The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run the mops check --fix command. mops is the standard, well-known package manager and linter for the Motoko programming language ecosystem.
[INDIRECT_PROMPT_INJECTION]: As a code review tool, the skill naturally processes untrusted external data (Motoko source code and project configuration files), creating a standard attack surface for indirect prompt injection.
Ingestion points: Reads and analyzes Motoko source files (.mo) and project configuration (mops.toml) provided by the user.
Boundary markers: The instructions do not define specific delimiters or 'ignore' instructions for the code being reviewed.
Capability inventory: The skill includes the capability to execute mops check --fix on the project files.
Sanitization: No specific sanitization of the input code is described; however, the skill's purpose is to find and report defects in that code rather than execute it directly.

reviewing-motoko