The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to resolve the orca CLI path using environment variables such as ORCA_CLI_COMMAND and ORCA_DEV_REPO_ROOT, or fallback names like orca-ide and orca-dev.
[COMMAND_EXECUTION]: The agent is directed to execute specific commands (status, worktree ps, terminal list) to interact with the Orca environment.
[PROMPT_INJECTION]: The skill uses a pattern where the agent retrieves its full command guide by executing ORCA skills get orca-cli. This creates an ingestion point for tool-generated instructions.
Ingestion points: The stdout from the ORCA skills get orca-cli command.
Boundary markers: None; the skill instructs the agent to read and follow the returned guide.
Capability inventory: The skill allows shell command execution through the orca binary.
Sanitization: None; the agent is instructed to trust the output of the local binary as its usage guide.

orca-cli