The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a command-line tool for automated code checking.
Evidence: The procedure in SKILL.md includes the execution of mops check --fix to handle mechanical style fixes and redundant code patterns.
Context: mops is the standard package manager and toolchain for the Motoko ecosystem.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it is designed to ingest and analyze untrusted source code files.
Ingestion points: The skill analyzes existing Motoko backend files (.mo), mops.toml configuration files, and migration chains.
Boundary markers: The skill provides a robust framework of specific design questions and severity-ranked findings (Blocker, Warning, Note) which helps the agent maintain a structured, objective analysis posture.
Capability inventory: The skill utilizes the mops CLI for automated analysis and code modification.
Sanitization: No explicit content sanitization is described, as the skill is intended for technical audit by an AI agent.

reviewing-motoko