The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructions for the agent to execute a local Python script (scripts/quality_gate.py) to validate sample outputs. This script is provided within the skill package and performs benign regex-based text analysis to ensure output quality and adherence to the specified persona.
[EXTERNAL_DOWNLOADS]: The references/methodology-basis.md file contains links to external GitHub repositories (e.g., github.com/leezythu/maoxuan-skill, github.com/weiyinfu/MaoZeDongAnthology) for attribution and methodology reference. These are static links for informational purposes and are not used for runtime downloads or code execution.
[PROMPT_INJECTION]: The skill contains specific instructions directing the agent to perform its reasoning process silently and to suppress the mention of its historical methodology and sources. These are stylistic and persona-based constraints and do not attempt to override the underlying model's safety filters.
[DYNAMIC_EXECUTION]: The test script scripts/test_quality_gate.py uses the importlib library to dynamically load and execute the quality_gate.py module for unit testing. This is a standard testing pattern and is performed on local, provided code.

product-decision-agent