← Back to Skills Marketplace

Lean Cloud Backtest

Name: Lean Cloud Backtest
Author: tangweigang-jpg

by Tang Weigang · GitHub ↗ · v0.3.3 · MIT-0

cross-platform ⚠ suspicious

119

Downloads

Stars

Active Installs

Versions

Install in OpenClaw

/install lean-cloud-backtest

Description

通过 LEAN 引擎搭建多市场量化研究与回测环境，支持 QuantBook 历史数据获取、技术指标计算和自定义因子建模。。

README (SKILL.md)

LEAN 云端回测 (lean-cloud-backtest)

通过 LEAN 引擎搭建多市场量化研究与回测环境，支持 QuantBook 历史数据获取、技术指标计算和自定义因子建模。

Pipeline

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

Top Use Cases (8 total)

C# QuantBook Research Environment Setup (`UC-101`)

Provides a foundational C# research environment template for loading QuantBook and fetching historical data across multiple asset classes for analysis Triggers: C#, QuantBook, research environment

Python QuantBook Basic Research with Indicators (`UC-102`)

Provides a Python research environment template demonstrating QuantBook setup, historical data fetching, price plotting, and Bollinger Bands indicator Triggers: Python, QuantBook, Bollinger Bands

C# Comprehensive QuantBook API and Data Fetching (`UC-103`)

Comprehensive C# template demonstrating QuantBook API cloud connectivity, project listing, and multiple methods for fetching historical data with diff Triggers: C#, QuantBook, API

For all 8 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-100. Evidence verify ratio = 23.0% and audit fail total = 20. 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-100 blueprint at 2026-04-22T13:00:45.713977+00:00. See human_summary.md for non-technical overview.

Usage Guidance

This skill appears to be a legitimate LEAN/QuantBook backtest guide, but it has some transparency issues: (1) SKILL.md expects Python 3.12+, pip installs, and uses the ZVT_HOME env var and external data providers (eastmoney, joinquant, akshare, qmt) — none of these credentials or install steps are declared in the manifest. Before installing or running the skill, confirm you are comfortable letting the agent run pip installs and shell/python commands, and be prepared to supply provider API keys (if you plan to use paid providers). If you need least-privilege assurance, ask the skill author to: (a) declare required environment variables and any credential names in the manifest; (b) provide an explicit install spec (or confirm no install will occur); and (c) document exactly which external endpoints the skill will contact and when. If you plan to run this on a machine with sensitive environment variables, do not enable it until those gaps are clarified.

Capability Analysis

Type: OpenClaw Skill Name: lean-cloud-backtest Version: 0.3.3 The 'lean-cloud-backtest' skill bundle is a highly sophisticated framework designed to provide a rigorous quantitative research and backtesting environment. It focuses heavily on preventing common financial engineering errors (such as lookahead bias, survivorship bias, and improper data normalization) through a comprehensive set of 'Semantic Locks' (SL-01 to SL-12) and 'Fatal Constraints' (finance-C-*). The bundle includes detailed documentation of anti-patterns in popular quant libraries like ZVT, Qlib, and Zipline. While it contains complex instructions for the AI agent to enforce these rules and validate outputs (e.g., checking for physically impossible returns in result.csv), all behaviors are strictly aligned with the stated purpose of financial modeling. No indicators of data exfiltration, malicious persistence, or harmful prompt injection were identified.

Capability Tags

cryptorequires-walletrequires-sensitive-credentials

Capability Assessment

✓ Purpose & Capability

Name, description, and use-cases all describe multi-market quantitative research and backtesting using LEAN/QuantBook/ZVT-like tooling. The referenced components, anti-patterns, and use-cases are coherent with that purpose.

⚠ Instruction Scope

SKILL.md instructs the agent to run runtime checks and shell/python commands (e.g. python3 -c 'import zvt...', python3 -m pip install zvt, touch/unlink tests) and to read the ZVT_HOME environment variable — but the manifest declares no required env vars or explicit runtime permissions. The instructions also direct the agent to use external data providers (eastmoney, joinquant, akshare, qmt) which may require credentials; those credentials are not declared. While these actions are expected for a backtest skill, the manifest does not surface them, creating a transparency gap.

ℹ Install Mechanism

The skill is instruction-only and has no install spec in the registry (low static risk). However SKILL.md and seed.yaml explicitly expect package installation and precondition runs (pip install zvt, pip checks, host_adapter.install_recipes). That means at runtime the agent may install packages and modify the environment despite no install metadata being declared.

⚠ Credentials

The manifest lists no required environment variables or credentials, but the runtime instructions access ZVT_HOME and expect interactions with external data providers (some of which require API keys/accounts). This mismatch means the skill may attempt to read environment variables or prompt for credentials that were not declared, increasing the chance of accidental exposure of secrets or unexpected network requests.

✓ Persistence & Privilege

The skill does not request always:true and does not include an install spec that would force persistent system-level changes. It is user-invocable and allows autonomous invocation (platform default). No evidence it modifies other skills or global agent config.

How to Use

Make sure OpenClaw is installed (local or Docker)
Run the install command in chat: /install lean-cloud-backtest
After installation, invoke the skill by name or use /lean-cloud-backtest
Provide required inputs per the skill's parameter spec and get structured output

Version History

v0.3.3

v0.3.3: bilingual metadata injected. H1 shows LEAN 云端回测; tagline replaced with skill-specific Chinese hook; tags upgraded to Level 1-4.

v0.3.1

Remove install.sh — knowledge-only bundle. Host AI consumes directly from URL; no user-side installation needed. Fixes ClawHub suspicious flag.

v0.3.0

Doramagic crystal portfolio v0.3.0. Full 5-layer bp-009 standard. github.com/tangweigang-jpg/doramagic-skills

Metadata

Slug lean-cloud-backtest

Version 0.3.3

License MIT-0

All-time Installs 0

Active Installs 0

Total Versions 3

Frequently Asked Questions

What is Lean Cloud Backtest?

通过 LEAN 引擎搭建多市场量化研究与回测环境，支持 QuantBook 历史数据获取、技术指标计算和自定义因子建模。。 It is an AI Agent Skill for Claude Code / OpenClaw, with 119 downloads so far.

How do I install Lean Cloud Backtest?

Run "/install lean-cloud-backtest" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Lean Cloud Backtest free?

Yes, Lean Cloud Backtest is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Lean Cloud Backtest support?

Lean Cloud Backtest is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Lean Cloud Backtest?

It is built and maintained by Tang Weigang (@tangweigang-jpg); the current version is v0.3.3.

More Skills