Crewai Multi Agent

v0.1.0

CrewAI 多智能体框架：role-goal-backstory 声明智能体，sequential / hierarchical 双流程，ReAct 与 OpenAI native function-calling 双 tool 循环，统一 Memory + 5 个原生 LLM provider + Lit C...

⭐ 0· 24·0 current·0 all-time

byTang Weigang@tangweigang-jpg

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for tangweigang-jpg/crewai-multi-agent.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "Crewai Multi Agent" (tangweigang-jpg/crewai-multi-agent) from ClawHub.
Skill page: https://clawhub.ai/tangweigang-jpg/crewai-multi-agent
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install tangweigang-jpg/crewai-multi-agent

ClawHub CLI

Package manager switcher

npx clawhub@latest install crewai-multi-agent

Security Scan

Capability signals

Crypto

These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.

VirusTotal

Benign

View report →

OpenClaw

Benign

high confidence

✓

Purpose & Capability

Name/description describe a multi-agent CrewAI framework and the package contains a detailed seed.yaml and human summary for a finance blueprint that references ZVT and LLM providers. The files and runtime instructions align with that purpose; nothing requires unrelated services or credentials.

ℹ

Instruction Scope

Runtime instructions require the host AI to read the bundled references/seed.yaml and to run precondition checks (python commands) that inspect the local environment (zvt import, ZVT_HOME, writable directories, K-data availability). Those file and command checks are appropriate for a finance/backtest blueprint but do instruct the agent to access the user's filesystem and run local Python commands — this is expected for the described tasks but worth noting.

✓

Install Mechanism

No install spec or code files are present; the skill is instruction-only. No downloads or external install URLs are requested, which minimizes install-time risk.

✓

Credentials

The skill declares no required environment variables or credentials (primaryEnv is the non-sensitive label 'knowledge'). The seed.yaml lists precondition checks that reference local paths and Python packages (zvt) which are proportional to a finance/backtest toolkit; there are no unrelated secret or cloud credentials requested.

✓

Persistence & Privilege

always is false and the skill does not request persistent or elevated system privileges. It instructs the host to read its bundled seed.yaml and to use host workspace paths for scripts/skills/trace; this is standard behavior for host-driven blueprints and does not modify other skills' configs.

Assessment

This is an instruction-only blueprint for running CrewAI-based multi-agent finance workflows. It will ask the host to read the included seed.yaml and to run local Python precondition checks (e.g., verify zvt is installed, check ~/.zvt write permission). That behavior is consistent with backtesting/data-retrieval tasks but does involve reading your filesystem and executing small python checks. Before installing, ensure you are comfortable with the agent running those local checks and that you understand the preconditions (zvt, data dirs). If you need to avoid filesystem access or installing packages, do not run the precondition steps or run the skill in an isolated environment.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

Primary envknowledge

aivk979aysm01gh36wp38z4xg931d85g35tapivk979aysm01gh36wp38z4xg931d85g35tlatestvk979aysm01gh36wp38z4xg931d85g35tmlvk979aysm01gh36wp38z4xg931d85g35t

24downloads

0stars

1versions

Updated 6h ago

v0.1.0

MIT-0

这个 skill 适合什么用户？能做哪些任务？

概览

CrewAI 是构建多智能体 LLM 应用的 Python 框架（github.com/joaomdmoura/crewAI）。核心特征：role-goal-backstory 智能体声明，两种执行流程（sequential / hierarchical 含 auto- 或自定义 manager），双 tool-call 循环（ReAct 文本解析 vs OpenAI 原生 function-calling，运行时特征探测选择），统一 Memory 层（Memory + MemorySlice + RecallFlow，自适应深度召回），可插拔 LLM provider 路由（5 个原生 SD...

Doramagic 晶体页: https://doramagic.ai/zh/crystal/crewai-multi-agent

知识规模

56 条约束 (5 fatal + 51 non-fatal)
上游源码: joaomdmoura/crewAI @ commit cb46a1c4
蓝图 ID: finance-bp-134

用法

Host AI（Claude Code / Cursor / OpenClaw）读 references/seed.yaml，按其中的：

intent_router 匹配用户意图
architecture 理解项目架构
constraints 应用 anti-pattern 约束
business_decisions 参考核心设计决策

FAQ 摘要

这个 skill 适合什么用户？能做哪些任务？

适合需要多 agent 协作完成复杂任务的工程师：研究 + 写作 + 校对、数据采集 + 分析 + 报告、销售线索挖掘 + 跟进等。两种流程满足不同需求：sequential 适合明确流水线，hierarchical 适合需要 manager 调度的开放任务。访问 doramagic.ai/r/crewai 查看完整用例。

需要准备什么环境？依赖什么？

Python（版本见 pyproject.toml），至少一个 LLM provider（Memory 默认 OpenAI gpt-4o-mini；Crew agent 各自挑 llm）。Memory 启用时默认 OpenAIEmbeddingFunction 嵌入 + lancedb 向量库。如需走非原生 SDK 模型，安装 LiteLLM。空气墙 / 数据驻留场景必须 ENV 关闭遥测。

会踩哪些坑？这个 skill 怎么防护？

本 skill 内置 56 条约束（5 条 fatal）。典型踩坑：(1) aggregate_raw_outputs_from_task_outputs 无 token cap，长任务链溢出 LLM 上下文；(2) tool 重复使用检测只比 last_used_tool，A→B→A→B 振荡漏检；

完整文档: 见 references/seed.yaml (v6.1 schema). 浏览页: https://doramagic.ai/zh/crystal/crewai-multi-agent

Comments

Loading comments...