Auto-compress session memories when context usage exceeds 60%
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。
SkillHub CLI
skillhub install bg1avd/context-shrink打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。
将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。
Auto-compresses session memories when context usage exceeds 60% threshold. Cleans up old daily logs and compresses them into MEMORY.md for long-term storage.
CONTEXT_THRESHOLD = 0.6 // 60% 触发阈值
DAYS_TO_KEEP = 3 // 保留最近 N 天日志
MIN_FILES_TO_KEEP = 5 // 至少保留文件数
COMPRESSION_MODEL = 'ollama-remote/qwen2.5:3b'
这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。
# Context Shrink Hook Auto-compresses session memories when context usage exceeds 60% threshold. Cleans up old daily logs and compresses them into MEMORY.md for long-term storage. ## Features - **自动触发**: 当 context 使用率 ≥ 60% 时自动执行 - **智能清理**: 保留最近 3 天的详细日志 - **压缩存储**: 旧日志压缩后写入 MEMORY.md - **Git 提交**: 自动 commit 变更记录 ## Configuration ```typescript CONTEXT_THRESHOLD = 0.6 // 60% 触发阈值 DAYS_TO_KEEP = 3 // 保留最近 N 天日志 MIN_FILES_TO_KEEP = 5 // 至少保留文件数 COMPRESSION_MODEL = 'ollama-remote/qwen2.5:3b' ``` ## Changelog ### 1.0.0 - Initial release - Auto-compression at 60% threshold - Git commit on cleanup
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...
Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.
Send and receive P2P messages using disposable numbers and PINs. No servers, no accounts. Use for human notifications, approval flows, and agent-to-agent communication.