Alphagbm Tepper Signal logo

Alphagbm Tepper Signal

CommunityPopular
AlphaGBM
alphagbm-tepper-signal

Quantified version of David Tepper's 2009 (+132%) and 2020 (+82%) panic-buy playbook. Detects whether current conditions match Tepper's signal: VIX ≥ 35 AND FearScore ≥ 80 AND quality filter (large-cap, positive margin). Only fires during genuine market panics — the rest of the time it returns the "waiting" state, which is ~80% of all days per Tepper's own framework. The API reuses our existing FearScore module, so the signal is directly comparable to the multi-indicator panic index. Triggers: "is this a Tepper buy signal", "panic-buy detector SPY", "should I buy the panic", "Tepper style entry check", "are we at a panic bottom", "is VIX 35+ and fear 80+", "historical bottom signal today"

Overview

PublisherAlphaGBM
Repositoryskills
Skill namealphagbm-tepper-signal
Stars
2.7K
Forks
290
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AlphaGBM on GitHub. Read the source before you install it.

Installation

Install the Alphagbm Tepper Signal AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AlphaGBM/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/alphagbm-tepper-signal .claude/skills/alphagbm-tepper-signal
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Alphagbm Tepper Signal in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Alphagbm Tepper Signal on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Alphagbm Tepper Signal is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AlphaGBM Tepper Panic-Buy Signal

David Tepper made two historic panic-bottom calls: March 2009 ("I'm betting on the Fed") and March 2020 (COVID bottom). Both had identical fingerprints: VIX spiked > 40, multi-indicator fear was maxed, and Tepper loaded quality large-caps (banks 2009, SPY/QQQ 2020).

This skill mechanizes that fingerprint.

The Signal Logic

Three gates must all pass for the signal to arm:

  1. VIX ≥ 35 — extreme fear, not just elevated
  2. FearScore ≥ 80 — multi-indicator panic (reuses existing FearScore module: VIX + IV Rank + RSI + Volume + Put/Call + Consec-Down-Days)
  3. Quality filter — market cap > $50B AND profit margin > 0 (no memes, concept stocks, or pre-revenue small caps)

When all three pass → signal: true, level: armed.

Signal Levels

LevelConditionPrescription
armedVIX ≥ 35 AND Fear ≥ 80🔥 Historic-level buying moment — scale into SPY/QQQ/DIA
watchVIX ≥ 30 OR Fear ≥ 70⚡ Approaching — prepare capital, don't act yet
nearVIX ≥ 25 OR Fear ≥ 60Lukewarm — far from Tepper-level panic
coldbelowCalm — the patience state, which is most of the time

Tepper's own framework includes "do nothing" as a first-class state. Most calls to this endpoint will return cold — that's by design. The value isn't in the signal firing often, it's in never missing a VIX > 40 event.

Why This Is a Separate Skill

alphagbm-fear-score gives the raw panic index. alphagbm-vix-status gives the VIX tier. This skill combines them with Tepper's specific criteria (quality filter + threshold rules) to produce a single yes/no decision.

How to Use

Input:

  • ticker (optional, default SPY) — the quality-filter applies to this ticker

Output:

  • vix, fear_score — the two input signals
  • vix_pass, fear_pass, quality_pass — per-gate booleans
  • signal — final boolean
  • levelarmed / watch / near / cold
  • recommended_etfs["SPY", "QQQ", "DIA"] (quality large-cap universe)
  • advice_zh, advice_en — natural-language prescription

Example Queries

  • is this a Tepper buy signal → call with default SPY
  • panic-buy check on QQQ → substitute QQQ
  • should I buy the panic now → returns cold if calm → "wait, this is the patience state"
  • am I missing a historic bottom → the only time this fires, the answer is "yes, don't miss it"
  • Tepper-style entry for DIA → quality large-cap → passes quality filter

Mock Data

Mock data in mock-data/tepper-signal/ — samples for armed (VIX 42, Fear 85) and cold (VIX 17, Fear 35).

API Endpoint

POST /api/masters/tepper-signal
Content-Type: application/json

Request body:

json
{"ticker": "SPY"}

Response shape:

json
{
  "success": true,
  "ticker": "SPY",
  "vix": 42.0,
  "fear_score": 85,
  "vix_pass": true,
  "fear_pass": true,
  "quality_pass": true,
  "signal": true,
  "level": "armed",
  "recommended_etfs": ["SPY", "QQQ", "DIA"],
  "advice_zh": "信号激活 — VIX 42.0、FearScore 85。按 Tepper 2009/2020 规则,分批买入大盘质量 ETF (SPY, QQQ, DIA)。不要买概念股或小盘股。",
  "advice_en": "Signal armed — VIX 42.0, FearScore 85. Per Tepper 2009/2020, scale into quality large-cap ETFs (SPY, QQQ, DIA). No memes, no small caps.",
  "timestamp": "2026-04-24T08:00:00"
}

Pricing: 1 option-analysis credit per call; 5-min cache per ticker (cache hits free).

Related Skills

SkillRelevance
alphagbm-fear-scoreThe underlying panic index — component of this signal
alphagbm-vix-statusStandalone VIX tier — complementary read
alphagbm-duan-analysisDuan's VIX ≥ 35 panic-buy philosophy on a specific ticker

Powered by AlphaGBM — Real-data options & research intelligence. 10K+ users.

Frequently asked questions

What does the Alphagbm Tepper Signal AI skill do?

Quantified version of David Tepper's 2009 (+132%) and 2020 (+82%) panic-buy playbook. Detects whether current conditions match Tepper's signal: VIX ≥ 35 AND FearScore ≥ 80 AND quality filter (large-cap, positive margin). Only fires during genuine market panics — the rest of the time it returns the "waiting" state, which is ~80% of all days per Tepper's own framework. The API reuses our existing FearScore module, so the signal is directly comparable to the multi-indicator panic index. Triggers: "is this a Tepper buy signal", "panic-buy detector SPY", "should I buy the panic", "Tepper style e...

Why use Alphagbm Tepper Signal on TypingMind?

Because you install it once and use it with any model. Alphagbm Tepper Signal is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Alphagbm Tepper Signal in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlphaGBM/skills/tree/main/skills/alphagbm-tepper-signal. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Alphagbm Tepper Signal?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Alphagbm Tepper Signal?

As many as you like. As long as a model supports skills, you can use Alphagbm Tepper Signal with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Alphagbm Tepper Signal AI skill free?

Yes. It is published on GitHub by AlphaGBM under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