This covers the fundamentals of building tools that language models can actually use well. The consolidation principle is the key insight: if you as a developer can't definitively say which tool an agent should pick in a situation, the agent won't do better either. Better to have one comprehensive tool than five narrow ones competing for attention. The architectural reduction section is worth reading, it argues for stripping away specialized tools in favor of primitives like file system access, backed by production evidence. Applies when you're creating new agent tools, debugging why tools get misused, or wondering why your carefully designed tool suite performs worse than expected.
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill tool-design