Eastmoney Market Data
HKUDS/Vibe-Trading
Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.
Queries Futu quotes, options, fundamentals and accounts and places orders through the Futu OpenAPI Python SDK, defaulting to simulated trading.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add qusong0627/QuantMind --skill futuapi -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qusong0627/QuantMind futuapi --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/futuapi .claude/skills/futuapi && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "futuapi" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/futuapi into .claude/skills/futuapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "futuapi", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/qusong0627/QuantMind/tree/master/skills/futuapiType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add qusong0627/QuantMind --skill futuapi -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qusong0627/QuantMind futuapi --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/futuapi .agents/skills/futuapi && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "futuapi" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/futuapi into .agents/skills/futuapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "futuapi", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add qusong0627/QuantMind --skill futuapi -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qusong0627/QuantMind futuapi --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/futuapi .cursor/skills/futuapi && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "futuapi" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/futuapi into .cursor/skills/futuapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "futuapi", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/qusong0627/QuantMind.git --path skills/futuapi--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add qusong0627/QuantMind --skill futuapi -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qusong0627/QuantMind futuapi --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/futuapi .gemini/skills/futuapi && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "futuapi" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/futuapi into .gemini/skills/futuapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "futuapi", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install qusong0627/QuantMind futuapiInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add qusong0627/QuantMind --skill futuapi -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/futuapi .github/skills/futuapi && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "futuapi" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/futuapi into .github/skills/futuapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "futuapi", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add qusong0627/QuantMind --skill futuapi -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install qusong0627/QuantMind futuapi --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/futuapi .opencode/skills/futuapi && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "futuapi" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/futuapi into .opencode/skills/futuapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "futuapi", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
futuapiQueries Futu quotes, options, fundamentals and accounts and places orders through the Futu OpenAPI Python SDK, defaulting to simulated trading.
Written in Chinese, this skill acts as a programming assistant for the Futu OpenAPI Python SDK. It covers market data (quotes, K-lines, snapshots, order books, ticks, time-sharing charts), symbol and news search, option chains with expiry dates, implied volatility and exercise probability, fundamentals, account, position and order queries, real-time subscriptions, crypto, prediction markets and technical indicators such as MA, MACD, RSI, KDJ and BOLL.
The agent identifies the intent, loads only the matching reference file, consults the docs for field mappings, rate limits or troubleshooting, then runs the right script from the quote, trade or subscribe folders and returns JSON. Trading defaults to the simulated environment, and live orders need a two-step confirmation flag plus an explicit question to you. Read-only queries can run directly.
It replies in the language you use, defaulting to Chinese. The OpenD gateway must be running locally, and the futu-api package must be recent enough, with a newer version required for crypto. If OpenD is not installed, the skill points to an install command. Ticker formats are market-prefixed, such as HK.00700, US.AAPL, SH.600519 and CC.BTC.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 2e93d9a. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
BashReadWriteEditFrom allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
pippythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Futu OpenAPI Market and Trading Assistant loads about 3.3k tokens when it runs, and up to ~41k if it reads all its reference files. Until then it costs about 144 tokens; SKILL.md has 841 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Bash, Read, Write, EditAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from qusong0627/QuantMind at commit 2e93d9a, republished under its AGPL-3.0 licence (© qusong0627). 841 words, ~3,280 tokens.
