Qc Backtest Master

QuantConnect automated backtest pipeline — submit local strategies, compile, execute, monitor with early-stop, and download results in one command.

This skill appears to do exactly what it claims: submit your local strategy to QuantConnect, compile, run/monitor it (with optional early-stop that permanently deletes the backtest), and fetch results. Before using it: 1) Only provide QC_USER_ID/QC_API_TOKEN/QC_PROJECT_ID for an account you trust; the token is used to authenticate to QuantConnect. 2) Run the skill from a directory that does not contain sensitive .json/.txt/.csv files or an unrelated .env you don't want uploaded — the submit step uploads all such files in the strategy directory. 3) Be aware early-stop will permanently delete the backtest (documented). 4) The code will also look for credentials in a parent .env (up to 6 levels) and in ~/.lean/credentials — remove or inspect those if you don't want them picked up automatically. 5) If you have any doubt, review the included Python files locally (they call only QuantConnect API endpoints) and run verify_connection.py first to confirm the connection behaves as expected.

Type: OpenClaw Skill Name: qc-backtest-master Version: 1.0.0 The skill bundle is a legitimate automation tool for the QuantConnect algorithmic trading platform. It facilitates uploading strategy files, monitoring backtest progress with an 'early-stop' drawdown feature, and downloading results via the official QuantConnect REST API v2. While it accesses sensitive information such as API tokens and the `~/.lean/credentials` file, it does so to authenticate with the official service (quantconnect.com) and follows standard practices for the QuantConnect ecosystem. No evidence of data exfiltration to third parties, malicious code execution, or harmful prompt injection was found.