The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs shell commands including rg (ripgrep), sed, cut, comm, sort, and terraform-docs to process text files. It also runs local Python scripts from the project's scripts/ directory using uv run. These commands are standard for project maintenance and documentation tasks within a local development environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes local configuration files (variables.tf) and documentation markdown. While this ingests external data into the agent's context, the skill's logic is focused on structural extraction of variable names and definitions via regular expressions, posing minimal risk.\n- [SAFE]: The skill exhibits safety-conscious behavior by providing explicit instructions on maintaining SELinux security policies and implementing safeguards (no-destroy gates) for critical infrastructure resources.

sync-docs