← Back to list
vectorbt Checked
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and ri…
8.2Overall rating
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "vectorbt" skill by following the instructions at https://skill123.me/install/vectorbt.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/vectorbt.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 19 KBAbout this skill
Overview
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics
Source
- Repo: https://github.com/agiprolabs/claude-trading-skills
- Path: skills/vectorbt
Score breakdown
Trigger
4.0
Description covers What with good keywords (vectorized backtesting, parameter optimization, portfolio simulation) but no When/When-Not or trigger variants: 3+2+3+0=8/20
Structure
9.3
348-line SKILL.md, two references and two scripts, inline load cues, Files section: 4+5+3+2=14/15
Workflow
8.0
Task-oriented 5-step workflow; tool-wrapper pattern with concrete API usage; walk-forward validation guards overfitting; realistic crypto fee/slippage parameters: 5+5+5+3+2=20/25
Content
10.0
Concise imperative, every code block directly runnable with realistic values: 10/10
Engineering
10.0
Valid frontmatter; scripts have shebangs, zero API deps, synthetic data documented; all paths exist: 10/10
Security
10.0
Fully offline scripts; no eval/base64/destructive ops, no secrets, no injection; capabilities match declared scope: 20/20
High-quality vectorbt wrapper skill: 5-step workflow, parameter tables, crypto-realistic fee/slippage guidance, two offline scripts on synthetic data (no API keys), walk-forward validation as an explicit overfitting guard. Capability manifest: no file/env/credential reads, no writes, no network in scripts (Yahoo Finance only mentioned as documentation example), no persistence — capabilities match declared scope.