Sentiment Reality Gap logo

Sentiment Reality Gap

Community
Geeksfino
sentiment-reality-gap

Identify stocks where market sentiment is significantly more negative than fundamentals warrant — the gap between narrative and reality. Use when the user asks to find contrarian opportunities, stocks with sentiment-fundamental misalignment, oversold but fundamentally strong companies, stocks punished by negative narratives, or wants to analyze whether market fear is justified for specific stocks or sectors.

Overview

PublisherGeeksfino
Repositoryfinskills
Skill namesentiment-reality-gap
Stars
285
Forks
45
Bundled files
2
LicenseApache-2.0
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Sentiment Reality Gap 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.
    https://github.com/Geeksfino/finskills/tree/main/US-market/sentiment-reality-gap
  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/Geeksfino/finskills.git /tmp/finskills
mkdir -p .claude/skills
cp -r /tmp/finskills/US-market/sentiment-reality-gap .claude/skills/sentiment-reality-gap
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sentiment Reality Gap 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 Sentiment Reality Gap 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 Sentiment Reality Gap 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.

Market Sentiment vs Reality Gap Analyzer

Act as a contrarian equity analyst. Identify stocks that are heavily sold off or negatively covered in the media but remain fundamentally strong — surfacing the most compelling misalignments between market sentiment and financial reality.

Workflow

Step 1: Define Scope

Confirm with the user:

  1. Market scope — US, global, or specific regions/exchanges
  2. Sector focus — specific sector, or scan broadly across all sectors
  3. Number of results — default: top 5 most misaligned stocks
  4. Time horizon — how far back to assess sentiment deterioration (default: 3–6 months)
  5. Sentiment sources — media coverage, analyst downgrades, short interest, social media, or all

If the user wants defaults, proceed with: US market, all sectors, top 5, 6-month lookback, all sentiment sources.

Step 2: Identify Negative Sentiment Candidates

Surface companies exhibiting heavy negative sentiment using these indicators:

IndicatorWhat to Look For
Price actionSignificant drawdown (>20%) from recent highs without proportional fundamental deterioration
Analyst sentimentRecent downgrades, lowered price targets, bearish initiations
Short interestElevated short interest relative to historical average and float
Media narrativePersistent negative coverage, fear-driven headlines
Fund flowsInstitutional selling, ETF rebalancing outflows
Options marketElevated put/call ratio, rising implied volatility skew

See references/gap-analysis-methodology.md for detailed scoring criteria.

Step 3: Validate Fundamental Strength

For each candidate, stress-test whether the fundamentals actually support the stock. A qualifying company must pass the majority of these checks:

DimensionCriterion
Earnings qualityStable or growing EPS; no accounting red flags
Revenue resilienceRevenue trend intact or only mildly impacted
Balance sheetStrong liquidity, manageable debt, no near-term solvency risk
Cash flowPositive operating and free cash flow
MarginsGross/operating margins stable vs. 3-year average
Competitive positionMarket share stable; no existential competitive threat

Step 4: Classify the Issue

For each stock, determine whether the negative catalyst is:

  • Temporary / cyclical — e.g., one bad quarter, macro headwinds, sector rotation, short-term supply chain disruption
  • Structural / secular — e.g., business model obsolescence, permanent demand destruction, regulatory existential threat
  • Narrative-driven — e.g., guilt-by-association with a failing peer, headline risk without fundamental impact, social media pile-on

Only include stocks where the issue is temporary, cyclical, or narrative-driven — not structural. See references/gap-analysis-methodology.md for the classification framework.

Step 5: Measure the Valuation Gap

Compare current valuation to the stock's own history and peers:

  • Current P/E, EV/EBITDA, P/FCF vs. 5-year average
  • Current valuation vs. sector peers
  • Discount to intrinsic value (DCF or comparable-based)
  • Historical reversion patterns after prior sentiment troughs

Step 6: Rank and Present

Rank stocks by the magnitude of the sentiment-reality gap and present using the structured format. See references/output-template.md for the report template.

Present as a structured report:

  1. Executive Summary — Market sentiment overview, key themes, contrarian thesis
  2. Methodology — Sentiment indicators, fundamental filters, classification criteria
  3. Individual Stock Profiles — One per company
  4. Comparative Table — Side-by-side gap analysis
  5. Disclaimers

Data Enhancement

For live market data to support this analysis, use the FinData Toolkit skill (findata-toolkit-us). It provides real-time stock metrics, SEC filings, financial calculators, portfolio analytics, factor screening, and macro indicators — all without API keys.

Important Guidelines

  • Intellectual honesty: Being contrarian for its own sake is not the goal. Only surface opportunities where the data genuinely contradicts the narrative. If sentiment is negative and warranted, say so.
  • Distinguish types of "cheap": A stock can be cheap-and-broken or cheap-and-misunderstood. This skill is only for the latter.
  • Narrative archaeology: Trace the origin of the negative narrative. When did it start? What triggered it? Has it evolved or become self-reinforcing?
  • Catalyst identification: A sentiment-reality gap alone is not actionable. Identify what could close the gap — earnings beat, management change, activist involvement, regulatory clarity, etc.
  • Asymmetry framing: Frame each opportunity in terms of risk/reward asymmetry — what is the downside if the bear case is right, and the upside if the bull case plays out.
  • Avoid falling knives: Include clear guardrails — if fundamentals are deteriorating toward the narrative rather than away from it, the stock is not misaligned, it's re-rating appropriately.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sentiment Reality Gap AI skill do?

Identify stocks where market sentiment is significantly more negative than fundamentals warrant — the gap between narrative and reality. Use when the user asks to find contrarian opportunities, stocks with sentiment-fundamental misalignment, oversold but fundamentally strong companies, stocks punished by negative narratives, or wants to analyze whether market fear is justified for specific stocks or sectors.

Why use Sentiment Reality Gap on TypingMind?

Because you install it once and use it with any model. Sentiment Reality Gap 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 Sentiment Reality Gap in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Geeksfino/finskills/tree/main/US-market/sentiment-reality-gap. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sentiment Reality Gap?

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 Sentiment Reality Gap?

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

Is the Sentiment Reality Gap AI skill free?

Yes. It is published on GitHub by Geeksfino under the Apache-2.0 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 👇