carloswecare

Build and reason about projects using Interpretable Context Methodology (ICM) — a filesystem-based way to structure AI work using numbered folders and markdown files (CLAUDE.md, CONTEXT.md) instead of code-heavy agent frameworks. Use this skill whenever the user wants to scaffold a new ICM workspace, set up a CLAUDE.md routing file, design CONTEXT.md stage contracts, organize an AI project into numbered stages with review gates, or convert a messy single-prompt workflow into a structured "glass-box" folder system. Also trigger when the user mentions ICM, "context engineering," "context methodology," staged markdown pipelines, or asks how to organize folders so an AI agent loads only the context it needs per step — even if they don't say "ICM" explicitly.