← Back to Skills Marketplace

Advisor Board

Name: Advisor Board
Author: mambamentatily24

by mambaMentatily24 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ Security Clean

Downloads

Stars

Active Installs

Versions

Install in OpenClaw

/install advisor-board

Description

🎩 36 位顶级思维顾问帮你做决策。输入问题→自动全网检索→顾问多角度分析→输出行动建议。含毛泽东/德鲁克/Jobs/巴菲特等。免费基础版（15 位顾问），Pro 版解锁完整 36 位 + 报告导出 + 团队会诊。

README (SKILL.md)

顾问委员会会诊系统（36 位顶级思维顾问）

🔄 重要：会诊前先全网检索最新信息，确保顾问基于实时数据判断！

顾问名单

🇨🇳 战略层（3 位）

毛泽东（主要矛盾/统一战线）、段永平（本分/长期主义）、任正非（活下去/压强原则）

📍 定位与战略层（4 位）

特劳特（心智定位）、里斯（品类创新）、波特（五力模型）、克里斯坦森（颠覆式创新）

🎯 商业管理层（4 位）

德鲁克（客户/价值）、芒格（多学科思维）、巴菲特（护城河）、科特勒（STP/4P）

⚙️ 运营与咨询层（4 位）

丹纳赫 DBS（精益改善）、丰田精益（JIT/消除浪费）、六西格玛（质量管理）、麦肯锡（MECE）

📊 经济学层（5 位）

亚当·斯密（市场机制）、凯恩斯（需求管理）、哈耶克（自发秩序）、科斯（交易成本）、卡尼曼（行为经济）

💡 增长与创新层（3 位）

Jobs（极致体验）、原研哉（极简设计）、雷军（性价比/风口）

🚀 执行层（2 位）

马斯克（第一性原理）、杰克·韦尔奇（数一数二战略）

🧠 哲学与心理层（3 位）

维特根斯坦（概念澄清）、弗洛伊德（深层动机）、西奥迪尼（影响力原则）

📈 投资层（6 位将军）

宏观/个股/价值/逆向/创新/成长将军

🔧 技术层（5 位）

架构师/安全官/数据科学家/产品技术/运维专家

会诊流程（11 步）

第 0 步：全网检索 → 行业最新动态、竞争对手动作、政策法规变化

战略定位 → 毛泽东 + 特劳特 + 波特
经济环境 → 经济学层（如需要）
问题本质 → 维特根斯坦 + 弗洛伊德
价值定义 → 德鲁克 + 段永平 + 科特勒
体验系统 → Jobs + 原研哉
运营优化 → 丹纳赫 + 丰田 + 六西格玛
执行突破 → 马斯克 + 杰克·韦尔奇
风险决策 → 芒格 + 巴菲特 + 任正非
投资分析 → 投资 6 将军（如需要）
技术咨询 → 技术层 5 位（如需要）
行动收敛 → 段永平 + 马斯克（最小行动）

使用方法

触发词

"启动顾问会诊" / "36 位顾问分析一下" / "顾问委员会怎么看"
"问问 [顾问名]" / "让 [顾问名] 给点意见"

会诊主题

商业决策、产品设计、投资分析、人生规划、战略方向、技术评估

检索增强（默认开启）

自动检索：行业最新动态、竞争对手财报、政策法规变化、技术趋势

输出格式

# 顾问会诊报告
**主题：** [问题] | **时间：** [日期] | **参与顾问：** [列表]

## 🔍 全网检索情报
- 关键发现：[1-3 条]
- 行业动态：[最新趋势]
- 竞争格局：[对手动作]

## 各顾问观点
### [顾问名]
> [核心问题]
> [分析观点]

## 综合建议
1. [行动建议 1]
2. [行动建议 2]

## 下一步行动
- [ ] [具体行动]

记忆管理

会诊记录：memory/顾问会诊/YYYY-MM-DD.md
检索情报：memory/检索情报/YYYY-MM-DD.md
每周回顾更新 MEMORY.md

模型选择

类型	模型	检索
单顾问	Qwen3.5-Plus	简单
2-3 位	Claude Sonnet 4	标准
完整会诊	GPT-5/Claude Opus	深度

典型场景

新产品上市：特劳特 + 科特勒 + Jobs + 毛泽东
竞争战略：波特 + 毛泽东 + 特劳特 + 麦肯锡
投资决策：巴菲特 + 芒格 + 段永平 + 投资 6 将军
运营改善：丹纳赫 + 丰田 + 六西格玛
产品设计：Jobs + 原研哉 + 数据科学家
技术评审：架构师 + 安全官 + 运维专家

