The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to execute its bundled Python automation scripts (generate_prompt.py, batch_generator.py, validator.py, and optimizer.py) to handle prompt generation and quality checks. These operations are performed using the local Python standard library.
[INDIRECT_PROMPT_INJECTION]: The skill generates prompts by interpolating user-provided responses into predefined templates. This creates a potential surface for indirect injection if a user provides malicious instructions that are then embedded into the final generated document intended for use with other AI models.
Ingestion points: User responses gathered through the mandatory 7-question requirement-gathering flow defined in SKILL.md.
Boundary markers: The generated output utilizes structured XML tags (e.g., <role>, <mission>, <context>) to delineate different sections of the prompt, providing structural separation.
Capability inventory: The skill has the capability to write text files to the local filesystem (Path.write_text) and execute the included Python scripts.
Sanitization: No specific filtering or sanitization of user-provided input is performed before it is placed into the output templates.

prompt-factory