Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
7.8
Rating
0
Installs
AI & LLM
Category
Excellent skill for context engineering in AI agent systems. The description clearly covers when to invoke the skill (designing agents, debugging context failures, optimizing tokens, etc.). The structure is exemplary with a concise SKILL.md that provides quick reference to detailed topic files, avoiding clutter. Task knowledge is comprehensive, covering fundamentals through advanced patterns with actionable metrics, anti-patterns, and concrete guidelines. The skill addresses a genuine complexity area where CLI agents would struggle with token optimization and multi-agent coordination, though the novelty is slightly tempered as some concepts (like summarization) are achievable by agents alone. Strong practical value with measurable targets and clear implementation guidance.
mrgoonie
Skill Author
Loading SKILL.md…
Skill Author
