“A library of specialized skills for managing context and operating loops in production agent systems.”
Combined rank
#26
across all skills
In Agent Orchestration
#4
category rank
Stars
17.6k
+0.6% in last 7d
Forks
1.4k
+0.5% in last 7d
Watchers
97
0.0% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
This collection provides a structured framework for context engineering, harness engineering, and the design of multi-agent architectures. It is designed for builders who need to optimize how agents handle information and maintain reliable execution patterns.
The repository offers tools for building, evaluating, and debugging agent systems, ensuring that context management remains effective as system complexity increases.
WHO IT'S FOR
AI agent / automation builders
designing multi-agent architectures and context management
LLM engineers
building book-to-SFT pipelines for voice replication
AI system debuggers
analyzing reasoning traces and context degradation
AI agent power users
implementing personal operating-system workflows for productivity