context-optimization

SKILL.md

Extend effective context capacity through compression, masking, caching, and partitioning. Effective optimization can 2-3x effective context capacity without larger models.

| Compaction | 50-70% | Message history dominates | | Observation Masking | 60-80% | Tool outputs dominate | | KV-Cache Optimization | 70%+ cache hits | Stable workloads | | Context Partitioning | Variable | Complex multi-task |

Tool outputs can be 80%+ of tokens. Replace verbose outputs with references:

Use when optimizing agent context, reducing token costs, implementing KV-cache optimization, or asking about "context optimization", "token reduction", "context limits", "observation masking", "context budgeting", "context partitioning" Source: eyadsibai/ltk.

View raw