The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown documentation and reference files. No executable scripts, binaries, or configuration files that could trigger automated commands were found.
[SAFE]: No network operations, file system modifications, or data exfiltration patterns are present. The skill does not interact with external APIs or remote servers.
[SAFE]: Prompt patterns such as "Forget everything we've discussed" and "Scrap this" are documented as legitimate techniques for managing session context during code refactoring. They do not target the underlying AI safety guidelines or ethical constraints.
[SAFE]: No obfuscation, hidden content (zero-width characters, homoglyphs), or malicious metadata were detected in the analyzed files.

advanced-prompting