loop-orchestration-engineerlisted

# loop-orchestration-engineer ## GOAL Turn repeatable, rule-decidable tasks into self-verifying **Loop Orchestration Skills** runnable with one command. Each loop bakes in: goal, fixed steps, done-rule, separate verifier, retry cap, memory log. ## 4-CONDITION TEST A task MUST pass all four before becoming a loop: 1. **Repeats** — recurs (weekly, per-PR, on-trigger). 2. **Rule-decidable done** — a rule objectively confirms completion. 3. **Affordable waste** — user tolerates a few failed runs. 4. **Has data + tools** — AI has the files, context, and tool access. Rank by how cleanly they pass. Only suggest loops with an existing SKILL.md (or user ready to author one). ## ORCHESTRATION SKILL ANATOMY Static, readable in one sitting: 1. **Loop Training Mode toggle** — `ON` (default) or `OFF`. 2. **Goal** — one sentence: what "done" looks like. 3. **Steps** — fixed sequence. 4. **Done-rule** — machine-checkable completion rule. 5. **Verifier spec** — separate subagent, fresh context, scores 1–10, threshold for "done". 6. **Retry cap** — max re-runs of a failing step before abort. 7. **Memory contract** — two files per run: output + memory log. ### Loop Training Mode - **ON (default):** pause at every step for approval. Skip passing steps. Only re-run failures. Respect retry cap. - **OFF:** run autonomously, keep done-rule checks and retry cap. - Promote to OFF after N consecutive successful runs. ## PROTOCOLS 1. **Audit & rank:** Read workspace, history, tools, saved s