Token导航 LogoToken导航

Agent Skill · 研究检索

einstein-research-bubble-dv(爱因斯坦研究气泡 dv)

einstein-research-bubble-dv 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

einstein-research-bubble-dv 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 24,059。

总安装 4,113周安装 168GitHub Stars 公开资料未说明下载 1,331核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.1.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:einstein-research-bubble-dv(爱因斯坦研究气泡 dv)
来源仓库:https://github.com/clawdiri-ai/einstein-research-bubble-dv
安装命令:
openclaw skills install einstein-research-bubble-dv
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install einstein-research-bubble-dv

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

einstein-research-bubble-dv 基于明斯基/金德尔伯格框架评估市场泡沫风险。专为 OpenClaw 设计,适用于识别潜在资产过热信号。通过 ClawHub 安装,优先考虑客观指标而非主观子分数。使用前需确认权限范围、维护状态,以及是否会触发宏观经济数据分析操作。

建议定期运行并结合基本面信息综合研判市场状态。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install einstein-research-bubble-dv;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

einstein-research-bubble-dv 怎么安装?

在终端执行 openclaw skills install einstein-research-bubble-dv。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

einstein-research-bubble-dv 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

einstein-research-bubble-dv 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

einstein-research-bubble-dv 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

einstein-research-bubble-dv 用的人多吗?

公开数据是累计安装 4,113 次,近一周安装 168 次,下载 1,331 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

einstein-research-bubble-dv 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
einstein-research-bubble-dv

爱因斯坦研究气泡 dv · 本页

4,113—需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

id
einstein-research-bubble
name
Einstein Research — Market Bubble Risk Detector
description
Evaluates market bubble risk through quantitative, data-driven analysis using a revised Minsky/Kindleberger framework. Prioritizes objective metrics over subjective impressions to prevent confirmation bias and support practical investment decisions.
version
1.0.0
author
DaVinci
last_amended_at
null
trigger_patterns
[]
pre_conditions
git_repo_required
false
tools_available
[]
expected_output_format
natural_language

Market Bubble Risk Detector

Overview

This skill evaluates market bubble risk through a quantitative, data-driven analysis based on a revised Minsky/Kindleberger framework. It prioritizes objective metrics over subjective impressions to prevent confirmation bias and support practical investment decisions.

Core Principles:

  • Data over Narrative: Relies on measurable data, not just "it feels frothy."
  • Composite Score: Generates a score from 0-100 to quantify bubble risk.
  • Multi-Factor Model: Incorporates sentiment, valuation, leverage, market structure, and new issuance data.
  • Action-Oriented: Provides clear thresholds for tactical adjustments (e.g., raising cash, hedging).

When to Use This Skill

Explicit Triggers:

  • "Are we in a stock market bubble?"
  • "Analyze the risk of a market crash."
  • "Is the market overvalued?"
  • "Should I be taking profits?"
  • User asks about "bubble risk," "market froth," "irrational exuberance," or "Minsky moment."

Implicit Triggers:

  • User expresses anxiety about high valuations or a rapid market run-up.
  • User is considering de-risking their portfolio.

Workflow

Step 1: Execute the Data Collection and Analysis Script

The bubble-detector CLI tool automates the entire process.

bubble-detector run

The script performs the following actions:

  1. Fetches Data: Collects data for each of the 7 quantitative indicators.

- Put/Call Ratio (CBOE) - VIX Index (CBOE) - Margin Debt (FINRA) - Market Breadth (% Stocks > 200d MA) - IPO Issuance (e.g., from a public data source) - Retail Volume as % of Total - Forward P/E Ratio vs. Historical Average

  1. Normalizes Indicators: For each indicator, it calculates a percentile rank over the last 5 years. A rank of 100 means the indicator is at its most "bubbly" level in 5 years.
  2. Calculates Composite Score: A weighted average of the normalized indicator scores.

- Sentiment (Put/Call, VIX, Retail Volume): 40% - Leverage (Margin Debt): 20% - Market Structure (Breadth): 20% - Valuation & Issuance (P/E, IPOs): 20%

  1. Generates Report: Outputs a JSON file and a Markdown summary.

Step 2: Analyze the Report

JSON Output (bubble_report_YYYY-MM-DD.json):

  • Contains the raw data, normalized scores for each indicator, and the final composite score.

Markdown Report (bubble_report_YYYY-MM-DD.md):

  • Overall Bubble Score: e.g., "78 / 100 (High Risk)"
  • Indicator Dashboard: A table showing the current value and normalized score for each of the 7 indicators.
  • Key Drivers: Highlights which indicators are contributing most to the high score.
  • Historical Context: Compares the current score to levels seen before previous market corrections.
  • Recommended Posture: Translates the score into a tactical recommendation.

Interpretation & Recommended Actions

The composite score maps to specific risk postures:

  • 0-40 (Low Risk - "Accumulate"):

- *Characteristics*: Fear is high, valuations are reasonable, leverage is low. - *Action*: A good time to be deploying capital and taking on risk.

  • 41-60 (Moderate Risk - "Cautious Accumulation"):

- *Characteristics*: Market is healthy but not cheap. Some signs of optimism are emerging. - *Action*: Continue to invest, but perhaps with a greater focus on quality.

  • 61-80 (High Risk - "Hold & Hedge"):

- *Characteristics*: Greed is prevalent, valuations are stretched, breadth may be narrowing. - *Action*: Hold existing positions, but stop new aggressive buying. Consider adding hedges (e.g., puts) or raising a small amount of cash.

  • 81-100 (Very High Risk - "Distribute & Protect"):

- *Characteristics*: Euphoria, extreme valuations, high leverage, widespread speculation. - *Action*: Systematically take profits from high-beta positions. Raise significant cash (e.g., 20-40%). Actively hedge the remaining portfolio. This is the time to be selling to the optimists.

Important Considerations

  • Not a Timing Tool: This skill indicates *when risk is high*, not the exact top of the market. Bubbly conditions can persist for months.
  • Context is Key: Always present the score in the context of the underlying indicators. A high score driven by stretched valuations is different from one driven by extreme sentiment.
  • No Panicking: The goal is to make small, rational adjustments to risk exposure, not to sell everything in a panic.

平台分布

OpenClaw

79.46%
按下载量换算1,058

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills