The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to interact with the host system using various versions of the Orca CLI (orca, orca-dev, orca-ide) to manage worktrees, terminals, and artifacts. These are local commands intended for session-specific operations.
[INDIRECT_PROMPT_INJECTION]: The skill implements a dynamic discovery mechanism by instructing the agent to run ORCA skills get orca-cli and treat the resulting output as a 'version-matched guide'. This creates a path where instructions generated by an external executable influence the agent's behavior.
Ingestion points: The output of the shell command ORCA skills get orca-cli is loaded into the agent's context (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or guardrails for the agent to use when interpreting the fetched guide.
Capability inventory: The skill facilitates broad interaction with the Orca CLI, including starting the service (ORCA open) and managing repository worktrees.
Sanitization: There is no explicit sanitization or validation process described for the content returned by the CLI tool before it is used as an instructional guide.

orca-cli