AI Agent #blog#ai#agent#skill 2,994 words · ~15 min read
After Writing Dozens of Skills, I Distilled This Engineering Method: From `Never Triggered` to `Production-Ready`
An engineering method for writing Skills that are correct, stable, and maintainable long-term, distilled from writing dozens of them. Skills are three layers, not one file: L1 metadata for routing, L2 body for behavior, L3 resources for facts and determinism. Most "never triggers" are routing failures — fixed by a `description` that says what, when, and especially when *not* to use it. Execution drift is fixed with numbered steps, stop conditions, and rule-plus-reason instructions. Guardrails turn "should" into machine-checkable checkpoints, with tiered failure handling. Splitting should follow change-reasons, not file length. Four eval metrics (routing, step-following, checkpoints, task success) pin down what to fix. Ends with versioning, a trace-reading workflow, and a copy-paste checklist.