The Agent Skills Directory

[SAFE]: The skill functions as a set of prompt instructions to steer reasoning style based on user-provided keywords. No malicious patterns or security vulnerabilities were identified.
[NO_CODE]: The skill consists exclusively of markdown instructions and YAML configuration. It does not include any scripts, executables, or package dependencies.
[PROMPT_INJECTION]: The 'AUTO-INVOKE' triggers were analyzed. These patterns are legitimate cognitive constraints (e.g., 'first-principles', 'falsifiable', 'adversarial') intended to improve reasoning depth and do not attempt to bypass safety filters or ignore system instructions.
[DATA_EXFILTRATION]: There are no network operations, file system access, or credential harvesting patterns present in the instructions.
[EXTERNAL_DOWNLOADS]: The skill does not reference or download any external resources or remote code.

ai-lingo