菜单
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()`.
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-sim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-sim |
| description | 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()`. |
crafter_sim(population_dirs, spawn, judge, generations) runs the loop: each generation, spawn(dir) builds a crafter Link from an AIOS dir, the crafters compete, the judge (often the user's purchase) selects, and the winners evolve into the next generation. The async engine over cave-tournament + cave-evolve.
from pathlib import Path
from cave_teams import crafter_sim, AgentLink
result = await crafter_sim(
population_dirs=["seed1", "seed2"],
spawn=lambda d: AgentLink(Path(d).name, "craft the best X", backend="minimax"),
judge=user_purchase_judge,
generations=3)
Not a single cave() build-op — it's a composed simulation engine. Call crafter_sim() directly, or assemble the pieces with cave-tournament + cave-evolve + cave-world.
cave-tournament · cave-evolve · cave-world
Part of the cave-teams plugin — the language + full DSL is the cave-teams skill; drive any pattern from data with the cave skill.