Execute a spec'd goal in one long autonomous run — hours of agent work pushing a whole acceptance ledger, with humans only at the two gates, spec before and review after. Use for /long-horizon, "make this a long-horizon goal", "run this across sessions", or…
用一次长程自主运行执行一个定稿的目标——数小时的 agent 工作推完整个验收台账，人只出现在两道闸：运行前的 spec、运行后的 review。适用于 /long-horizon、「长程执行这个任务」「跑一个长程目标」，或在已有 `.long-horizon/` 工作区的仓库中恢复工作时。入口交互式反复迭代；运行由 fan-out 驱动、副作用被授权信封约束；进展只认证据；实时 report.html 以 DAG 呈现台账。
Dispatch the current task to multiple subagents — after checking that fan-out is actually justified. Use for /fan-out, when the user says "multi-agent this" or "fan out", or when a task decomposes into genuinely independent subtasks. Decomposes along context…
把当前任务派发给多个 subagent——但先检查这次拆分到底值不值。适用于 /fan-out，触发语：「用多智能体做」「派发出去」「拆给多个 agent 并行」，或任务能拆成真正独立的子任务时。按上下文耦合度拆解，spawn prompt 用 handoff 的纪律写成任务契约。
Write replies and work reports a person can take in on one read — one claim per sentence, action in the verb, uncertainty attached to the claim it belongs to. Use for /readout, "make your reports readable", "your output is hard to read", "stop writing like an…
写出别人一遍就能读懂的回复和工作汇报：一句话只说一件事，动作放在动词里，不确定性绑在它所属的那条结论上。当用户说 /readout、「你的汇报太难读了」「说人话」「别写得像 AI」，或者需要修正某次运行的汇报风格时使用。下面的正文独立成篇：整段贴进 AGENTS.md 或 CLAUDE.md，就能每轮生效，不必调用。
One-shot answer-only turn — the user is asking a question, not assigning work. Invoked as /just-ask with the question attached (e.g. "/just-ask why does this test flake"). For that turn only, investigate read-only and reply with an analyzed answer; do not…
一次性「只回答」回合——用户是在问问题，不是在派活。用 /just-ask 加问题调用（如「/just-ask 这个测试为什么会偶发失败」）。仅该回合内：只读调查、给出经过分析的回答；不改文件、不跑会改状态的命令、不写计划、不动手修。下一条消息恢复正常。以显式调用为主；用户说「只问一下，别动手」「你就解释，不用修」时同样适用。