writing-for-agents

Front-load the leading trigger word, list one trigger per distinct branch the document handles, and cut identity the body already carries. The description's wording, not its target, decides when the agent reaches the material.

A model-invoked skill keeps a description so the agent and other skills can fire it autonomously, at the cost of permanent context load. A user-invoked skill sets disable-model-invocation: true, so only a human typing its name can reach it.

Split by sequence when visible later steps tempt the agent to rush the current one, and split by invocation when a distinct trigger word should fire a skill on its own. Each split spends context or cognitive load, so the cut must earn it.

Progressive disclosure moves reference material out of the main file and behind a context pointer, loaded only when the pointer fires. Inline what every branch needs and disclose what only some branches reach, keeping the top level legible.

Negation drags the forbidden behavior into context and makes it more available, since the strongly activated concept overruns the weak negation. State the positive target behavior instead so attention lands on what to do.