← Back to Skills Marketplace
SMA Crossover Backtester with PyFolio Analytics (
OHLC Data Printer Utility (
Backtrader Event Driven
by
Tang Weigang
· GitHub ↗
· v0.3.3
· MIT-0
117
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install backtrader-event-driven
Description
运行经典双均线交叉策略回测，事件驱动模拟信号生成与持仓，输出 PyFolio 绩效报告。
README (SKILL.md)
Backtrader 事件回测 (backtrader-event-driven)
运行经典双均线交叉策略回测，事件驱动模拟信号生成与持仓，输出 PyFolio 绩效报告。
Pipeline
data_collection -> data_storage -> factor_computation -> target_selection -> trading_execution -> visualization
Top Use Cases (2 total)
SMA Crossover Backtester with PyFolio Analytics (UC-101)
Implements a classic dual moving average crossover trading strategy using backtrader, generating LONG/LONGSHORT signals when fast and slow SMAs cross, Triggers: backtrader, SMA crossover, moving average
OHLC Data Printer Utility (UC-102)
Provides a minimal backtrader strategy that logs and prints OHLC (Open, High, Low, Close) data in CSV format for debugging and verifying data feed int Triggers: backtrader, data printing, OHLC logging
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-086. Evidence verify ratio = 28.8% and audit fail total = 15. 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-086 blueprint at 2026-04-22T13:00:35.750880+00:00.
See human_summary.md for non-technical overview.
Usage Guidance
This skill appears to be a legitimate backtesting helper, but the package metadata underreports what it actually needs. Before installing or running it: (1) confirm you have Python 3.12+ and an isolated virtual environment; (2) expect to need zvt and possibly data-provider credentials (eastmoney is free, joinquant/qmt require accounts) — ask the skill author to declare required env vars (e.g., JOINQUANT_TOKEN, QMT_API_KEY) and explicit install steps; (3) don't run it in a production / credentialed machine until you verify what commands it will execute (seed.yaml requests host install recipes and precondition pip installs); (4) review/validate the references/seed.yaml and LOCKS.md semantics (they enforce fatal constraints like next-bar execution and T+1 rules); and (5) run first in an isolated sandbox to confirm no unexpected network calls or writes. If the author cannot provide explicit dependency and credential declarations, treat the skill as untrusted.
Capability Analysis
Type: OpenClaw Skill
Name: backtrader-event-driven
Version: 0.3.3
The skill bundle is a highly structured framework for quantitative trading backtests using the Backtrader and ZVT libraries. It contains extensive documentation, semantic locks (e.g., SL-01 to SL-12 in LOCKS.md), and domain constraints (e.g., SHARED-BT-LAB-001 in CONSTRAINTS.md) specifically designed to prevent common financial modeling errors like lookahead bias and survivorship bias. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the provided instructions and configuration files (seed.yaml) are focused on ensuring the integrity and accuracy of financial simulations.
Capability Tags
Capability Assessment
Purpose & Capability
SKILL.md and companion files clearly implement a backtesting pipeline built on Python and ZVT (data recorders, providers like eastmoney/joinquant, ZVT_HOME). However the registry metadata lists no required binaries, no required env vars, and no install spec. The declared surface (no dependencies) does not match the skill's actual needs (Python 3.12+, zvt, data providers).
Instruction Scope
Runtime instructions (SKILL.md + seed.yaml + LOCKS.md/PC preconditions) tell an agent to run Python checks, potentially run pip install zvt, touch files under ~/.zvt, and enforce many fatal semantic locks (T+1, no look-ahead, specific DataFrame schemas). These are reasonable for a backtest tool, but the instructions also expect the agent to run environment-changing commands and to use external data providers (which may require credentials) — none of which are declared or scoped in the registry metadata.
Install Mechanism
The skill is instruction-only and has no declared install spec (lowest-risk form). However seed.yaml/execution_protocol references host_adapter.install_recipes[] and the SKILL.md header explicitly requires Python 3.12+ with the 'uv' package manager; this implicit install expectation isn't surfaced in the registry. The absence of an explicit, traceable install mechanism (e.g., a known package release) is an omission worth flagging.
Credentials
No environment variables or credentials are declared, yet the content references ZVT_HOME, pip installing zvt, and choosing providers like joinquant/qmt/eastmoney (some of which require API keys/accounts). The skill may ask users for provider credentials at runtime but does not declare or justify any required secret/env vars in the manifest — disproportionate and missing declarations.
Persistence & Privilege
always:false and no install spec mean the skill does not demand persistent, forced inclusion. However seed.yaml's execution_protocol instructs agents to 'reload seed.yaml', run preconditions, and run host install recipes if present — which implies the agent may execute environment-modifying commands during use. Autonomous invocation is allowed (platform default) and should be considered together with the other concerns.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install backtrader-event-driven - After installation, invoke the skill by name or use
/backtrader-event-driven - 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 Backtrader 事件回测; 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
v0.2.0
Doramagic crystal portfolio v0.2.0. Full 5-layer bp-009 standard. github.com/tangweigang-jpg/doramagic-skills
Metadata
Frequently Asked Questions
What is Backtrader Event Driven?
运行经典双均线交叉策略回测，事件驱动模拟信号生成与持仓，输出 PyFolio 绩效报告。 It is an AI Agent Skill for Claude Code / OpenClaw, with 117 downloads so far.
How do I install Backtrader Event Driven?
Run "/install backtrader-event-driven" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Backtrader Event Driven free?
Yes, Backtrader Event Driven is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Backtrader Event Driven support?
Backtrader Event Driven is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Backtrader Event Driven?
It is built and maintained by Tang Weigang (@tangweigang-jpg); the current version is v0.3.3.
More Skills