vynn-backtester

Run trading strategy backtests with natural language — powered by Vynn

3,891 stars

Best use case

vynn-backtester is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Run trading strategy backtests with natural language — powered by Vynn

Teams using vynn-backtester should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/vynn-backtester/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/beee003/vynn-backtester/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/vynn-backtester/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How vynn-backtester Compares

Feature / Agentvynn-backtesterStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Run trading strategy backtests with natural language — powered by Vynn

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Vynn Backtester

Backtest any trading strategy with natural language. Get Sharpe ratio, returns, drawdown, and full equity curves in seconds.

## What it does

- **Natural language strategies**: Describe your strategy in plain English and Vynn translates it into a runnable backtest
- **Structured strategies**: Power users can pass precise entry/exit rules as JSON
- **Full metrics**: Sharpe ratio, total return, max drawdown, win rate, trade count, and equity curve
- **Multi-ticker**: Backtest across any combination of stocks, ETFs, or indices
- **Strategy comparison**: Compare multiple strategies head-to-head, ranked by Sharpe ratio
- **No infrastructure**: No local data downloads, no dependencies beyond Python stdlib

## Setup

1. Get a free API key at [the-vynn.com](https://the-vynn.com) (10 backtests/month, no credit card)
2. Set `VYNN_API_KEY` in your environment or skill config
3. Run `/backtest "your strategy here"` from any OpenClaw agent

### Quick start

```bash
# Sign up (instant, returns your API key)
curl -X POST https://the-vynn.com/v1/signup -H "Content-Type: application/json" -d '{"email": "you@example.com"}'

# Set the key
export VYNN_API_KEY="vynn_free_..."
```

## Usage examples

### Simple natural language backtest

```
/backtest "RSI mean reversion on AAPL, 2 year lookback"
```

### Momentum strategy

```
/backtest "MACD crossover on SPY with 20/50 EMA filter"
```

### Multi-ticker portfolio

```
/backtest --tickers AAPL,MSFT,GOOGL --strategy "momentum top 3"
```

### Structured entry/exit rules

```
/backtest '{"entries": [{"indicator": "RSI", "op": "<", "value": 30}], "exits": [{"indicator": "RSI", "op": ">", "value": 70}]}' --tickers AAPL
```

### Compare strategies

```python
from plugin import VynnBacktesterPlugin

vynn = VynnBacktesterPlugin()
results = vynn.compare(
    strategies=[
        "RSI mean reversion",
        "MACD crossover",
        "Bollinger band breakout",
    ],
    tickers=["SPY"],
)
for r in results:
    print(f"{r.strategy}: Sharpe={r.sharpe_ratio}, Return={r.total_return_pct}%")
```

## Environment Variables

| Variable | Required | Description | Default |
|---|---|---|---|
| `VYNN_API_KEY` | Yes | Your API key from the-vynn.com | -- |
| `VYNN_BASE_URL` | No | Override API base URL (for self-hosted instances) | `https://the-vynn.com/v1` |

## External Endpoints

| Endpoint | Purpose | Data Sent |
|---|---|---|
| `https://the-vynn.com/v1/backtest` | Execute a strategy backtest | Strategy text, ticker list, lookback period |
| `https://the-vynn.com/v1/signup` | Free API key registration | Email address |

## Security & Privacy

- All requests authenticated via `X-API-Key` header
- Strategy descriptions and ticker lists are sent to the Vynn API for backtest execution
- No trading data, portfolio holdings, or personal information is stored beyond the backtest run
- Backtest results are ephemeral and not persisted on Vynn servers
- No credentials are stored by the skill -- only your API key in environment variables
- Source code is fully open: [github.com/beee003/astrai-openclaw](https://github.com/beee003/astrai-openclaw)

## Model Invocation

This skill does not invoke any LLM models. It sends strategy descriptions to the Vynn backtest engine, which is a quantitative execution engine (not an AI model). No prompts or completions are generated.

## Pricing

- **Free**: 10 backtests/month, all features, no credit card required
- **Pro** ($29/mo): Unlimited backtests, priority execution, extended lookback periods

Related Skills

backtester

3891
from openclaw/skills

Professional backtesting framework for trading strategies. Tests SMA crossover, RSI, MACD, Bollinger Bands, and custom strategies on historical data. Generates equity curves, drawdown analysis, and performance metrics.

Finance & Investing

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research