.claude/skills/futuapi/SKILL.md (or your agent's skills folder). This skill also uses 196 other files; get the full folder from GitHub.你是富途 OpenAPI 编程助手,帮助用户使用 Python SDK 获取行情数据、执行交易操作、订阅实时推送。
收到用户请求后按以下顺序处理:
references/*.md(不全量加载,避免浪费上下文)docs/STOCK_SCREEN_FIELDS.md、持仓查 docs/FIELD_MAPPING.md、限频查 docs/API_LIMITS.md、报错查 docs/TROUBLESHOOTING.mdscripts/{quote,trade,subscribe}/*.pySIMULATE;实盘须 --confirmed 两步 + AskUserQuestion 确认;只读类(行情/基本面)可直接跑--json 输出便于解析;分析类用 references/analysis-frameworks.md 模板组织输出(非 raw 数据堆)根据用户输入的语言自动回复。用户使用英文提问则用英文回复,使用中文提问则用中文回复,其他语言同理。语言不明确时默认使用中文。技术术语(如代码、API 名称、参数名)保持原文不翻译。
⚠️ 安全警告:交易涉及真实资金。默认使用 模拟环境(TrdEnv.SIMULATE),除非用户明确要求使用正式环境。
127.0.0.1:11111(可通过环境变量配置)futu-api >= 10.4.6408futu-api >= 10.5.6508(首次提供 OpenCryptoTradeContext)。检测方法:python -c "from futu import OpenCryptoTradeContext" 2>&1ImportError / cannot import name,运行升级:pip install --upgrade "futu-api>=10.5.6508"环境检查(SDK 版本、版本戳、OpenD 连通性)已内置到脚本的
common.py中,首次运行自动完整检查,1 小时内后续脚本跳过。检查未通过时脚本会报错并提示运行/install-futu-opend。
from futu import *当用户说"启动 OpenD"、"打开 OpenD"、"运行 OpenD"时,先检测本地是否已安装 OpenD,再决定下一步操作。
Windows:
Get-ChildItem -Path "C:\Users\$env:USERNAME\Desktop","C:\Program Files","C:\Program Files (x86)","D:\" -Recurse -Filter "*OpenD-GUI*.exe" -ErrorAction SilentlyContinue | Select-Object -First 1 -ExpandProperty FullNameMacOS:
ls /Applications/*OpenD-GUI*.app 2>/dev/null || mdfind "kMDItemFSName == '*OpenD-GUI*'" 2>/dev/null | head -1Start-Process "找到的exe路径"open "/Applications/找到的.app"/install-futu-opend 进入安装流程HK.00700(腾讯)、HK.09988(阿里巴巴)US.AAPL(苹果)、US.TSLA(特斯拉)SH.600519(贵州茅台)SZ.000001(平安银行)SG.D05(星展集团)、SG.U11(大华银行)MY.1155(马来亚银行)、MY.1295(Public Bank)JP.7203(丰田汽车)、JP.9984(软银集团)SG.CNmain(A50 指数期货主连)、SG.NKmain(日经期货主连)CC.BTC、CC.ETH、CC.SOLCC.BTCUSD、CC.ETHUSD、CC.BTCHKD(币对代码不带 /)get_stock_filter --market JP:支持价格 / 市值排序等基础筛选。注意:API 只返回筛选/排序涉及的字段,其他字段(如未指定排序时的 price、未指定价格筛选时的 market_val)会是 0get_stock_screen:JSON 配置 {"filters": [{"type": "simple_field", "field": "MARKET", "values": ["JP"]}]},全 JP 市场覆盖约 3800 只正股;复杂因子(基本面 / 技术形态 / 资金流等)优先用 V2get_option_chain / get_option_expiration_date 会返回错误码 -1,错误信息 期权标的仅支持港美正股ETF以及港指美指get_option_screen --markets JP_STOCK/JP_INDEX 接口可调,all_count 有统计(JP_STOCK ≈ 24500,JP_INDEX ≈ 13500),但 data 始终为空——SDK / 服务端的半完工状态,无可用期权明细get_broker_queue)仅支持港股,日股调用会报错JP.<数字股票编号>,如 JP.6758(索尼)get_stock_filter --market SG:支持价格 / 市值排序等基础筛选(实测全市场约 820 只标的)get_stock_screen:JSON 配置 {"filters": [{"type": "simple_field", "field": "MARKET", "values": ["SG"]}]}get_warrant_screen --market SG:SG 是窝轮筛选支持的三个市场之一(HK/SG/MY)OptMarketCategory 不含 SG,get_option_chain / get_option_screen 无法用 SGget_broker_queue)仅支持港股SG.