Vnpy Futures Trading

VeighNa（原vnpy）支持中国期货自动交易执行，集成日盘/夜盘交易时段管理，并提供CSI300成分股数据下载及Alpha101/LightGBM等因子研究工作流。。

Security Scan

The skill's functionality (Chinese futures backtesting/trading and factor research) matches its documentation, but it omits declaring the runtime credentials and environment access you would expect for real data providers and trading gateways and instructs the agent to check/create local config directories — this gap is worth caution.

Purpose & Capability

The SKILL.md, use-case list, and reference files consistently describe a futures/backtesting/factor-research toolkit (VeighNa/vnpy + ZVT style pipelines). That purpose justifies references to data providers (RQData, XTQuant, eastmoney, joinquant, akshare) and trading gateways (CTP). However, the skill declares no required environment variables or credentials although real use (downloading paid data or connecting to CTP) normally requires API keys/account credentials. The absence of declared credentials is a notable omission but could be intentional if the skill only generates code/instructions rather than performing live connections.

Instruction Scope

The runtime instructions focus on data collection, pipeline, and backtesting and include preconditions that run Python checks and reference ZVT_HOME and local data dirs (e.g., creating ~/.zvt). There is no instruction in SKILL.md to read arbitrary user files or exfiltrate data, but the seed.yaml/execution_protocol text and preconditions instruct the agent to run commands and verify imports (e.g., pip install zvt, run python checks) which implies filesystem and environment access. The instructions are scoped to the stated purpose but give the agent broad discretion to install packages and create/use local directories.

Install Mechanism

There is no install spec and no code files to execute; risk from automatic installs is low in the package metadata. However, SKILL.md and seed.yaml instruct the agent to run precondition checks that could prompt the user (or the agent, if allowed) to run pip install commands — the skill itself does not include a packaged install recipe or external download URL.

Credentials

The skill does not declare any required env vars or credentials, yet its documented flows require access to third-party data services (RQData, XTQuant, joinquant) and trading gateways (CTP) which normally need API keys/accounts. References and preconditions explicitly reference and test ZVT_HOME and attempt write tests in ~/.zvt. This mismatch (no declared credentials but expectation of provider/broker credentials and filesystem writes) is a proportionality concern: if the agent is granted environment access it may read or create files and could be later asked to accept credentials without those being surfaced in the skill metadata.

Persistence & Privilege

The skill is not marked always:true and does not request persistent system-wide privileges. It does instruct creation/use of a local data directory (~/.zvt) and may run Python commands to install/check packages, but it does not modify other skills or system-wide agent configuration in the provided artifacts.

What to consider before installing

This skill appears to be a coherent trading/backtesting blueprint, but take these precautions before installing/using it: - Understand credential needs: the SKILL.md references paid data providers (RQData, XTQuant, joinquant) and broker gateways (CTP) but does not declare the required API keys/tokens. Do not paste broker or data-provider credentials into the agent or skill unless you fully trust it. - Prefer manual provisioning: if you plan to run real data downloads or live trading, prepare credentials locally and only pass them to tools you control. Consider running the skill in an isolated environment (virtualenv, container, sandbox) so any pip installs or file writes do not affect your global Python environment (note the seed files mention pip install and potential global installs). - Check where data is stored: the skill expects a ZVT_HOME (defaults to ~/.zvt) and will try to create/write there. If you want to limit disk exposure, set ZVT_HOME to a dedicated, writable folder or a mounted volume you control. - Ask for clarifications before trusting autonomous runs: request from the skill author (or registry) a clear list of external endpoints the agent will contact, an explicit list of environment variables or secrets it will request, and whether the agent will attempt to run pip install / modify system packages. - If you only want code generation (not live connections), constrain the agent: instruct it to produce code snippets or notebooks and not to perform any network connections or package installations automatically. If you want higher assurance, ask the publisher for: (1) an explicit list of required env vars/credentials (and how/where they are used); (2) an install recipe or container image so you can review/execute it locally; and (3) confirmation that the skill will not autonomously send data to external endpoints other than documented provider APIs.

