Finance Quant Skills
Thirteen skills for quantitative trading on China's A-share market: AKShare and BaoStock data, Backtrader and RQAlpha backtests, QMT and JoinQuant docs
- 469 ★ on the repository
- Last commit
Broad access
Why this level
- The miniqmt skill places and cancels trade orders through the QMT client, including on a live account
- pywencai needs session cookies and jqdatasdk and tushare need tokens, which grant access to accounts
- Skill scripts run Python and call external data sources
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/finance-quant-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The miniqmt skill places and cancels trade orders through the QMT client, including on a live account
- pywencai needs session cookies and jqdatasdk and tushare need tokens, which grant access to accounts
- Skill scripts run Python and call external data sources
This is third-party code. Review the repository files before installing.
What it does
The repository collects thirteen skills for quantitative trading, mostly on the Chinese stock market. They fall into four groups. Data: akshare (stocks, futures, options, funds, FX, bonds, crypto and macroeconomics with no registration), baostock (candles and financial statements for A-shares), pywencai (natural-language queries to Tonghuashun's iWencai), tdxquant, miniqmt, jqdatasdk and tushare. Backtests: backtrader and rqalpha. Strategy development: akquant, qmt-strategy and joinquant-strategy. Research: equity-researcher for institutional-style reports, listed as an official Kimi skill. Each skill lives in its own folder with a SKILL.md, and some have scripts. For example, akshare calls scripts/stock_data.py with --type, --symbol, --start, --end, --period and --adjust and returns JSON quotes. The miniqmt skill connects to the MiniQMT client through the xtquant library: it reads quotes (xtdata) and can place and cancel orders (xttrader). The skills install as Claude Code and Codex plugins or through npx skills add lzwme/finance-quant-skills.
Who it is for. For quants and investors who test strategies on the Chinese stock market and want an agent to write strategy code and fetch data.
Good fit when
- You need daily candles for a stock with adjustment through akshare and a chart
- A Backtrader or RQAlpha strategy has to be written and run on history
- An idea must be ported to the QMT client or the JoinQuant platform using their API references
- You want to screen stocks with a natural-language query through pywencai
- The agent should assemble a company report in investment-brief form through equity-researcher
Not a fit when
- You need Russian exchange data: the set targets the Chinese market, and separate MCP servers cover MOEX
- You want to trade without manual confirmation: the miniqmt skill can place orders, so test automated trading in simulation first
- You lack a token or client for the gated sources: jqdatasdk, tushare, pywencai, tdxquant and miniqmt need access
- You want a ready trading bot: the skills provide instructions and scripts, not a strategy
Example request
Fetch daily candles for stock 600519 for 2024 through akshare and write a moving-average crossover strategy in BacktraderLimitations
Data sources have different terms: baostock and akshare are free and need no registration, pywencai needs a cookie, jqdatasdk and tushare need a token, and tdxquant and miniqmt need an installed client (for miniqmt, the QMT terminal, working with simulated and real accounts).
- Skill descriptions are written in Chinese.
- The akshare scripts need Python 3.9 or newer and the akshare library, which the docs advise to keep updated.
- equity-researcher is described as an official Kimi skill; the rest are by the repository owner.
- Data and backtest results are not investment advice.
How to disable. Delete the skill folders from the agent's skills directory, run /plugin uninstall for installed plugins or npx skills remove. Revoke jqdatasdk and tushare tokens with the data providers.
FAQ
How do I install Finance Quant Skills in Claude Code?
Run /plugin marketplace add lzwme/finance-quant-skills, then /plugin install quant-skills@finance-quant-skills. Add the quant-data-api plugin for data and quant-docs for documentation.
Is registration needed to get data?
Not for akshare and baostock. jqdatasdk and tushare ask for a token, pywencai for a session cookie, and tdxquant and miniqmt run through an installed client.
How is miniqmt different from qmt-strategy?
miniqmt connects to the MiniQMT client from an external Python program through xtquant. qmt-strategy helps write strategies inside the QMT client itself and supplies an API reference.
Can the skills be used in Codex?
Yes. The repository has a .codex-plugin/plugin.json manifest: add the marketplace with codex plugin marketplace add lzwme/finance-quant-skills and pick the plugin in /plugins.
Which markets does akshare cover?
Stocks, futures, options, funds, FX, bonds, indices, crypto and macroeconomics. There are separate scripts per data category.
Discussion
No questions or reviews yet.
Related
SkillsA skill with Chinese A-share market data: quotes, research reports, financials, news and 11 more categories from 34 sources, no keys
A set of installable finance skills for the agent: news, stock data, sentiment, forecasting, signals, reports and search
Claude for Financial Services CN
claude-for-financial-services-cn
An unofficial set of 63 skills for Claude Code: DCF, comps, LBO, notes and decks for Chinese equities with Wind, iFind and AkShare data
A set of skills for individual investors and traders: market review, stock screening, technical analysis, trade planning, journaling and post-trade review
A skill and MCP server that give an agent quotes, candles and ticker search for the China, Hong Kong and US markets
A skill that writes a nine-chapter report on a US, Hong Kong or China stock: reverse DCF, EPV, earnings-quality review and scripted valuation
README in short
The page gives the repository structure and four install routes: ask an agent, the Claude Code marketplace, npx skills, and the Codex marketplace. A separate tip shows how to expose one skills folder to several agents with symbolic links. It continues with a table of all skills by category and access method, a new-skill template and lists of external resources on quantitative trading.
README badge
Original SKILL.md
---
name: akshare
description: AKShare 开源金融数据接口库，提供股票、期货、期权、基金、外汇、债券、指数、加密货币等全品类金融数据；当用户需要获取各类金融市场数据时使用
metadata: {"openclaw":{"emoji":"📈","requires":{"bins":["python3"]}}}
keywords:
- 股票
- 期货
- 期权
- 基金
- 外汇
- 债券
- 指数
- 加密货币
- 宏观经济
- AKShare
---
# AKShare 金融数据获取
## 任务目标
- 本 Skill 用于：通过 AKShare 接口获取全品类金融市场数据
- 能力包含：股票、期货、期权、基金、外汇、债券、指数、加密货币、宏观经济等数据
- 触发条件：用户提及 AKShare 或需要获取各类金融数据时
## 前置准备
- 依赖说明：安装 akshare 库（已包含在 dependency 中）
- 凭证配置：AKShare 无需注册或 API Key，直接调用即可使用
- 环境要求：Python 3.9+，建议定期更新 `pip install akshare --upgrade`
## 操作步骤
- 标准流程：
1. 确定数据需求 — 智能体理解用户意图（股票/期货/基金/外汇等）
2. 调用对应脚本 — 根据数据类型选择脚本
3. 解析结果 — 智能体分析返回的 JSON 格式数据
- 脚本调用映射：
- 股票数据 → `python scripts/stock_data.py --type hist --symbol 000001 --start 20240101 --end 20240131`
- 期货数据 → `python scripts/futures_data.py --type daily --exchange CFFEX --start 20240101 --end 20240131`
- 基金数据 → `python scripts/fund_data.py --type etf --symbol 510300`
- 外汇数据 → `python scripts/forex_data.py --type spot --symbol usd`
- 宏观经济 → `python scripts/macro_data.py --type gdp`