context-engineering

SKILL.md

Context engineering is the discipline of curating and maintaining the optimal set of tokens during LLM inference. Unlike prompt engineering (crafting individual prompts), context engineering focuses on what information enters the context window and when.

LLMs have limited "attention budgets." As context length increases, models experience context rot—decreased ability to accurately recall information. The goal is finding the smallest possible set of high-signal tokens that maximize desired outcomes.

Key insight: More context isn't better. The right context is better.

Stratégies pour gérer efficacement les fenêtres contextuelles LLM dans les agents IA. À utiliser lors de la création d'agents qui gèrent de longues conversations, des tâches en plusieurs étapes, l'orchestration d'outils ou qui doivent maintenir la cohérence au sein d'interactions étendues. Source : itsmostafa/llm-engineering-skills.

Voir l'original