llm-aidata-ai
context-compression
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
maintainer
SyntaxAsSpiral
업데이트됨 1/17/2026
스타
1
포크
1
quick start
Installation and usage
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
설치
$ install --globalskills.sh
사용법
설치 후 터미널에서 다음 명령을 실행하여 이 스킬을 사용할 수 있습니다:
skills use context-compression