Context Compressor — Real-time conversation context compression engine. Activates when user says "compress context", "压缩上下文", "上下文爆了", "context full", "上下文瘦身", "reduce context", or when context exceeds 70% threshold. This skill compresses the CURRENT conversation history into a clean, short prompt. NOT a memory manager — pure context compression tool. Core capabilities: Compress current chat history (180k → 30k instantly) Auto-trigger at 70% context threshold Structured JSON output with compression metrics Preserve system prompt, keep recent N messages intact Summarize older messages with configurable intensity No database, no dependencies, pure Python

Install

openclaw skills install @relunctance/hawk-context