Download
Agent Skills for Context Engineering is a curated collection of reusable “agent skills” focused on helping AI agents perform better on long-horizon, multi-step work by managing context deliberately. Rather than being a single application, it packages practical guidance into skill modules that agents can load to improve planning, retrieval, memory usage, and overall reliability in real workflows. The repository emphasizes context engineering as a discipline, covering why agents fail when context gets too large, too noisy, or poorly structured, and how to mitigate those failure modes with repeatable patterns. It is designed to be used across modern agent environments that support skill folders and structured instructions, so teams can standardize how agents operate instead of relying on ad-hoc prompting.
Features
- Modular skill library centered on context engineering practices
- Guidance for long-horizon task reliability and failure prevention
- Patterns for structuring context, memory, and retrieval workflows
- Composable skills that can be mixed and matched per project
- Designed for agent environments that support skill folders and structured instructions
- Community-friendly format for extending and contributing additional skills
Project Samples
