Agent skill

Mootdx A-Share Data

by HKUDS in HKUDS/Vibe-Trading

Pulls A-share price data from 通达信 (TDX) servers through the mootdx library over TCP, free and without an API key, as a stable fallback when akshare scraping is throttled.

MITAuto-check passedBusiness, Finance & HR

Install Mootdx A-Share Data

skills CLI
$ npx skills add HKUDS/Vibe-Trading --skill mootdx -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUDS/Vibe-Trading mootdx --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent/src/skills/mootdx .claude/skills/mootdx && rm -rf skills-src

Use ~/.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/

Facts

Skill name
mootdx
GitHub stars
35k
Token cost
~1.1k tokens
SKILL.md length
437 words
Files
1
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

Pulls A-share price data from 通达信 (TDX) servers through the mootdx library over TCP, free and without an API key, as a stable fallback when akshare scraping is throttled.

  • Fetching daily A-share OHLCV when akshare's East Money source is throttled
  • SKILL.md covers Overview, Quick Start, Frequency Codes and Key Methods, plus 5 more sections
  • Calls pip
  • Pulling intraday, weekly or monthly bars with mootdx frequency codes

What it does

Mootdx speaks the native TDX binary protocol over TCP, which avoids the HTTP scrapers that periodically fail under load, with akshare's East Money source as the usual example. It serves public market data only, with no token, per-IP throttling or captcha. Installation includes a second pip step that restores a modern httpx version the rest of the project needs.

The skill lists the key methods: get_k_data for daily bars with a date range, bars for intraday, weekly and monthly data using integer frequency codes, minute for the current day, quotes for a real-time snapshot, stocks for ticker lists and F10 or finance for fundamentals. Six-digit symbols are mapped to Shanghai, Shenzhen or Beijing from their prefix, suffixed forms like 000001.SZ are accepted by the loader, and the column names and the vol-to-volume rename are described.

When your agent uses it

  • Fetching daily A-share OHLCV when akshare's East Money source is throttled
  • Pulling intraday, weekly or monthly bars with mootdx frequency codes
  • Getting a real-time level 1 snapshot for an A-share ticker
  • Mapping six-digit symbols to Shanghai, Shenzhen or Beijing exchanges

Example prompts

  • “Fetch daily bars for 600519 with mootdx.”
  • “Get 5-minute bars for 000001 using mootdx.”
  • “Show the real-time quote for 600519.SH.”
  • “Switch my A-share loader to mootdx because akshare keeps timing out.”

Requirements

  • Python with mootdx and a modern httpx, installed through pip

What it can do on your machine

Read from SKILL.md and the folder at commit e532650. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com
    • mootdx.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mootdx A-Share Data loads about 1.1k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 437 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated 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); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/Vibe-Trading at commit e532650, republished under its MIT licence (© HKUDS). 437 words, ~1,050 tokens.

Download SKILL.mdSave it as .claude/skills/mootdx/SKILL.md (or your agent's skills folder).
name
mootdx
description
Mootdx A-share market data via TCP-direct 通达信 servers. Free, no API key, no IP rate limits. Use as the stable A-share OHLCV fallback when akshare's East Money scrape is throttled.
category
data-source

Overview

Mootdx talks the native 通达信 (TDX) binary protocol over TCP, bypassing the HTTP scrapers that periodically fail under load (akshare → East Money is the canonical example). Public market data only — no token, no per-IP throttling, no captcha.

Mootdx pins httpx<0.26 in setup.py, but only uses basic httpx.Client/get APIs that are forward-compatible. The second pip install restores the modern httpx that the rest of Vibe-Trading (MCP server, fastmcp) needs.

Quick Start

python
from mootdx.quotes import Quotes

client = Quotes.factory(market="std")  # std = 沪/深/京; ext = 期货/期权 (upstream-broken)

# Daily OHLCV with a date range (preferred API).
df = client.get_k_data(code="000001", start_date="2025-01-01", end_date="2025-02-01")

# Intraday — offset-from-latest only, no native date range.
df_15m = client.bars(symbol="600519", frequency=1, offset=800)

Frequency Codes

bars(frequency=N) uses integer codes from mootdx.consts:

CodeBar
81m
05m
115m
230m
31H
41D
51W
61M

get_k_data() is daily only but accepts start_date / end_date. For intraday, bars() returns the latest N rows — the built-in loader over-fetches offset=800 then clips to the requested window.