<数字或字母代码>,如 SG.D05(星展)、SG.S3N(Top Glove)get_stock_filter --market MY:支持价格 / 市值排序等基础筛选(实测全市场约 1221 只标的)get_stock_screen:JSON 配置 {"filters": [{"type": "simple_field", "field": "MARKET", "values": ["MY"]}]}get_warrant MY.1155 拉正股的窝轮列表;get_warrant_screen --market MY 全市场筛选(MY 是窝轮筛选支持的三个市场之一 HK/SG/MY)OptMarketCategory 不含 MY,get_option_chain / get_option_screen 无法用 MYget_broker_queue MY.xxxx 接口可调(ret=0),但买卖盘队列始终为空——马股无券商挂单数据get_stock_quote / get_market_snapshot / F10 会返回行情权限不足。统计类接口(V2 选股、窝轮筛选)通常不受权限限制MY.<数字股票编号>,如 MY.1155(MAYBANK);窝轮代码形如 MY.11552A(正股代码 + 序号)当用户用中文名、英文名或 Ticker 描述标的时,映射为完整代码。完整速查表(港股/美股/A股:腾讯→HK.00700、苹果→US.AAPL、茅台→SH.600519 等)见 references/quote-commands.md(顶部小节)。不在表中的标的根据你的知识判断市场和代码,不确定时用 AskUserQuestion 询问用户。
不需要手动指定 --market 参数。 交易脚本会自动从 --code 的前缀(如 US.、HK.、CC.)推断交易市场。如果传入的 --market 与代码前缀不一致,脚本会自动以代码前缀为准并打印警告。
这是代码层的硬约束,无论是否传 --market 参数,市场都以代码前缀为准。
交易脚本会校验 --code 的基本格式:必须包含 . 分隔符,且前缀必须是 US、HK、SH、SZ、SG、MY、JP、CC 之一。格式不合法时脚本会直接报错退出。
| 特性 | 模拟交易 SIMULATE | 正式交易 REAL |
|---|---|---|
| 资金 | 虚拟资金,无风险 | 真实资金 |
| 交易密码 | 不需要,可直接下单 | 需要,用户须在 OpenD GUI 界面手动解锁交易密码后才能下单 |
| 默认 | ✅ 本技能默认 | 需用户明确指定 |
交易密码说明:模拟交易无需任何密码即可下单;实盘交易需用户先打开 OpenD GUI 界面,点击「解锁交易」按钮输入交易密码完成解锁,之后才能通过 API 下单。如果 API 返回
unlock needed错误,说明尚未解锁,请提示用户在 OpenD GUI 中操作。
模拟交易支持「比赛账户」,由 sim_acc_type=COMPETITION 标识。比赛账户与普通模拟账户的差别:
| 维度 | 美股比赛账户 | 港股比赛账户 |
|---|---|---|
| 市场 | TrdMarket.US | TrdMarket.HK |
acc_type | MARGIN(支持融资融券) | CASH(不支持融资融券) |
trdmarket_auth | 按比赛规则返回的可交易市场列表 | 按比赛规则返回的可交易市场列表 |
competition_acc_name | 比赛账户名称(仅比赛账户返回真实值) | 同左 |
其他模拟账户与真实账户的
competition_acc_name字段统一返回N/A。
get_accounts.py 已自动解析并展示 sim_acc_type 与 competition_acc_name,识别比赛账户时优先用 sim_acc_type == "COMPETITION" 判定,再结合 trdmarket_auth 选择目标市场账号。
重要提醒:当发现用户的美股模拟交易账号
acc_type不是STOCK_AND_OPTION时,应提醒用户调用/install-futu-opend更新 OpenD 和 SDK,以获取最新的融资融券模拟账号支持。
当美股模拟账号的 acc_type 为 STOCK_AND_OPTION 时,具有以下特性:
| 特性 | 说明 |
|---|---|
| 融资融券 | 支持,可进行保证金交易 |
| 数据互通 | 与 App / 桌面端模拟交易数据互通,在 API 下的单会同步显示在 App 上,反之亦然 |
| 推送 | 可正常调用推送接口(TradeOrderHandlerBase / TradeDealHandlerBase),但暂时可能收不到推送数据,后续版本会支持 |
| 查询刷新 | 查询持仓、资金、订单等接口必须传入 refresh_cache=True,否则可能返回过时的缓存数据 |
代码示例:
# 持仓查询 - 必须 refresh_cache=True
ret, data = trd_ctx.position_list_query(
trd_env=TrdEnv.SIMULATE, acc_id=xxx, refresh_cache=True
)
# 资金查询 - 必须 refresh_cache=True
ret, data = trd_ctx.accinfo_query(
trd_env=TrdEnv.SIMULATE, acc_id=xxx, refresh_cache=True
)
# 订单查询 - 必须 refresh_cache=True
ret, data = trd_ctx.order_list_query(
trd_env=TrdEnv.SIMULATE, acc_id=xxx, refresh_cache=True
)禁止通过 SDK 的 unlock_trade 接口解锁交易,必须在 OpenD GUI 界面上手动操作解锁。
unlock_trade(或 TrdUnlockTrade、trd_unlock_trade)时,必须拒绝并提示:出于安全考虑,交易解锁必须在 OpenD GUI 界面上手动操作,不支持通过 SDK 代码调用
