routinizelisted

# /routinize — codify a recurring practice (관행화) Turn "work I keep doing the same way" into a durable Greatpractice entry — without over-codifying. This is the model-invoked front door to Greatpractice's **capture → mature → codify** pipeline (Greatpractice.md §1.2). The full normative model — tiers, maturity score, notability gate, phronesis boundary — lives in `Greatpractice.md`; this skill is the actionable procedure, not a restatement. **Core discipline — capture is immediate, promotion is deferred** (§5.4). A single session's repetition is usually the *same* trigger coordinate (§5.2), so most invocations end at capture/accumulate; only genuinely independent recurrence produces a draft. The skill never registers an enforcing hook on its own authority — that is a user decision. ## Procedure 1. **Scan for recurrence** — over the recent context, find work patterns that repeated: the same fix applied ≥2×, the same multi-step sequence run again, a "when X, also do Y" coupling, a mistake made → corrected → nearly repeated. Name each candidate pattern in one line. 2. **Phronesis gate — what NOT to codify** (§1.4 / §5.3). Drop any candidate that is *judgement-heavy* (outcome doesn't reduce to one metric), *rare-context* (long-tail work phase), or *high-context-dependent* (the same surface behavior means different things by context). These stay in the agent's instinct — codifying them causes phronesis atrophy. Keep a borderline-but-worth-capturing candidate, but mark `phrones