The Agent Skills Directory

[SAFE]: The skill consists entirely of high-level instructions and methodology descriptions for creative thinking. It contains no executable scripts, shell commands, or platform-specific tool invocations.
[PROMPT_INJECTION]: While the skill uses the term 'Constraint Injection', this refers to a logical brainstorming technique (e.g., time or resource limits) rather than an attempt to bypass AI safety filters or override system instructions.
[DATA_EXFILTRATION]: No network tools, external URLs, or sensitive file access patterns are present in the documentation.

constraint-protocol