No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by xbtlin · MCP Server · ★ 16.6k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ai-berkshire safe to install? View the security audit →
AI Berkshire - AI 时代的价值投资研究框架 "Price is what you pay, value is what you get." — Warren Buffett 用 AI 重新定义投资研究的深度与效率。 AI Berkshire 是一套基于 Claude Code 的投资研究 Skill 合集，将巴菲特、芒格、段永平、李录四位价值投资大师的方法论系统化、结构化，通过 AI Agent 实现专业级投资研究。 一个人 + Claude = 一个投研团队。 Real Track Record 不是纸上谈兵。这套框架背后是真金白银验证的投资体系。 2024 全年收益：+69.29% 2025 年至今收益：+66.38% 与主要指数对比 2024 年超额收益：跑赢标普500 46个百分点，跑赢恒生指数 52个百分点 2025 年超额收益：跑赢标普500 50个百分点，跑赢恒生指数 39个百分点 两年累计实盘收益超 146万元，连续两年大幅跑赢全球主要指数。 免责声明：历史收益不代表未来表现。截图来自富途证券真实账户。 为什么不能直接问 AI？ 你当然可以直接问 Claude："帮我分析拼多多值不值得买"。你会得到一篇"一方面...另一方面..."的平衡分析，最后以"投资有风险，请自行判断"收尾。 这种分析看起来对，但没法拿来做决策。 AI Berkshire 解决的不是"能不能分析"的问题，而是分析质量和决策纪律的问题。以下是核心差异： 强制给结论，不打太极 直接问AI，你得到的是两面讨好的"分析"。AI Berkshire 强制输出：通过/不通过/灰色地带，带具体价格区间和分层建议。 普通AI回答："拼多多有增长潜力但也面临竞争压力，投资者需要权衡..." AI Berkshire 输出： 镜子测试：5句话说不完整 = 不买，没有例外。 四大师视角对抗，而非单一分析 不是"用巴菲特方法分析一下"这么简单。四个视角会产生真实的矛盾和张力—— 以拼多多为例： 段永平（商业模
| Stars | 16,564 |
| Forks | 2,477 |
| Language | HTML |
| Category | MCP Server |
| License | MIT |
| Quality Score | 59.9421372242652/100 |
| Open Issues | 31 |
| Last Updated | 2026-09-27 |
| Created | 2026-04-07 |
| Platforms | claude-code, codex, mcp |
| Est. Tokens | ~19k |
Looking for a ai-berkshire alternative? If you're comparing ai-berkshire with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Pr
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici
CowAgent是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页
⌥ Coding agent with the IDE wired in. Built by Stencil Labs.
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets,
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
Explore other popular mcp server tools:
ai-berkshire is AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-ag. It is categorized as a MCP Server with 16.6k GitHub stars.
ai-berkshire is primarily written in HTML. It covers topics such as ai, ai-agent, anthropic.
You can find installation instructions and usage details in the ai-berkshire GitHub repository at github.com/xbtlin/ai-berkshire. The project has 16.6k stars and 2477 forks, indicating an active community.
ai-berkshire is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ai-berkshire on Agent Skills Hub include ai-guide, Unity-MCP, chatgpt-on-wechat. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: