The Agent Skills Directory

[NO_CODE]: The skill consists entirely of high-level instructions, decision rubrics, and output templates for the AI agent to follow when performing architectural reviews. There are no scripts, binaries, or active commands embedded within the file.
[SAFE]: The disable-model-invocation: true flag in the frontmatter indicates that the skill is restricted from calling other models or tools unless explicitly configured, further limiting the potential attack surface.
[SAFE]: The internal logic emphasizes grounding decisions in existing documentation and codebase facts while explicitly forbidding implementation or file modification within the convergence phase, ensuring no destructive actions are taken during the architectural design process.

architect