `chg_10d` `chg_20d` `chg_60d` `chg_ytd` |\n| 52 周 | `high_52week` `low_52week` `close_vs_52w_high` |\n| 均线 | `ma5` `ma10` `ma20` `ma60` `close_vs_ma20` |\n\n`detail` 接口默认返回全部字段；`symbol`、`date` 始终返回，不受 `fields` 过滤；detail 不含 `adj_factor`。\n\n## 套餐与配额（后端 `PLANS_DEFINITION`）\n\n| | 免费版 | 专业版 | 企业版 |\n|---|---|---|---|\n| 日配额（行） | 5,000 | 200,000 | 2,000,000 |\n| 速率（rpm，文档值） | 30 | 120 | 600 |\n| 批量标的 | 5 | 50 | 50 |\n| 单次行数 | 100 | 500 | 500 |\n\n- 配额按「返回行数」计：kline 按行数、detail 按标的数、screen 按 `limit`。\n- 速率：api-docs 文档值为上表；**服务端另设全局 `200/min` 硬上限**，超限返回 429。\n- 建议：批量请求之间留 ≥ 0.5s 间隔；先用 `/quota` 看剩余再决定分批或缩减时间跨度。\n\n## 错误码（HTTP 状态）\n\n| HTTP | 含义 | 处理 |\n|------|------|------|\n| 400 | 参数错误 | `fields` 非法 / `symbols` 超套餐上限 / `market` 不存在 / `indicator` 未知 |\n| 401 | 认证失败 | `X-API-Key` 缺失、无效或已禁用 → 让用户检查 Key |\n| 403 | 禁止访问 | 仅 dashboard 写操作的 CSRF 校验；本 Skill 只做 GET 查询，正常不会触发 |\n| 404 | 资源不存在 | 标的代码不存在 / `macro` 库未就绪 |\n| 429 | 速率或配额耗尽 | 退避后重试；仍失败则告知用户配额用尽 |\n| 503 | 服务暂不可用 | 优雅关闭中；稍后重试 |"},{"path":"skill-card.md","content":"## Description:\n\nDataQuant Connector gives agents REST API access to DataQuant market data for OHLCV and K-line retrieval, valuation snapshots, conditional screening, macro data, and quota checks across A-shares, Hong Kong stocks, U.S. stocks, crypto, indices, and ETFs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ai-ip](https://clawhub.ai/user/ai-ip)\n\n### License/Terms of Use:\n\nMIT\n\n## Use Case:\n\nExternal developers, AI-assisted quantitative researchers, and individual traders use this skill to retrieve structured DataQuant market data and guide agent-assisted backtesting, screening, and analysis workflows.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: API keys can leak if pasted into chat or passed on the command line.\n\nMitigation: Set DATAQUANT_API_KEY through a protected environment variable or secret store, and avoid sharing real keys in chat or shell history.\n\nRisk: Generated backtest code or trading analysis may be incorrect or misleading if run without review.\n\nMitigation: Review generated code and outputs before execution or investment decisions, and consider using a virtual environment with pinned dependencies.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/ai-ip/skills/dataquant-connector)\n- [Server-Resolved GitHub Repository](https://github.com/ai-ip/dataquant-connector)\n- [DataQuant API Reference](references/api-reference.md)\n- [Interactive DataQuant API Documentation](https://app.dataquant.trade/api-docs)\n- [DataQuant Homepage](https://app.dataquant.trade/)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]\n\n**Output Format:** [Markdown guidance with shell commands and JSON API output]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires a valid DataQuant API key; CLI calls return JSON from DataQuant REST endpoints.]\n\n## Skill Version(s):\n\n0.1.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"对接 DataQuant 量化数据平台，为回测与选股提供 REST API 取数通道，覆盖 A股/港股/美股/加密货币/指数/ETF 六大市场，支持 K线、估值快照、条件筛选与宏观数据。 当用户需要从 DataQuant 查询行情、K线、估值快照、条件选股或宏观数据，或消息中出现 \"DataQuant\" / \"dataquant kline\" / \"dataquant screen\" 等取数指令时启用本 Skill。 Skill: Dataquant Connector 量化数据通道 Owner: ai-ip Summary: 对接 DataQuant 量化数据平台，为回测与选股提供 REST API 取数通道，覆盖 A股/港股/美股/加密货币/指数/ETF 六大市场，支持 K线、估值快照、条件筛选与宏观数据。 当用户需要从 DataQuant 查询行情、K线、估值快照、条件选股或宏观数据，或消息中出现 \"DataQuant\" / \"dataquant kline\" / \"dataquant screen\" 等取数指令时启用本 Skill。 Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-06T06:31:39.949Z | auto - Initial release of dataquant-connector skill. - Provides REST API access t","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1541,"uniquenessScore":47,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T15:02:36.629Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T15:02:36.629Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T06:43:36.998Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}