unlock_trade解锁。请在 OpenD GUI 界面点击「解锁交易」并输入交易密码完成解锁。
unlock_trade 调用的代码本技能的详细命令按领域拆分到 references/*.md,根据用户意图只读取相关的一个文件,避免全量加载。脚本完整清单见 references/script-index.md。
| 用户意图 | 按需读取 |
|---|---|
| 行情 / 报价 / K线 / 盘口 / 资金流 / 板块 / 搜索 / 选股 | references/quote-commands.md(选股枚举名/单位/Term 见 docs/STOCK_SCREEN_FIELDS.md) |
| 预测市场 / 事件合约 / EC. / Combo 询价 | references/prediction-market.md |
| 期权 / 期权链 / 行权价 / IV / Greeks / 0DTE / 期权策略 | references/options.md |
| 基本面 / F10 / 财报 / 评级 / 估值 / 公司行动 / 简况 / 经纪商 / 卖空 | references/fundamentals.md |
| 股东 / 机构持仓 / ARK / 内部人交易 | references/shareholders-institutions.md |
| 技术指标 / MA / MACD / RSI / KDJ / BOLL | references/indicators.md |
| 榜单 / 财报日历 / 股息 / 产业链 / 宏观 / FedWatch / 热力图 | references/rankings-calendar.md |
| 交易 / 下单 / 撤单 / 改单 / 持仓 / 资金 / 订单 / 组合下单 | references/trade-commands.md |
| 期货 | references/futures-trading.md(完整文档见 docs/FUTURES_TRADING.md) |
| 加密货币 / BTC / ETH | references/crypto-commands.md |
| 订阅 / 推送 | references/subscribe-push.md |
| 分析框架(财报点评/持仓诊断/选股排序) | references/analysis-frameworks.md |
| 脚本清单(查某个脚本是否存在/路径) | references/script-index.md |
其他参考资料(docs/ 目录,按需读取):docs/API_LIMITS.md(频率/额度/分页)、docs/API_REFERENCE.md(完整函数签名)、docs/FIELD_MAPPING.md(持仓/资金字段与 APP 对齐)、docs/TROUBLESHOOTING.md(已知问题与错误处理)。
运行脚本前,必须先确认脚本文件是否存在。如果默认路径 skills/futuapi/scripts/ 下找不到脚本,则自动到 skill 的 base directory 下查找。
执行流程:
skills/futuapi/scripts/{category}/{script}.py 是否存在{SKILL_BASE_DIR}/scripts/{category}/{script}.py(其中 {SKILL_BASE_DIR} 为 skill 加载时系统提示的 "Base directory for this skill" 路径)示例:假设要运行 get_accounts.py,skill base directory 为 /home/user/.claude/skills/futuapi:
# 先检查默认路径
ls skills/futuapi/scripts/trade/get_accounts.py 2>/dev/null
# 如果不存在,则使用 skill base directory
ls /home/user/.claude/skills/futuapi/scripts/trade/get_accounts.py 2>/dev/null找到脚本后,用该路径执行 python {找到的路径} [参数...]。后续命令示例均使用默认路径 skills/futuapi/scripts/,实际执行时按此规则查找。
完整脚本清单(行情 130 + 交易 24 + 订阅 17)见
references/script-index.md。
所有脚本支持 --json 参数输出 JSON 格式,便于程序解析。
大多数交易脚本支持:
--market: US, HK, HKCC, CN, SG, MY, JP--trd-env: REAL, SIMULATE(默认: SIMULATE)--acc-id: 账户 ID(可选)| 变量 | 说明 | 默认值 |
|---|---|---|
FUTU_OPEND_HOST | OpenD 主机 | 127.0.0.1 |
FUTU_OPEND_PORT | OpenD 端口 | 11111 |
FUTU_TRD_ENV | 交易环境 | SIMULATE |
FUTU_DEFAULT_MARKET | 默认市场 | NONE |
FUTU_TRADE_PWD | 已移除,需在 OpenD GUI 手动解锁 | |
FUTU_ACC_ID | 默认账户 ID | (首个账户) |
FUTU_SECURITY_FIRM | 券商标识(见下表) | (自动探测) |
FUTU_SECURITY_FIRM 可选值:
| 值 | 地区 |
|---|---|
FUTUSECURITIES | 富途证券(香港) |
FUTUINC | 富途(美国) |
FUTUSG | 富途(新加坡) |
FUTUAU | 富途(澳大利亚) |
FUTUCA | 富途(加拿大) |
FUTUJP | 富途(日本) |
FUTUMY | 富途(马来西亚) |
