← Back to Skills Marketplace
quant-trading-backtrader
by
gmsx000-cloud
· GitHub ↗
· v1.0.0
985
Downloads
1
Stars
7
Active Installs
1
Versions
Install in OpenClaw
/install quant-trading-backtrader
Description
Build, backtest, and optimize quantitative trading strategies in Python using Backtrader with support for indicators, risk management, and reporting.
Usage Guidance
This package behaves like a simple Backtrader example and contains no obvious exfiltration or secret access, but proceed cautiously because the source is unknown and the bundle contains a suspicious npm-style package.json that lists Python packages (likely a packaging mistake). Before running: 1) Verify the publisher or obtain the SKILL from a trusted source. 2) Inspect code yourself (you already have examples/sma_crossover.py) and search for any network calls or subprocess execution. 3) Run in an isolated environment (virtualenv or VM) and avoid running pip install globally — malicious or typo-squatted PyPI packages are a general risk. 4) If you plan to install dependencies, pin known-good package versions from trusted indexes, and consider auditing the actual PyPI packages (or use a vetted wheel). If you need higher assurance, request the upstream source/repository or a maintained release rather than this anonymous bundle.
Capability Analysis
Type: OpenClaw Skill
Name: quant-trading-backtrader
Version: 1.0.0
The skill bundle is benign. It provides a quantitative trading backtesting tool using the Backtrader framework. The `SKILL.md` file contains standard instructions and usage examples without any prompt injection attempts. The `examples/sma_crossover.py` script uses the `os` module solely for creating and then cleaning up a temporary CSV file (`temp_data.csv`) that it generates for backtesting purposes, which is a legitimate and contained file system operation. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or other harmful behaviors.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, and the included example (sma_crossover.py) all align: they implement/backtest a simple SMA crossover using Backtrader, demonstrate stop-loss handling, generate synthetic CSV data, run a backtest, and delete the temp file. There are no requested env vars, binaries, or config paths that conflict with the trading/backtesting purpose.
Instruction Scope
Runtime instructions are narrowly scoped to installing Backtrader/matplotlib and using the provided templates/examples. The SKILL.md and example script only read/write a local temporary CSV, run backtests, and print logs. There are no instructions to read unrelated system files, access network endpoints, or exfiltrate data.
Install Mechanism
The skill is instruction-only (no install spec), which is low risk, but there's a package.json in the bundle listing Python packages (backtrader, matplotlib) as npm dependencies — an incoherence. This manifest is out of place (npm manifests normally list JS packages) and could indicate sloppy packaging or automated conversion; it does not itself install anything, but it is unexpected and should be verified.
Credentials
The skill requests no credentials or environment variables. The example script writes a temporary CSV (temp_data.csv) to the current directory and then removes it — file I/O is limited and proportional to its stated purpose. No sensitive environment access or unrelated credentials are requested.
Persistence & Privilege
The skill does not request persistent or elevated privileges. always is false, and there are no install hooks or configuration changes in the repository. The skill does not attempt to modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install quant-trading-backtrader - After installation, invoke the skill by name or use
/quant-trading-backtrader - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of quant-trading-backtrader.
- Build and backtest quantitative trading strategies using the Backtrader framework in Python.
- Includes structured examples for indicator-based strategies, risk management (stop-loss, take-profit, position sizing), and reporting (trade logs, PNL).
- Supports flexible data input (CSV, pandas DataFrame).
- Provides template code and best practices for robust, research-driven strategy development.
- Example strategies included, such as a basic SMA crossover with stop-loss.
Metadata
Frequently Asked Questions
What is quant-trading-backtrader?
Build, backtest, and optimize quantitative trading strategies in Python using Backtrader with support for indicators, risk management, and reporting. It is an AI Agent Skill for Claude Code / OpenClaw, with 985 downloads so far.
How do I install quant-trading-backtrader?
Run "/install quant-trading-backtrader" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is quant-trading-backtrader free?
Yes, quant-trading-backtrader is completely free (open-source). You can download, install and use it at no cost.
Which platforms does quant-trading-backtrader support?
quant-trading-backtrader is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created quant-trading-backtrader?
It is built and maintained by gmsx000-cloud (@gmsx000-cloud); the current version is v1.0.0.
More Skills