Key Methods

MethodUseReturns
get_k_data(code, start_date, end_date)Daily OHLCV with date range[open, close, high, low, vol, amount, date, code]
bars(symbol, frequency, offset=800)Intraday / weekly / monthly[open, close, high, low, vol, amount, datetime, volume, ...]
minute(symbol)Current trading day 1m barsSame schema as bars()
quotes(symbol)Real-time L1 snapshot{price, bid, ask, volume, ...}
stocks(market)List all tickers on an exchangeDataFrame of code/name
F10(symbol) / finance(symbol)Fundamentals snapshotHeterogeneous dict

Symbol Format

  • Pure 6-digit: "000001", "600519", "835174" — mootdx auto-detects exchange from prefix:
    • 60x / 68x → SH
    • 00x / 30x / 002 / 003 → SZ
    • 4x / 8x → BJ
  • The built-in loader also accepts "000001.SZ", "600519.SH", "835174.BJ" and strips the suffix.
Show full SKILL.md (200 more words)Show less

Column Names

get_k_data() returns lowercase English: open / close / high / low / vol / amount / date / code. The built-in loader renames vol → volume to match the project's OHLCV contract.

bars() returns the same OHLC columns plus a duplicate volume (alongside the legacy vol), a datetime string column, and decomposed year / month / day / hour / minute columns.

Built-in Loader

backtest/loaders/mootdx_loader.py is registered as the mootdx source. Fallback chain for a_share is [tushare, mootdx, akshare] — tushare wins when a token is present; mootdx wins when no token but TCP egress works; akshare is the broadest fallback.

python
from backtest.runner import run
result = run(strategy=..., source="mootdx")  # explicit override

Known Limitations

LimitationWorkaround
北交所 (BJ): get_k_data raises KeyError, bars() returns empty (upstream missing data)Loader logs a warning and skips BJ symbols — use akshare or tushare
Extended market (futures/options) returns empty as of v0.11.7 (upstream issue)Use tushare/akshare for futures
Each bars() page is 800 rows; loader paginates back up to 25 pages (≈10y daily / ≈5y 1H / ≈3mo 1m)For longer 1m history use tushare minute bars
Server selection has cold-start latency (first call picks the fastest server)First call may be ~2s slower
Returns data in 前复权 by default — no API parameter for 不复权Use tushare/akshare if raw prices are required

Reference Docs

© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agent/src/skills/mootdx of HKUDS/Vibe-Trading.

Open the folder on GitHubat commit e532650

Compare with similar skills

Mootdx A-Share Data 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.

Mootdx A-Share Data compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mootdx A-Share Data this skillHKUDS/Vibe-Trading35k—~1.1kAutomated safety check: PassMIT
WorldQuant BRAIN Alpha ResearchQuantML-Research/wq-alpha-research405—~4.9kAutomated safety check: PassNone
A-Share Daily Reviewqusong0627/QuantMind1.7k—~1.9kAutomated safety check: PassAGPL-3.0
Quant Buddy Page Publisherpseudo-longinus/quant-buddy-skills193—~12kAutomated safety check: PassMIT
Senpi Market PulseSenpi-ai/senpi-skills134—~4.3kAutomated safety check: PassApache-2.0
One-Line Stock Analysis Reportsmingli30119/stock-analysis619—~8.6kAutomated safety check: WarnMIT

Similar skills

  • WorldQuant BRAIN Alpha Research

    QuantML-Research/wq-alpha-research

    Chinese-language playbook for WorldQuant BRAIN alphas: choose fields, write expressions, backtest, diagnose check failures, tune turnover, submit and build portfolios.

    405 GitHub stars~4.9k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • A-Share Daily Review

    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.

    1.7k GitHub stars~1.9k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Quant Buddy Page Publisher

    pseudo-longinus/quant-buddy-skills

    Publishes quantitative analysis or existing images, HTML and PDF files as shareable Quant Buddy live pages and dashboards, and interprets existing page links.

