What problem does it solve? When starting a new coding task or switching context, developers lose access to past decisions, coding conventions, and known pitfalls stored in long-term memory. This Skill pre-fetches relevant memories from mem0 so the AI assistant begins work with the right project history already loaded. ## Core Features & Use Cases - Multi-angle memory search: Runs 2-4 parallel search_memories queries filtered by memory type (decision, convention, anti_pattern) plus a broad catch-all query. - Deduplicated compact output: Merges results by memory ID and outputs at most 10 memories in a plain-text context block compatible with the OpenCode TUI. - Silent on empty results: Produces no output when no relevant memories exist, avoiding noise in the conversation. - Use Case: A developer starts work on a payment module; the Skill searches mem0 for past architecture decisions, coding conventions, and known anti-patterns related to that module and injects them into context before any code is written. ## Quick Start Ask the assistant to load context for the feature you are about to work on, for example: load what we know about the authentication module before I start refactoring it.
