keli-wen

Closed-loop orchestrator — from a one-line brief straight through init → gold → freeze → check-loop → smoke-train → short train → report, in one command, at minimum cost. Infers everything inferable and compresses any remaining blocking questions into ONE AskUserQuestion round (data present + goal clear ⇒ zero questions). Defaults to machine-signing BOTH sign-off gates — rubric AND gold (fast, distillation-flavored: J-Score means agreement-with-teacher, not verified correctness) — so a default run reaches a real training round with no human touch; pass sign=human to stop at the human sign-off gate exactly like /strop-gold, byte-for-byte the same as before. Fails fast at every step — never silently retries. Use when the user types /strop-auto or asks to "一条龙跑一个 task / one-shot this task / fully automate a new task / close the loop end to end". Arguments: task name (required), the brief (free text), sign=human|machine (default machine), rounds=N (default 3).

Loop-engineering audit of one Strop task — is the training loop CLOSED (task↔harness contract, frozen gold, signed rubric, env, forward liveness, smoke-ability)? Read-only; verdict table + LOOP-READY / NOT READY. Use when the user types /strop-check-loop or asks "这个 task 闭环了吗 / loop-ready 吗 / 能开训吗 / check the loop". Arguments (optional): task dir; `smoke` to additionally live-run a 1-item forward.

Score one or more prediction files ("arms") against a Strop task's frozen gold with the fixed judge → a J-Score comparison table (the standalone eval / transfer entry, outside the training loop). Use when the user types /strop-eval or asks to "对比 J-Score / eval these preds / transfer eval / bare vs skill 对比". Arguments: arms (label=preds path pairs — required), task dir, split=train|dev|heldout.

Launch the gold-generation pipeline for a Strop task (N independent strong-reference labeling passes + per-ticker reconcile → DRAFT gold + human review doc) as a background Workflow. Default (`sign=human`, or no flag) ALWAYS STOPS before freeze for human review + sign-off. `sign=machine` (the default when invoked BY /strop-auto; a human may also pass it directly) skips the human gate — after reconcile, a dev agent merges the drafts and freezes gold with an explicit `signer: machine` field plus a machine-signed watermark. Use when the user types /strop-gold or asks to "造 gold / 打 gold 标 / run the gold pipeline". Arguments (all optional): task dir, splits=..., tickers=..., passNum=N, sign=human|machine (default human), smoke, smokeFull, smokeItems=N, runId=....

Bootstrap a NEW Strop task from a short brief. Infers everything inferable first (the brief text, any data samples already under tasks/<name>/data/, whether ./.env is configured, the shipped news-labeling task as a structural precedent) — a complete brief needs ZERO questions. For genuine gaps, asks ONE decision at a time via AskUserQuestion (recommended option listed FIRST, suffixed "(Recommended)") in dependency order: goal → data source → output schema → correctness standard/rubric weights → student model/.env → split policy. Then scaffolds tasks/<name>/, runs strop-init-agent to draft θ₀ (skill.seed.md), a rubric DRAFT, and task.md's `## Forward` / `## Output schema` / smoke-safe contract blocks, and writes the interview's decision record to tasks/<name>/design.md. Use when the user types /strop-init or asks to "新建一个 task / bootstrap a task / 起一个新任务". Arguments: task name (required), the brief (free text), headNum=N (default 0).

Launch one full Strop training run (forward → judge → optimize → dev-validate, N rounds → experiment report) as a background Workflow. Use when the user types /strop-train or asks to "train the skill/instruction", "跑一轮训练", "start the strop loop", "smoke train / 冒烟跑一次". Arguments (all optional): task dir, rounds=N, smoke, smokeItems=N, headNum=N, heldout, runId=....

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

AI Agent Harness 设计模式 — 记忆、权限、上下文工程、委派、技能、 Hook、Bootstrap。中文版。