The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown files and guidelines. No executable code, shell commands, or network operations are included.
[PROMPT_INJECTION]: The instructions are designed to guide the agent in code review and authoring. No bypass markers, role-play injections, or attempts to override system safety guidelines were found.
[DATA_EXFILTRATION]: No network requests (curl, wget, fetch) or sensitive file access patterns were detected. The skill does not handle credentials or environment variables.
[REMOTE_CODE_EXECUTION]: There are no remote script downloads or installations of external packages. References to libraries like Zod and Pydantic are instructional examples for users, not dependencies of the skill itself.
[OBFUSCATION]: No obfuscated content, such as Base64, zero-width characters, or encoded URLs, was found in any of the analyzed files.

code-quality