Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
/plugin marketplace add zechenzhangAGI/AI-research-SKILLs/plugin install transformer-lens-interpretability@ai-research-skillsExpert guidance for Next.js Cache Components and Partial Prerendering (PPR). Proactively activates in projects with cacheComponents enabled.
Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.