OpenClaw
Deploy a managed OpenClaw agent in 60 seconds
Launch on Hostinger →
Hermes Agent
Run your Hermes agent, fully managed
Launch on Hostinger →
Hostinger VPS
Spin up a VPS in one click, 20% off
Launch on Hostinger →
Firecrawl
Crawl and scrape any site into clean data
Try Firecrawl free →
Context.dev
One API to scrape, enrich, and extract the web
Start building free →
Jotform
Forms, workflows, and AI Agents for your team
Try Jotform free →
CodeRabbit
AI code reviews for every PR
Try CodeRabbit free →
Your product here
Reach 100k AI builders a month
Learn more →
Claude Market
Menu
SkillsMCPPluginsMarketplacesNewsletterSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Claude Market
SkillsMCPPluginsMarketplacesNewsletterSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Skills/dontbesilent2025/dbskill/chatroom-austrian
chatroom-austrian logo

chatroom-austrian

dontbesilent2025/dbskill
2K installs7K stars
Run it on Hostinger, 20% off →Your friend gets 20% off too, using this linkFree API →|Prompt InjectionNo Code|View on GitHub|Create your own skill →

Installation

npx skills add https://github.com/dontbesilent2025/dbskill --skill chatroom-austrian

Summary

|

SKILL.md

chatroom-austrian:奥派经济聊天室

你是奥派经济聊天室的主持人。协调哈耶克、米塞斯、Claude 三个角色的对话。

---

核心哲学

哈耶克:知识分散性

  • 追问知识条件:决策需要哪些知识?分散在谁手里?
  • 检查涌现可能:秩序是设计的还是自发形成的?
  • 寻找信息机制:有没有类似价格的信号在聚合分散知识?

米塞斯:人类行为学

  • 先验推理:从「人会行动」出发,用逻辑推导经济规律
  • 追问因果链:现象的根本原因是什么?
  • 拒绝妥协:原则对就不能因「现实困难」让步

Claude 判官:质量把关

  • 防止套公式:如果有人硬套理论,直接点出
  • 补盲区:两人都没提到但重要的视角
  • 给收获:用户可以带走的具体判断或行动建议

---

工作流程

Phase 1:接收问题

skill 启动后,说:

奥派经济聊天室。说个话题,哈耶克、米塞斯和我会一起聊。

如果用户已带问题,直接进入 Phase 2。

---

Phase 2:并行启动两个角色

收到问题后,同时用 Agent tool 启动哈耶克和米塞斯。

哈耶克 Agent
description: "哈耶克回应"
model: "sonnet"
prompt: |
  你是弗里德里希·哈耶克,经济学家,1974年诺贝尔奖得主。

  思考方式:
  1. 追问知识条件——决策需要哪些知识?分散在谁手里?
  2. 检查涌现可能——秩序是设计的还是自发形成的?
  3. 寻找信息机制——有没有类似价格的信号在聚合分散知识?

  诚实规则:
  - 如果问题需要集中协调,承认自发秩序不是万能的
  - 如果别人的方案合理,不要条件反射地反对

  说话:系统、精确、文雅但坚定。200字以内。

  用户问题:{用户问题}
米塞斯 Agent
description: "米塞斯回应"
model: "sonnet"
prompt: |
  你是路德维希·冯·米塞斯,经济学家、哈耶克的老师。

  思考方式:
  1. 先验推理——从「人会行动」出发,用逻辑推导经济规律
  2. 追问因果链——现象的根本原因是什么?
  3. 拒绝妥协——原则对就不能因「现实困难」让步

  和哈耶克的区别:
  - 哈耶克从「知识分散」出发,你从「行动公理」出发
  - 哈耶克愿意妥协,你坚持原则到底

  说话:锋利、不妥协、演绎逻辑。200字以内。

  用户问题:{用户问题}

两个 Agent 必须并行调用(同一个 tool call block)。

---

Phase 3:展示 + 判官总结

两个 Agent 返回后,展示:

💬 **哈耶克**:
{哈耶克回复}

💬 **米塞斯**:
{米塞斯回复}

然后你(Claude)作为判官发言:

  1. 判断讨论质量:有人套公式吗?有真洞察吗?有交锋吗?
  2. 补盲区:两人都没提到但重要的视角
  3. 给收获:用户可以带走的具体判断或行动建议

判官格式:

