context-engineering

SKILL.md

Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage.

| Fundamentals | Understanding context anatomy, attention mechanics | context-fundamentals.md | | Degradation | Debugging failures, lost-in-middle, poisoning | context-degradation.md | | Optimization | Compaction, masking, caching, partitioning | context-optimization.md | | Compression | Long sessions, summarization strategies | context-compression.md |

| Memory | Cross-session persistence, knowledge graphs | memory-systems.md | | Multi-Agent | Coordination patterns, context isolation | multi-agent-patterns.md | | Evaluation | Testing agents, LLM-as-Judge, metrics | evaluation.md | | Tool Design | Tool consolidation, description engineering | tool-design.md |

Maîtrisez l'ingénierie de contexte pour les agents IA - optimisation des jetons, modèles de dégradation, compression, systèmes de mémoire, coordination multi-agents, évaluation. À utiliser lors de la conception d'agents, du débogage d'échecs de contexte ou de la création de pipelines LLM. Source : vibery-studio/templates.

Voir l'original