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()`.
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。
基于 SOC 职业分类
Drive the whole cave-teams library from one function, as DATA — build/run any team from a spec in any sequence, save a team to your proven library, reuse a proven team anywhere, and discover teams across projects. Use when you want to serialize a team, run a team from JSON/dict, save+reuse a proven team across repos ("golden"), or have a higher system / global app drive cave-teams. NOT how you normally program (use the cave-teams DSL for that). Triggers: "cave()", "metacontrol", "run from a spec", "team as data", "golden team", "reuse a proven team", "scan for .cave", "global cave".
Build and run programmable agent teams with cave-teams — the provider-agnostic version of Claude Code Teams. Use when the user wants to wire multiple agents together, run agents in sequence or parallel, build a multi-agent pipeline/workflow, make a "team" of coding agents (Claude Code, Codex, MiniMax, or any), loop an agent until a check passes, run a contest between agents, or compose agents with the >> / | DSL. Triggers: "agent team", "multi-agent", "orchestrate agents", "wire these agents", "run agents in parallel", "cave-teams", "agent pipeline", "agent workflow".
Program WHEN each agent may be messaged — conditions on messages, the GUARDRAILS of a leader-driven team run. Use to gate agents on runtime state: after these two respond, only when a flag holds, any predicate over the message log. THIS is what makes cave-teams programmable where Claude Code Teams' flow is fixed.
Run agents that craft, compete, and evolve over generations — the user buys the best, winners reproduce. A compiler (a domain → a trained agent) and a research lab (selection discovers what works) in one engine. `crafter_sim()`.
N agents read and write a shared state over rounds, with a mutator that folds each contribution in and an optional adjudicator (stigmergy arena). Use for agents collaborating on a shared board, a market, a workspace they all see. `blackboard()`.
Run different agents depending on a condition (guarded choice / router). Use for 'if X do this else that', routing, triage, picking a path by the state. `choice()` / `router()`.
| 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.