ai-memory

Provide first-turn understanding of the ai-memory repository with minimal tokens. Always use this skill when user asks what this project does, asks for implementation entrypoints, requests architecture explanation, or when a subagent needs a narrow read plan for this repository.

Route tasks in the ai-memory project and load only the minimum required memory context. Always use this skill when user asks about ai-memory architecture, inject modes, copilot-instructions redesign, project memory lookup, learn pipeline behavior, or when a subagent should avoid broad file reads.

Audit and optimize token usage for ai-memory prompts and instruction files. Use when user asks to reduce context cost, compare inject modes, improve first-turn hit rate, or design skills-based on-demand memory loading.