The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and frontmatter metadata. It does not include any scripts, binaries, or automated tools.
[SAFE]: The skill's instructions focus on logical auditing, scoring, and ranking of design tasks. No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected.
[INDIRECT_PROMPT_INJECTION]: While the skill involves auditing project files (untrusted data source), it lacks capabilities such as file writing, shell command execution, or network operations that could be exploited through malicious content in those files. The risk is negligible as the output is limited to a text-based action plan.

refactor-plan