Skip to content
TrustedSkillsbeta
Back to all skills

Strategy Compare

Checked
marketcalls·vlatest·other

Compares multiple strategies to identify optimal approaches based on defined criteria, boosting decision-making efficiency and effectiveness.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add marketcalls/vectorbt-backtesting-skills --skill strategy-compare -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

marketcalls

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned marketcalls/vectorbt-backtesting-skills at 05d9e8b12f.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
05d9e8b12f
Manifest
.claude/skills/strategy-compare/SKILL.md
Scanned
1 file, 46 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

The strategy-compare skill allows AI agents to evaluate and rank multiple trading strategies against each other using historical data. It leverages the VectorBT library to calculate performance metrics like Sharpe ratio, drawdown, and total return for side-by-side analysis.

When to use it

  • You need to determine which of several algorithmic approaches performs best under specific market conditions.
  • You want to validate a new strategy by comparing its risk-adjusted returns against established benchmarks.
  • You are optimizing a portfolio by identifying the most efficient strategies based on custom criteria.

Key capabilities

  • Executes backtests for multiple strategies simultaneously within a single session.
  • Calculates and compares standard performance metrics including profit factor, max drawdown, and annualized return.
  • Generates structured output suitable for ranking strategies or feeding into further decision-making logic.

Example prompts

  • "Compare the performance of a moving average crossover strategy against an RSI mean-reversion strategy using 5 years of data."
  • "Rank three different volatility-based trading models by their Sharpe ratio and maximum drawdown."
  • "Analyze how a trend-following bot performed compared to a buy-and-hold approach during the last market correction."

Tips & gotchas

Ensure you provide sufficient historical data context for accurate backtesting results, as short timeframes may yield misleading comparisons. Be aware that this skill relies on the VectorBT library, so complex custom indicators may require specific formatting or pre-processing before comparison.