The Agent Skills Directory

[SAFE]: The skill consists of markdown-based documentation and reference materials providing guidance on AI design patterns. It does not include any executable scripts, binaries, or automated tasks.
[NO_CODE]: The skill package contains no functional code or tool implementations, ensuring no technical risk from script execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided project requirements to offer architectural advice. 1. Ingestion points: Project descriptions and requirements provided by the user. 2. Boundary markers: None identified. 3. Capability inventory: The skill has no tool access or shell execution permissions defined in its configuration. 4. Sanitization: None identified. The finding is safe as the skill's functionality is restricted to providing text-based recommendations and reasoning.

anthropic-architect