菜单
Run agents at the same time on the same input (fan-out / scatter). Use for 'in parallel', 'at once', 'concurrently', 'fan out', multiple independent reviewers or checks. The `|` operator / `par()`.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/sancovp/cave-teams --skill cave-parallel命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | cave-parallel |
| description | Run agents at the same time on the same input (fan-out / scatter). Use for 'in parallel', 'at once', 'concurrently', 'fan out', multiple independent reviewers or checks. The `|` operator / `par()`. |
Run agents concurrently on the same input; each gets a copy of the context and their outputs merge back (each kept under output:<name>). The | operator, or par(a, b, c). To merge the results with a reducer, see cave-tournament (map_reduce).
reviews = clarity | punch | honesty
# or, by function:
from cave_teams import par
reviews = par(clarity, punch, honesty)
{"op": "par", "links": [<spec>, <spec>, ...]}
If the spec is malformed, cave() returns {"status": "construction_error", "hint": "read the cave-parallel skill"} — the error names this skill.
cave-sequential · cave-tournament · cave-teams
Part of the cave-teams plugin — the language + full DSL is the cave-teams skill; drive any pattern from data with the cave skill.