菜单
Implements Anthropic's "Dreaming" pattern—asynchronous reflection and memory consolidation to build long-term playbooks and self-improve.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
End-to-end management of AI agent skills, context optimization (MCE), and lifecycle monitoring (Discovery to Refinement to Consolidation).
Orchestrate AI agent infrastructure using Modal.com as the execution layer, managing persistent state, and integrating with Cline/OpenCode/Hermes.
Background maintenance agent that prunes, consolidates, and refines agent-created skills to prevent bloat and reduce token waste.
Manages cross-session tiered memory (L1/L2/L3) and compaction logic to maintain performance over long durations.
| name | dream-system |
| description | Implements Anthropic's "Dreaming" pattern—asynchronous reflection and memory consolidation to build long-term playbooks and self-improve. |
Inspired by Anthropic's "Dreaming" pattern, this skill enables the agent to perform asynchronous self-reflection, turning raw session history into structured knowledge (Playbooks) and pruning "Memory Rot."
docs/PLAYBOOK.md หรือ docs/LEARNINGS.md เพื่อเก็บ "วิธีทำงานที่ถูกต้อง" (Golden Paths)MEMORY.md หรือ AGENTS.md