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
Mis à jour 1/17/2026
Étoiles
1
Forks
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.
Installation
$ install --globalskills.sh
Utilisation
Après l'installation, vous pouvez utiliser ce skill en exécutant la commande suivante dans votre terminal :
skills use context-compression