The Agent Skills Directory

[SAFE]: The skill's functionality is strictly limited to reviewing code against a static set of animation standards provided in the local STANDARDS.md file.
[SAFE]: No network operations, external data fetching, or remote code execution patterns were found. All referenced URLs are purely for documentation and citation.
[SAFE]: The skill uses disable-model-invocation: true in its frontmatter, which serves as a platform-level configuration to prevent the agent from calling any tools, effectively neutralizing command execution or file system access risks.
[SAFE]: No obfuscation, data exfiltration, or persistence mechanisms are present within the skill's instructions or supporting files.
[SAFE]: While the skill processes user-supplied code (an indirect prompt injection surface), the risk is mitigated by the lack of tool usage and a strictly defined output format that focuses the agent on structured feedback.

review-animations