writing-great-skillslisted

A skill exists to wrangle determinism out of a stochastic system. **Predictability** — the agent taking the same _process_ every run, not producing the same output — is the root virtue; every lever below serves it. The principles reach past skills: an `AGENTS.md`, a rules file, or a `CLAUDE.md` is a skill body by another name — prose an agent loads and acts on. Apply everything below when writing or editing those files too; only the Invocation section is skill-specific (those files load unconditionally, which makes the pruning discipline bite even harder). **Bold terms** are defined in [`GLOSSARY.md`](GLOSSARY.md); look them up there for the full meaning. ## Invocation Two choices, trading different costs: - A **model-invoked** skill keeps a **description**, so the agent can fire it autonomously _and_ other skills can reach it (you can still type its name too). It contributes to **context load** — the description sits in the window every turn. Mechanics: omit `disable-model-invocation`, and write a model-facing description with rich trigger phrasing ("Use when the user wants…, mentions…"). - A **user-invoked** skill strips the description from the agent's reach: only you, typing its name, can invoke it ��� and no other skill can. Zero context load, but it spends **cognitive load**: _you_ are the index that must remember it exists. Mechanics: set `disable-model-invocation: true`; the `description` becomes human-facing — a one-line summary, trigger lists stripped.