The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to interact with the system and an external CLI tool named gsd-sdk. This tool is used to resolve context and likely perform other task-related operations. This represents a standard but powerful capability for development-oriented agents.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest "plans" from local files and execute them using subagents.
Ingestion points: The skill reads workflow files and plan files located within the user's home directory at $HOME/.claude/get-shit-done/.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the plans are present in the skill definition.
Capability inventory: The skill and its spawned subagents have access to powerful tools including Bash, Agent (for spawning further subagents), Write, and Edit.
Sanitization: There is no evidence of sanitization or validation of the plan content before it is processed by the orchestrator or subagents.

gsd-execute-phase