菜单
N agents attempt the same task in parallel and a judge selects the winner (also scatter-gather / map-reduce). Use for 'best of N', contests, judge panels, generate-and-select, picking the strongest output. `tournament()` / `synthesis_gate()`.
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-tournament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。
正在显示 SKILL.md
基于 SOC 职业分类
| name | cave-tournament |
| description | N agents attempt the same task in parallel and a judge selects the winner (also scatter-gather / map-reduce). Use for 'best of N', contests, judge panels, generate-and-select, picking the strongest output. `tournament()` / `synthesis_gate()`. |
N competitors craft in parallel, then a judge selects (the tree-search pattern) — tournament(competitors, judge). The general scatter→merge form is synthesis_gate(workers, reducer) (map-reduce): run workers in parallel, then a reducer sees every output.
from cave_teams import tournament, synthesis_gate
best = tournament([minimalist, bold, nerdy], judge)
merged = synthesis_gate([clarity, punch, honesty], synthesizer) # map-reduce
The judge/reducer reads the competitors' outputs (output:<name> keys). In the crafter sim, the judge is the user's purchase — the sound external gate.
{"op": "tournament", "competitors": [<spec>, ...], "judge": <spec>}
// or: {"op": "map_reduce", "workers": [<spec>, ...], "reducer": <spec>}
If the spec is malformed, cave() returns {"status": "construction_error", "hint": "read the cave-tournament skill"} — the error names this skill.
cave-parallel · cave-evolve · cave-sim
Part of the cave-teams plugin — the language + full DSL is the cave-teams skill; drive any pattern from data with the cave skill.