The Agent Skills Directory

[SAFE]: The skill serves as a documentation and analysis toolkit for quantitative trading validation.
[COMMAND_EXECUTION]: Provides a Python script (evaluate_backtest.py) that performs scoring on user-provided metrics. The script uses standard libraries and validates numeric inputs to ensure they fall within expected ranges.
[EXTERNAL_DOWNLOADS]: No external downloads or remote script executions are performed. All dependencies are part of the Python standard library or used for local development/testing.
[DATA_EXFILTRATION]: No network activity or access to sensitive local files (like SSH keys or environment variables) was detected. Outputs are limited to local report files.
[PROMPT_INJECTION]: The skill instructions contain no attempts to override agent behavior, bypass safety filters, or extract system prompts.

backtest-expert