创建交易连接 OpenSecTradeContext、OpenFutureTradeContext 或 OpenCryptoTradeContext 时,security_firm 参数默认填 SecurityFirm.NONE。
首次涉及交易操作时,如果环境变量 FUTU_SECURITY_FIRM 未设置,运行 get_accounts.py --json 获取所有账户(脚本自动遍历所有 SecurityFirm),查看实盘账户的 security_firm 字段,作为后续所有交易命令的 --security-firm 参数。
探测代码示例及详细说明参见
docs/TROUBLESHOOTING.md
完整函数签名(65 个接口)参见
docs/API_REFERENCE.md。接口限制(频率、额度、分页等)参见docs/API_LIMITS.md。
完整的已知问题、错误处理表、自定义 Handler 模板参见
docs/TROUBLESHOOTING.md。
ai_type 参数报错:如果创建 OpenQuoteContext、OpenSecTradeContext、OpenFutureTradeContext 或 OpenCryptoTradeContext 时报错提示没有 ai_type 参数(如 unexpected keyword argument 'ai_type'),说明 SDK 版本过低,需升级至 >= 10.4.6408:
pip install --upgrade "futu-api>=10.4.6408"OpenCryptoTradeContext 不存在:运行加密货币脚本时若提示 当前 futu-api X.X.X 未提供 OpenCryptoTradeContext,说明 SDK 版本低于 10.5.6508,运行升级:
pip install --upgrade "futu-api>=10.5.6508"SIMULATE,除非用户明确要求正式交易--market:脚本会自动从 --code 前缀推断市场(代码硬约束)--trd-env REALplace_order.py 与 place_combo_order.py 在实盘环境下强制要求 --confirmed 参数。第一次调用不带 --confirmed 会返回订单摘要并退出(exit code 2),确认无误后第二次带 --confirmed 才真正下单。同时仍应先用 AskUserQuestion 向用户确认订单详情。如果 API 返回解锁错误,提示用户在 OpenD GUI 界面手动解锁交易密码。例外:当用户要求运行其自己编写的策略脚本时,无需每次下单前二次确认,因为策略脚本的下单逻辑由用户自行控制--json 参数便于解析OpenFutureTradeContext:普通期货下单仍建议按「期货交易命令」直接生成代码。已支持脚本路径:预测市场(EC.)可用 place_order.py / place_combo_order.py;查询期货/EC 账户持仓、订单、成交、撤改单等传 --ctx-type FUTURE(或代码为 EC. 时自动切换);EC 实盘交易账户须开通 PREDICTION 权限docs/API_LIMITS.md--price 必须用 get_option_strategy_analysis.py 的 bid1/ask1;禁止对各腿 get_snapshot.py 后手动加减买卖价© qusong0627, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 196 other files (scripts, references) in skills/futuapi of qusong0627/QuantMind.
Open the folder on GitHubat commit 2e93d9a
Futu OpenAPI Market and Trading Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Futu OpenAPI Market and Trading Assistant this skillqusong0627/QuantMind | 1.7k | — | ~3.3k | Automated safety check: Notes | AGPL-3.0 | |
| Eastmoney Market DataHKUDS/Vibe-Trading | 35k | — | ~1k | Automated safety check: Pass | MIT | |
| Stock Deep Analysis Workflowwbh604/UZI-Skill | 7.1k | — | ~9.1k | Automated safety check: Notes | MIT | |
| OKX Market DataHKUDS/Vibe-Trading | 35k | — | ~1.3k | Automated safety check: Pass | MIT | |
| SEC EDGAR Filings FetcherHKUDS/Vibe-Trading | 35k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Supply Chain Bottleneck Hunterxbtlin/ai-berkshire | 17k | — | ~2.6k | Automated safety check: Pass | MIT |
HKUDS/Vibe-Trading
Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.
wbh604/UZI-Skill
Runs a staged deep analysis of a single stock on China A-share, Hong Kong and US markets, ending in an HTML report with valuation models and investor-panel scores.
