Super Save

Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.

Claude Code 的高效持久化内存系统，在会话启动时可节省约 67% 的 token（经 tiktoken 验证）。分层架构，具有渐进式加载、紧凑编码、分支感知上下文、智能压缩、会话差异、冲突检测、会话续传协议和恢复模式。在会话开始时（如果存在 MEMORY.md）、在响应“记住这一点”、“继续我上次的进度”、“我们上次在做什么”、“总结”、“保存进度”、“别忘了”、“切换上下文”、“交接”、“内存健康”、“保存状态”、“继续我上次的进度”、“上下文预算”、“还剩多少上下文”或任何具有现有内存文件的项目会话开始时激活。此技能一次解决两个问题：Claude 在会话之间忘记一切，以及会话太快达到上下文限制。它用紧凑、结构化的内存加载取代了数千个浪费的重新解释 token，使 Claude 能够在 2000 个 token 内获得完整的项目上下文。

AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.

Store a global memory that is visible across all projects. Use when the user shares architecture rules, coding conventions, infrastructure facts, security policies, team agreements, or any knowledge that applies beyond a single project. Triggers on 'remember this everywhere', 'this applies to all projects', 'global rule', 'shared convention', 'infrastructure note', 'cross-project', or when the content is clearly universal (clean architecture, SOLID, deployment configs, server addresses).

Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.