The Agent Skills Directory

[SAFE]: The skill operates as an orchestrator that requires explicit user confirmation at specific stopping points before proceeding with automated actions.
[COMMAND_EXECUTION]: The skill performs git commit operations via Bash, which is a standard component of its intended implementation lifecycle and is gated by manual approval.
[PROMPT_INJECTION]: The skill processes user input via the $ARGUMENTS variable to determine workflow steps. Potential indirect injection is mitigated through mandatory system constraint suffixes for all sub-agents and human-in-the-loop checkpoints. Ingestion points: $ARGUMENTS variable in Situation Assessment. Boundary markers: Mandatory [SYSTEM CONSTRAINT] suffix for all sub-agent prompts. Capability inventory: Git command execution, task creation/updates, and sub-agent invocation. Sanitization: No explicit sanitization or filtering of the argument string is defined.

recipe-implement