    193 GitHub stars~12k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Senpi Market Pulse

    Senpi-ai/senpi-skills

    Produces a structured cross-asset read of the day across crypto, equities, indices, commodities and macro, using a bundled engine for data and ending with a signals brief.

    134 GitHub stars~4.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • One-Line Stock Analysis Reports

    mingli30119/stock-analysis

    Turns a single request like 'analyze this stock' into a full research report, pulling 30-plus data sources into an interactive HTML page with charts.

    619 GitHub stars~8.6k tokensUpdated 4 mo ago
    Business, Finance & HRAuto-check: warnings
  • 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.

    7.1k GitHub stars~9.1k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check: notes

More from HKUDS/Vibe-Trading

All 89 skills in this repo
  • 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.

    35k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • OKX Market Data

    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.

    35k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • SEC EDGAR Filings Fetcher

    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.

    35k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • A-Share ST Risk Screener

    HKUDS/Vibe-Trading

    Predicts whether a mainland China A-share company risks an ST or *ST warning after its next annual report, using financial thresholds and Sina penalty records.

    35k GitHub stars~4.9k tokensUpdated yesterday
    Auto-check passed
  • Breaks a structural trend such as AI infrastructure into its physical supply chain and ranks lesser-known listed companies sitting on each bottleneck.

    35k GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed
  • Plans and drafts an eight-part, roughly 120k-word investigative series on one company, built around a strict fact-check pass rather than fast drafting.

    35k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Mootdx A-Share Data

What does Mootdx A-Share Data do?

Pulls A-share price data from 通达信 (TDX) servers through the mootdx library over TCP, free and without an API key, as a stable fallback when akshare scraping is throttled. Mootdx speaks the native TDX binary protocol over TCP, which avoids the HTTP scrapers that periodically fail under load, with akshare's East Money source as the usual example. It serves public market data only, with no token, per-IP throttling or captcha.

When should I use Mootdx A-Share Data?

Mootdx A-Share Data fits situations like: fetching daily A-share OHLCV when akshare's East Money source is throttled; pulling intraday, weekly or monthly bars with mootdx frequency codes; getting a real-time level 1 snapshot for an A-share ticker; mapping six-digit symbols to Shanghai, Shenzhen or Beijing exchanges.

How do I install Mootdx A-Share Data in Claude Code?

Run `npx skills add HKUDS/Vibe-Trading --skill mootdx -a claude-code`. Or copy the skill folder (agent/src/skills/mootdx in HKUDS/Vibe-Trading) into .claude/skills/mootdx in your project. Claude Code loads it when a task matches its description.

How do I install Mootdx A-Share Data in Codex?

Run `npx skills add HKUDS/Vibe-Trading --skill mootdx -a codex`. Or copy the skill folder (agent/src/skills/mootdx in HKUDS/Vibe-Trading) into .agents/skills/mootdx in your project. Codex loads it when a task matches its description.

Can I use Mootdx A-Share Data in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/Vibe-Trading --skill mootdx -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mootdx, .gemini/skills/mootdx, .github/skills/mootdx and .opencode/skills/mootdx in your project.

What does Mootdx A-Share Data need to run?

Going by SKILL.md and its folder, Mootdx A-Share Data needs the command-line tools its instructions call (pip). Our summary lists: Python with mootdx and a modern httpx, installed through pip.

Does Mootdx A-Share Data access the network?

SKILL.md names 2 domains. As links in the text: github.com and mootdx.com. This is read from the text; nothing was executed.

Is Mootdx A-Share Data safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Mootdx A-Share Data use?

Mootdx A-Share Data is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mootdx A-Share Data use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mootdx A-Share Data?

Skills that share tags, products or a category with Mootdx A-Share Data: WorldQuant BRAIN Alpha Research (QuantML-Research/wq-alpha-research, 405 stars), A-Share Daily Review (qusong0627/QuantMind, 1.7k stars), Quant Buddy Page Publisher (pseudo-longinus/quant-buddy-skills, 193 stars) and Senpi Market Pulse (Senpi-ai/senpi-skills, 134 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mootdx A-Share Data?

HKUDS (a GitHub organization) maintains it in HKUDS/Vibe-Trading, which has 35,043 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 8, 2026.

Source: HKUDS/Vibe-Trading on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.