The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and natural language instructions for an AI agent. It does not contain any code, scripts, or automation that could be executed maliciously.
[NO_CODE]: No shell commands, Python scripts, or Node.js code are present in the file. All procedures described are manual analysis steps for the AI to perform on provided data.
[DATA_EXPOSURE]: There are no hardcoded credentials, API keys, or instructions to access sensitive system files like SSH keys or environment secrets.
[EXTERNAL_DOWNLOADS]: The skill does not reference or attempt to download any external resources or dependencies.
[PROMPT_INJECTION]: The instructions do not contain bypass markers, 'DAN' style role-play injections, or attempts to override the underlying AI safety guidelines.

testing-strategy