The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation providing mental models and cognitive frameworks. It contains no executable scripts, shell commands, or binary files.\n- [SAFE]: All external references point to a legitimate and well-known repository hosted by a trusted organization (Microsoft), which is used for attribution purposes.\n- [SAFE]: Although the skill uses strong instructional markers such as 'IMPORTANT MUST ATTENTION', these are directed at ensuring the agent follows structured workflows, such as breaking down tasks, citing evidence, and seeking user consent before skipping steps. There are no attempts to bypass safety filters or override core system instructions.\n- [SAFE]: The skill does not perform any network requests, file system modifications (beyond internal task management), or data exfiltration.

problem-solving