The Agent Skills Directory

[SAFE]: The skill is composed of purely instructional and educational content. It defines a 'delivery framework' for system design and provides high-quality reference materials for various technical concepts such as CAP theorem, sharding, and API design.
[SAFE]: All referenced materials are local markdown files containing standard architectural principles. No remote scripts, binary dependencies, or automated installations are requested or executed.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided code and design documents to explain or improve them. This is the primary intended function of the skill. While processing untrusted data is an inherent attack surface, the skill does not grant the agent any dangerous capabilities (such as file system writes, privilege escalation, or outbound network access) that could be abused via prompt injection.

system-design