marketcalls

marketcalls / vectorbt-backtesting-skills

Public

Agentic coding skills for backtesting trading strategies using VectorBT. Supports Indian, US, and Crypto markets with realistic transaction cost modeling, TA-Lib indicators, QuantStats tearsheets, and 12 ready-made strategy templates.

docs.openalgo.in agent-skills backtesting monte-carlo optimization python
88
21
89% credibility
Found Feb 26, 2026 at 62 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A set of skills for an AI coding assistant to generate and execute backtests of popular trading strategies using Indian stock market data.

How It Works

1
🔍 Discover Backtesting Helpers

You stumble upon a collection of handy tools that let an AI buddy help test stock trading ideas on Indian markets.

2
📥 Add Skills to AI Friend

With one simple command, you bring these special abilities into your AI coding companion so it's ready to assist.

3
🔌 Link Up Market Data

You set up a straightforward connection to a service that grabs historical prices from Indian exchanges like NSE.

4
💻 Prep Your Test Space

You create a cozy workspace on your computer with the right tools to run and view trading experiments safely.

5
💬 Chat: Test a Strategy

You tell your AI something fun like 'Backtest EMA crossover on SBIN' and it whips up a full test script just for you.

6
▶️ Launch the Test

You run the script, it pulls in real market history, simulates trades, and crunches the numbers behind the scenes.

📊 Admire the Results

Stunning interactive charts and stats appear, revealing how your strategy stacks up against benchmarks like Nifty or safe savings.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 62 to 88 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is vectorbt-backtesting-skills?

This Python project packs Claude code skills for backtesting trading strategies with VectorBT on Indian market data from OpenAlgo. Chat commands like /backtest ema-crossover SBIN NSE D or /optimize rsi RELIANCE NSE D generate full scripts that fetch NSE/BSE data, run simulations, print stats versus Nifty benchmarks, plot interactive charts, and export trades to CSV. It skips the boilerplate of data setup and VectorBT plumbing, letting you prototype strategies via Claude code agents in seconds.

Why is it gaining traction?

Unlike raw VectorBT notebooks or generic backtesters, it hooks into Claude code integration for conversational backtesting—/quick-stats for inline metrics or /strategy-compare to pit EMA versus RSI side-by-side. Quick npx skills install pulls in vectorbt-expert knowledge for any chat, with free Claude code skills handling Indian exchanges out-of-the-box. Devs dig the Plotly dashboards and OpenAlgo API for realistic fees, slippage-free tests.

Who should use this?

Algo traders tweaking momentum or Supertrend on Niftybees/SBIN, quant devs building Indian market portfolios, or VectorBT users wanting Claude github integration for rapid iteration. Ideal for backtesting dual-momentum rotations or RSI accumulation without firing up separate data pipelines.

Verdict

Grab it if you're in Indian markets and use Claude code skills—solid docs and MIT license make claude code install painless, despite 19 stars signaling early maturity. 0.8999999761581421% credibility score reflects niche focus, but examples prove it delivers; test locally before production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.