HKUDS/Vibe-Trading
Retrieves public OKX cryptocurrency market data such as spot prices, candlesticks, funding rates and open interest through the OKX V5 REST API, with no authentication.
HKUDS/Vibe-Trading
Fetches U.S. SEC EDGAR data: resolves tickers to CIK numbers, lists recent 10-K, 10-Q and 8-K filings with document URLs, and pulls XBRL financial series.
xbtlin/ai-berkshire
Scans a long-running industry trend for supply chain chokepoints, aiming to find second- and third-layer suppliers that the market has not yet priced in.
BlockRunAI/ClawRouter
Reads structured prediction market data for Polymarket, Kalshi and other venues through a local BlockRun gateway: markets, search, leaderboards, wallet analytics and odds.
qusong0627/QuantMind
Produces a post-market review report for the China A-share market from local QuantDB data, news sentiment and model signals, ending in a next-day direction call.
qusong0627/QuantMind
Turns a plain-language model training request into a validated QuantMind training config file that can be imported from the Model Training page.
qusong0627/QuantMind
Covers the Tiger Brokers OpenAPI Python SDK for market data, stock, futures and options trading, push subscriptions, a CLI and an MCP server, defaulting to paper trading.
qusong0627/QuantMind
Guides an agent through the Tiger Brokers OpenAPI C++ SDK for build setup, market data, orders and real-time push, defaulting to paper trading.
qusong0627/QuantMind
Guides building C# and .NET apps on the Tiger Brokers OpenAPI SDK: setup, market data, orders, accounts, options and real-time push, defaulting to paper trading.
qusong0627/QuantMind
Reference guides for building Go trading apps on the Tiger Brokers OpenAPI: SDK setup, market data, stock, futures and options orders, accounts and push streams.
Categories
Queries Futu quotes, options, fundamentals and accounts and places orders through the Futu OpenAPI Python SDK, defaulting to simulated trading. Written in Chinese, this skill acts as a programming assistant for the Futu OpenAPI Python SDK. It covers market data (quotes, K-lines, snapshots, order books, ticks, time-sharing charts), symbol and news search, option chains with expiry dates, implied volatility and exercise probability, fundamentals, account, position and order queries, real-time subscriptions, crypto, prediction markets and technical indicators such as MA, MACD, RSI, KDJ and BOLL.
Futu OpenAPI Market and Trading Assistant fits situations like: looking up quotes, K-lines or order books for a listed stock; checking option chains, expiry dates and implied volatility; reviewing financial statements, ratings or shareholder changes; placing or cancelling orders in the simulated trading environment.
Run `npx skills add qusong0627/QuantMind --skill futuapi -a claude-code`. Or copy the skill folder (skills/futuapi in qusong0627/QuantMind) into .claude/skills/futuapi in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qusong0627/QuantMind --skill futuapi -a codex`. Or copy the skill folder (skills/futuapi in qusong0627/QuantMind) into .agents/skills/futuapi in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qusong0627/QuantMind --skill futuapi -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/futuapi, .gemini/skills/futuapi, .github/skills/futuapi and .opencode/skills/futuapi in your project.
Going by SKILL.md and its folder, Futu OpenAPI Market and Trading Assistant needs the command-line tools its instructions call (pip and python). Our summary lists: Futu OpenD running locally, version 10.4.6408 or later; The futu-api Python package. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Futu OpenAPI Market and Trading Assistant is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 37k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Futu OpenAPI Market and Trading Assistant: Eastmoney Market Data (HKUDS/Vibe-Trading, 35k stars), Stock Deep Analysis Workflow (wbh604/UZI-Skill, 7.1k stars), OKX Market Data (HKUDS/Vibe-Trading, 35k stars) and SEC EDGAR Filings Fetcher (HKUDS/Vibe-Trading, 35k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
qusong0627 (a GitHub user) maintains it in qusong0627/QuantMind, which has 1,717 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 8, 2026.
Source: qusong0627/QuantMind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.