配置

依赖工具： web_search、web_fetch

存储目录： memory/顾问会诊/、memory/检索情报/

更新日志

v2.0 - 2026-04-01

✅ 补全 36 位顾问
✅ 新增全网检索功能
✅ 11 步会诊流程
✅ 检索情报保存

v1.0 - 初始版本

15 位顾问基础框架

Usage Guidance

This skill appears internally consistent for a decision‑support tool. Before installing, consider: 1) It will perform web searches (web_search/web_fetch) and ingest web content — avoid feeding highly sensitive secrets into consultations. 2) It saves reports/feedback under memory/… (persistent storage inside the agent); verify where 'memory/' is stored and who can access those files. 3) It schedules follow‑ups (7/30 day) and may send automated messages — confirm you want that autonomous behavior. 4) The included validator is a simple local script using substring matching (can misclassify quality), so validation is lightweight. 5) Pro/paid upgrade references exist but no payment integration is present in the package; check the publisher/homepage and payment flow before upgrading. If you need higher assurance, ask the publisher for a homepage, a privacy policy describing where memory is stored and how web fetches are performed, and whether scheduled follow‑ups can be disabled.

Capability Analysis

Type: OpenClaw Skill Name: advisor-board Version: 1.0.0 The 'advisor-board' skill bundle is a decision-support system that uses a multi-persona 'board of advisors' approach to analyze user queries. The bundle includes a Python validation script (consultation-validator.py) that performs safe string matching to ensure AI responses align with specific philosophical keywords. The skill's instructions (SKILL.md) and documentation (README.md, advisor-profiles.md) are consistent with its stated purpose, utilizing standard OpenClaw tools like 'web_search' and 'web_fetch' for legitimate information gathering and 'memory/' for state persistence. No evidence of malicious intent, data exfiltration, or unauthorized execution was found.

Capability Assessment

✓ Purpose & Capability

The name/description (36-advisor decision system) matches the SKILL.md and reference files. The SKILL.md explicitly declares the needed agent tools (web_search, web_fetch) and the files implement advisor profiles and a validator script — all expected for a decision/consultation skill. No unrelated credentials, binaries, or config paths are requested.

ℹ Instruction Scope

Instructions direct the agent to run '全网检索' (use web_search/web_fetch), assemble multi‑advisor analyses, save reports under memory/..., collect feedback, and run scheduled follow‑ups (7/30 day). These behaviors are aligned with the stated function but grant the skill scope to fetch arbitrary web content and persist user consultation data — notable for privacy and outbound activity even though they are within purpose.

✓ Install Mechanism

No install spec is present (instruction-only with shipped reference files and a small local Python validator). No downloads, package installs, or external archives are required.

✓ Credentials

The skill requests no environment variables, no credentials, and no access to unrelated config paths. The only storage referenced are agent memory paths (memory/顾问会诊/..., memory/检索情报/...).

ℹ Persistence & Privilege

always:false and agent invocation is normal. The SKILL.md intends to persist consultation reports, feedback logs, and run periodic follow‑ups — reasonable for this skill but means it will create/maintain data in the agent's memory directory and may autonomously message or re‑engage users per its workflow. Confirm you accept that persistent records and scheduled follow‑ups are part of the skill's behavior.

How to Use

Make sure OpenClaw is installed (local or Docker)
Run the install command in chat: /install advisor-board
After installation, invoke the skill by name or use /advisor-board
Provide required inputs per the skill's parameter spec and get structured output

Version History

v1.0.0

advisor-board 1.0.0 Changelog - 首发上线：顾问委员会会诊系统（advisor-board） - 提供 15 位顶级思维顾问，涵盖战略、管理、创新、心理等领域 - 支持多角度分析问题，输出具体行动建议 - 免费基础版，付费可升级 Pro（解锁 36 位顾问、报告导出等功能） - 集成触发词，支持商业决策、产品、投资、人生等场景

Metadata

Slug advisor-board

Version 1.0.0

License MIT-0

All-time Installs 0

Active Installs 0

Total Versions 1

Frequently Asked Questions

What is Advisor Board?

🎩 36 位顶级思维顾问帮你做决策。输入问题→自动全网检索→顾问多角度分析→输出行动建议。含毛泽东/德鲁克/Jobs/巴菲特等。免费基础版（15 位顾问），Pro 版解锁完整 36 位 + 报告导出 + 团队会诊。 It is an AI Agent Skill for Claude Code / OpenClaw, with 77 downloads so far.

How do I install Advisor Board?

Run "/install advisor-board" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Advisor Board free?

Yes, Advisor Board is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Advisor Board support?

Advisor Board is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Advisor Board?

It is built and maintained by mambaMentatily24 (@mambamentatily24); the current version is v1.0.0.

More Skills