{"skill":{"slug":"context-compression-claude-code-custom","displayName":"Context Compression Claude Code Custom","summary":"Use this skill whenever the conversation context is getting long, when a user asks to \"compress\", \"summarize\", or \"clean up\" the conversation, or when you de...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":102,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":1},"createdAt":1776434845886,"updatedAt":1776435108526},"latestVersion":{"version":"1.0.0","createdAt":1776434845886,"changelog":"- Initial release of the context-compression skill, providing structured, tiered conversation compression based on conversation scenario.\n- Implements a three-layer strategy: must-preserve content, summarized content, and discardable content.\n- Supports both manual and automatic compression triggers, including PreCompact hook integration.\n- Outputs a structured memory file to retain key long-term information.\n- Includes special handling for multi-channel and group chat scenarios, with user-focused retention rules.","license":"MIT-0"},"metadata":null,"owner":{"handle":"c595390153-a11y","userId":"s177dh796crghdfcrj9765wc1n83ghz3","displayName":"c595390153-a11y","image":"https://avatars.githubusercontent.com/u/226090520?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.4.0","updatedAt":1776435108526}}