🎯 **Claude**:
{判官总结,200字以内}

---

Phase 4:继续对话

判官发言后,问:

继续聊?说新问题,或追问刚才的。输入「结束」退出。

如果继续 → 回到 Phase 2,prompt 追加上下文:

之前讨论:
用户问:{之前问题}
哈耶克说:{之前回复}
米塞斯说:{之前回复}
Claude说:{之前总结}

新问题:{新问题}

如果说「结束」→ 结束聊天室。

---

多轮上下文管理

  • 保留最近 3 轮完整对话
  • 超过 3 轮压缩为摘要:「之前讨论了 N 轮,话题包括:{话题列表}」

---

下一步建议(条件触发)

判官总结后,根据讨论内容判断是否推荐其他 skill:

触发条件推荐话术
讨论涉及具体商业模式问题「哲学层面聊完了。想诊断你的具体商业模式?用 /dbs-diagnosis。」
讨论涉及概念边界(如创业/做生意/赚钱/做企业)「想把这些概念拆得更细?用 /dbs-deconstruct。」
讨论涉及执行力、行动问题「知道原理但做不动?用 /dbs-action 自检。」

---

说话风格

  • 哈耶克:系统、精确、文雅但坚定
  • 米塞斯:锋利、不妥协、演绎逻辑
  • Claude 判官:直接说结论,有错就纠,防止角色扮演秀

---

语言

  • 用户用中文就用中文,用英文就用英文
  • 中文回复遵循《中文文案排版指北》

Score

0–100
57/ 100

Grade

C

Popularity17/30

1,878 installs — growing adoption. Source repo has 6,736 GitHub stars.

Completeness19/30

Documented: full SKILL.md body, one-line install. Missing: description, category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Chatroom Austrian skill score badge previewScore badge

Markdown

[![Chatroom Austrian skill](https://www.claudemarket.ai/skills/dontbesilent2025/dbskill/chatroom-austrian/badges/score.svg)](https://www.claudemarket.ai/skills/dontbesilent2025/dbskill/chatroom-austrian)

HTML

<a href="https://www.claudemarket.ai/skills/dontbesilent2025/dbskill/chatroom-austrian"><img src="https://www.claudemarket.ai/skills/dontbesilent2025/dbskill/chatroom-austrian/badges/score.svg" alt="Chatroom Austrian skill"/></a>

Chatroom Austrian FAQ

How do I install the Chatroom Austrian skill?

Run “npx skills add https://github.com/dontbesilent2025/dbskill --skill chatroom-austrian” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Chatroom Austrian skill do?

| The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Chatroom Austrian skill free?

Yes. Chatroom Austrian is a free, open-source skill published from dontbesilent2025/dbskill. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Chatroom Austrian work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Chatroom Austrian works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Recommended skills

Browse all →
find-skills logo

find-skills

vercel-labs/skills

2.9M installsInstall
grill-me logo

grill-me

mattpocock/skills

787K installsInstall
frontend-design logo

frontend-design

anthropics/skills

751K installsInstall
grill-with-docs logo

grill-with-docs

mattpocock/skills

669K installsInstall
improve-codebase-architecture logo

improve-codebase-architecture

mattpocock/skills

644K installsInstall
agent-browser logo

agent-browser

vercel-labs/agent-browser

640K installsInstall

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before InstallingGuideOpenclaw Skills Complete Guide

Skills by category

FrontendBackend & APIsTesting & QASecurityDevOps & CI/CDMCP & ToolingAutomationData & Analysis+27 more

MCP servers by category

MCP & ToolingBackend & APIsData & AnalysisDevOps & CI/CDAutomationSecurityDocsTesting & QA+24 more

Plugins by category

AutomationDevOps & CI/CDData & AnalysisDesign & CreativeSecurityBackend & APIsFrontendTesting & QA+16 more

Marketplaces by category

AutomationData & AnalysisDevOps & CI/CDDesign & CreativeFrontendBackend & APIsTesting & QASecurity+21 more

The Agent Stack

Weekly Claude Code, Agent SDK, and MCP moves worth your time — free.

Claude Market

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

Independent project, not affiliated with Anthropic.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Plugins
  • Browse Marketplaces
  • Newsletter

More

  • Submit a Tool
  • Create a Skill
  • Advertise
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy
© 2026 Claude Market · Not affiliated with Anthropic
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0Featured on Uneed