Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Fan out N independent parallel workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.
Open a todolist with one entry per phase before launching anything.
first pass, rank all, or best-of before spawning.AGENTS.md. Use the current environment's configured worker roles and available delegation interface. Inherit supported defaults when no override is configured; report unsupported configuration rather than inventing identifiers. Use only supported execution settings. For a race, name each arm's role and setup up front. Shared role configuration is managed separately..agents-state/ here). Name writable file or directory ownership in each editing brief so workers do not overwrite one another's work. When workers verify or measure commits, each brief names the exact SHAs. A measurement brief also names the method (sample count, what one sample is, order). The worker records both in its result.Launch all N workers through the available delegation interface, concurrently within its capacity or in batches when necessary. Choose execution environments with the source, tools and data access their briefs require.
Provide the requested branch or starting revision through the environment's supported checkout mechanism; ensure it matches the brief rather than relying on an implicit default.
Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use PASS, ISSUES, or BLOCKED with evidence. A worker that can prove a defect reports ISSUES and lists every issue it can prove, not only the first.
If a worker drops out, proceed with N-1 and note it.
Read the terminal results. Drop a result that does not record the SHAs and method its brief names, and respawn that worker once. After a second miss, record a gap. A gap does not count as a pass. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.
Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.
Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
中文简介正在准备中。当前显示原文说明。
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
中文简介正在准备中。当前显示原文说明。
Inspect or supervise a PR or stack through review and CI to merge-ready, using current GitHub evidence and the requested mode.
中文简介正在准备中。当前显示原文说明。
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you benchmark or report a measured speedup or regression, including complete framework flows and compilation of projects that consume the framework.
中文简介正在准备中。当前显示原文说明。
Restate the last message in plain human language, with no jargon.
中文简介正在准备中。当前显示原文说明。
Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.
中文简介正在准备中。当前显示原文说明。