The Agent Skills Directory

[PROMPT_INJECTION]: No patterns designed to bypass safety filters or extract system prompts were found. The skill provides architectural guidance for creating other skills.\n- [COMMAND_EXECUTION]: Executes bundled Python scripts (init_skill.py, validate_skill.py, package_skill.py) to automate skill creation tasks. These operations are essential for the skill's primary function as a development utility.\n- [DATA_EXFILTRATION]: No access to sensitive files or hardcoded credentials detected. File operations are restricted to relevant development paths.\n- [REMOTE_CODE_EXECUTION]: No remote downloads or script executions from external URLs were identified. All resources are local to the skill package.\n- [DYNAMIC_EXECUTION]: Uses dynamic bash execution for environment context and generates template scripts. The generation process utilizes static templates and does not execute untrusted code at runtime.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests user requirements via AskUserQuestion to generate new instructions. This creates an interpolation surface, but the skill itself functions as a benign developer tool.

create-skill