← 返回 Skills 市场
BacktestBot
作者
Collier King
· GitHub ↗
· v0.0.2
511
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install backtestbot
功能描述
Backtest trading strategies against historical market data with performance analytics and risk metrics
使用说明 (SKILL.md)
BacktestBot
Backtest trading strategies against historical market data with detailed performance analytics.
What it does
BacktestBot enables you to define, test, and evaluate trading strategies using historical data, including:
- Strategy definition — describe strategies in natural language or structured rules (entry/exit signals, position sizing, stop losses)
- Historical simulation — run strategies against years of tick or daily data across equities, options, futures, and crypto
- Performance metrics — Sharpe ratio, max drawdown, win rate, profit factor, CAGR, and trade-level breakdown
- Risk analysis — value-at-risk, correlation to benchmarks, worst-case drawdown periods, and tail risk metrics
- Comparison — test multiple strategy variants side-by-side and rank by risk-adjusted returns
Usage
Ask your agent to backtest strategies and analyze results:
- "Backtest a mean reversion strategy on SPY using RSI below 30 as entry over the last 5 years"
- "Compare buy-and-hold vs momentum rotation across the S&P 500 sectors since 2020"
- "What is the max drawdown if I use a 2% trailing stop on AAPL swing trades?"
- "Optimize the lookback period for my moving average crossover strategy on QQQ"
Configuration
Set the following environment variables:
BACKTESTBOT_API_KEY— API key for BacktestBot. Used to authenticate requests for historical OHLCV data, strategy simulations, and performance metrics.BACKTESTBOT_DATA_DIR— (optional) local directory for cached historical data. Defaults to~/.backtestbot/data.
安全使用建议
This skill appears to do what it says (backtesting), but the package provides no source code, homepage, or endpoint documentation — so you cannot verify where your BACKTESTBOT_API_KEY or any strategy/data will be sent. Before installing or setting BACKTESTBOT_API_KEY: (1) prefer to obtain the key from a known/trustworthy provider and confirm the service's endpoint and privacy policy, (2) create a scoped or revocable API key with least privilege, (3) avoid using production accounts or real brokerage credentials for testing, (4) if you set BACKTESTBOT_DATA_DIR, point it to a controlled directory and confirm what is cached, and (5) be prepared to revoke the API key if you notice unexpected activity. If the publisher can supply a homepage, API docs, or contact info, re-evaluate once those are available.
功能分析
Type: OpenClaw Skill
Name: backtestbot
Version: 0.0.2
The skill bundle defines a 'BacktestBot' for trading strategy analysis. It requires an API key (`BACKTESTBOT_API_KEY`) for authentication with an implied external service and optionally uses a local directory (`BACKTESTBOT_DATA_DIR`) for caching historical data. The `SKILL.md` provides descriptive information and usage examples, but contains no instructions for the agent to perform malicious actions, exfiltrate data, establish persistence, or execute arbitrary commands. All described functionalities align with the stated purpose of backtesting financial strategies.
能力评估
Purpose & Capability
The name/description (backtesting + analytics) align with requesting an API key to a backtest service. Asking for a BACKTESTBOT_API_KEY is proportionate to that purpose. However, the registry entry lists no source, homepage, or implementation details, which means you cannot verify where your API key will be sent or how data will be handled.
Instruction Scope
SKILL.md describes backtesting capabilities and references an optional BACKTESTBOT_DATA_DIR for caching, but it does not specify endpoints, request formats, or where network requests are sent. The SKILL.md documents BACKTESTBOT_DATA_DIR as an optional variable but that variable is not listed in the declared requires.env block—this mismatch is a minor inconsistency. Because the instructions lack explicit trustable endpoints or telemetry/privacy statements, it's unclear what data (strategy definitions, historical data, or results) will be transmitted off-host.
Install Mechanism
This is an instruction-only skill with no install spec or code files, so nothing will be written to disk or downloaded during install. That lowers the attack surface relative to skills that fetch external binaries.
Credentials
Only a single required credential (BACKTESTBOT_API_KEY) is declared, which is proportionate for an external backtesting API. The optional BACKTESTBOT_DATA_DIR is mentioned but not declared in requires.env. There are no unrelated or extra credentials requested, but because the API key will be used to authenticate network calls to an unverified service, you should treat it as sensitive and only provide a key with limited scope.
Persistence & Privilege
The skill does not request 'always: true' and is user-invocable only. It does not declare any system-wide configuration changes or elevated persistence. Autonomous invocation is allowed by default but is not combined here with other high-risk flags.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install backtestbot - 安装完成后，直接呼叫该 Skill 的名称或使用
/backtestbot触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.0.2
- Added OpenClaw metadata indicating that BACKTESTBOT_API_KEY is required.
- Clarified configuration instructions for environment variables, specifying `BACKTESTBOT_API_KEY` is for authentication and that `BACKTESTBOT_DATA_DIR` is optional with a default path.
- Updated version to 0.0.2.
v0.0.1
Initial release of BacktestBot.
- Backtest trading strategies using historical market data across various asset classes.
- Define strategies in natural language or structured trading rules.
- Analyze with advanced performance metrics: Sharpe ratio, max drawdown, win rate, CAGR, and more.
- Includes risk assessment: value-at-risk, worst-case drawdown, and tail risk analytics.
- Compare multiple strategy variants and rank by risk-adjusted returns.
- Requires environment variables for API key and data directory configuration.
元数据
常见问题
BacktestBot 是什么？
Backtest trading strategies against historical market data with performance analytics and risk metrics. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 511 次。
如何安装 BacktestBot？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install backtestbot」即可一键安装，无需额外配置。
BacktestBot 是免费的吗？
是的，BacktestBot 完全免费（开源免费），可自由下载、安装和使用。
BacktestBot 支持哪些平台？
BacktestBot 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 BacktestBot？
由 Collier King（@collierking）开发并维护，当前版本 v0.0.2。
推荐 Skills