The Agent Skills Directory

[SAFE]: The skill's primary function is to serve as a comprehensive reference for AI agent design patterns including ReAct, multi-agent orchestration, and memory systems.
[SAFE]: All code snippets included in the reference files are illustrative templates and are not configured for automatic execution.
[SAFE]: The permissions manifest in tank.json is appropriately scoped, allowing only read access to the skill's directory for serving content, with no subprocess or network access enabled.
[SAFE]: No patterns of prompt injection, data exfiltration, or obfuscation were identified during the analysis.

@tank/ai-agent-patterns