VnPy 期货交易 (vnpy-futures-trading)

VeighNa（原vnpy）支持中国期货自动交易执行，集成日盘/夜盘交易时段管理，并提供CSI300成分股数据下载及Alpha101/LightGBM等因子研究工作流。

Pipeline

data_collection -> data_storage -> factor_computation -> target_selection -> trading_execution -> visualization

Top Use Cases (21 total)

CSI300 Index Data Download via RQData (UC-101)

Download historical CSI300 index constituent stock data from RQData data service for use in alpha factor research and backtesting Triggers: download index constituents, RQData, CSI300 data

CSI300 Index Data Download via XTQuant (UC-102)

Download historical CSI300 index constituent stock data from XTQuant data service for use in alpha factor research Triggers: download index constituents, XTQuant, CSI300 data

CTA Strategy Backtesting Demo (UC-110)

Backtest ATR RSI trading strategy on futures contracts to evaluate performance metrics and optimize parameters Triggers: backtesting, ATR RSI strategy, futures trading

For all 21 use cases, see references/USE_CASES.md.

Execute trigger: When user intent matches intent_router.uc_entries[].positive_terms AND user uses action verb (run/execute/跑/执行/backtest/fetch/collect)

What I'll Ask You

• Target market: A-share (default), HK, or crypto? (US stocks in ZVT are half-baked — stockus_nasdaq_AAPL exists but coverage is thin)
• Data source / provider: eastmoney (free, no account), joinquant (account+paid), baostock (free, good history), akshare, or qmt (broker)?
• Strategy type: MACD golden-cross, MA crossover, volume breakout, fundamental screen, or custom factor?
• Time range: start_timestamp and end_timestamp for backtest period
• Target entity IDs: specific stocks (stock_sh_600000) or index components (SZ1000)?

Semantic Locks (Fatal)

ID	Rule	On Violation
SL-01	Execute sell orders before buy orders in every trading cycle	halt
SL-02	Trading signals MUST use next-bar execution (no look-ahead)	halt
SL-03	Entity IDs MUST follow format entity_type_exchange_code	halt
SL-04	DataFrame index MUST be MultiIndex (entity_id, timestamp)	halt
SL-05	TradingSignal MUST have EXACTLY ONE of: position_pct, order_money, order_amount	halt
SL-06	filter_result column semantics: True=BUY, False=SELL, None/NaN=NO ACTION	halt
SL-07	Transformer MUST run BEFORE Accumulator in factor pipeline	halt
SL-08	MACD parameters locked: fast=12, slow=26, signal=9	halt

Full lock definitions: references/LOCKS.md

Top Anti-Patterns (25 total)

• AP-ZVT-183: 除权因子为 inf/NaN 时直接参与乘法导致复权静默失败
• AP-ZVT-179: 第三方数据接口超限后异常被吞噬，数据静默缺失
• AP-ZVT-183B: HFQ（后复权）与 QFQ（前复权）K 线表使用错误导致因子计算漂移

All 25 anti-patterns: references/ANTI_PATTERNS.md

Evidence Quality Notice

[QUALITY NOTICE] This crystal was compiled from blueprint finance-bp-081. Evidence verify ratio = 31.4% and audit fail total = 23. Generated results may have uncaptured requirement gaps. Verify critical decisions against source files (LATEST.yaml / LATEST.jsonl).

Reference Files

File	Contents	When to Load
references/seed.yaml	V6+ 全量权威 (source-of-truth)	有行为/决策争议时必读
references/ANTI_PATTERNS.md	25 条跨项目反模式	开始实现前
references/WISDOM.md	跨项目精华借鉴	架构决策时
references/CONSTRAINTS.md	domain + fatal 约束	规则冲突时
references/USE_CASES.md	全量 KUC-* 业务场景	需要完整示例时
references/LOCKS.md	SL-* + preconditions + hints	生成回测/交易代码前
references/COMPONENTS.md	AST 组件地图（按 module 拆分）	查 API 时

---

Compiled by Doramagic crystal-compilation-v6.1 from finance-bp-081 blueprint at 2026-04-22T13:00:31.772009+00:00. See human_summary.md for non-technical overview.