菜单
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()`.
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-blackboard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。
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.
基于 SOC 职业分类
正在显示 SKILL.md
| name | cave-blackboard |
| description | 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()`. |
The arena / stigmergy core: N agents ↔ a shared state ↔ a mutator ((board, name, value) -> board) over rounds, with an optional adjudicator Link. The gameworld's core building block.
from cave_teams import blackboard
from cave_teams import register_fn
# the mutator folds each agent's contribution into the shared board:
def keep_latest(board, name, value): return {**board, name: value}
arena = blackboard({"a": a, "b": b}, keep_latest, adjudicator=judge, rounds=3)
The mutator is required and is a Python callable. For the cave() spec, register it by name (register_fn) and reference the name — that's the callable axis of extending the metacontrol surface.
{"op": "blackboard", "agents": {"a": <spec>, "b": <spec>},
"mutator": "keep_latest", "rounds": 3}
// the mutator is referenced BY NAME — register it first:
// cave_teams.register_fn("keep_latest", keep_latest)
If the spec is malformed, cave() returns {"status": "construction_error", "hint": "read the cave-blackboard skill"} — the error names this skill.
cave-season · cave-world · cave
Part of the cave-teams plugin — the language + full DSL is the cave-teams skill; drive any pattern from data with the cave skill.