XVARY Stock Research
XVARY Stock Research is a Claude Code skill that generates thesis-driven equity reports with conviction scoring, kill criteria, and EDGAR-backed financial snapshots from public data. It solves the problem of raw data tools lacking analysis and verdicts, and is for developers and analysts who want quick, structured stock research without API keys.
✨ Key features
- Provides a verdict with conviction score, not just data
- Names kill criteria that would break the thesis
- Composite scores across momentum, stability, financial health, upside
- EDGAR-backed financial snapshot from public SEC data
- Works locally with no API key required
- Published methodology and scoring framework
🎯 Use cases
- Run /analyze NVDA to get a one-page thesis and scorecard
- Compare two tickers side-by-side with /compare
- Score a stock on four dimensions with /score
- Pull SEC XBRL data and market data via command-line tools
- Integrate as a Claude Code plugin for in-editor research
📦 Installation
🧰 Requirements: Requires Python 3 and Claude Code; no API keys needed.
git clone git@github.com:xvary-research/claude-code-stock-analysis-skill.git
cd claude-code-stock-analysis-skill
python3 tools/edgar.py AAPL # pulls SEC XBRL data
python3 tools/market.py AAPL # pulls price + ratios
Install as a Claude Code skill:
mkdir -p ~/.claude/skills/xvary-stock-research
cp SKILL.md ~/.claude/skills/xvary-stock-research/SKILL.md
cp -R references tools examples ~/.claude/skills/xvary-stock-research/
Or open Claude Code in this repo and say:
Read SKILL.md and run /analyze AAPL
🚀 Usage
/analyze NVDA
Example output:
Verdict: CONSTRUCTIVE (Conviction 74/100)
┌─────────────────┬───────┬──────────────────────────────────────────────┐
│ Score │ Value │ Read │
├─────────────────┼───────┼──────────────────────────────────────────────┤
│ Momentum │ 88 │ Demand + operating leverage remain strong │
│ Stability │ 70 │ Strong execution, non-zero cyclicality risk │
│ Financial Health│ 84 │ Robust balance sheet vs obligations │
│ Upside Estimate │ 64 │ Positive setup, expectations already high │
└─────────────────┴───────┴──────────────────────────────────────────────┘
⚠️ Good to know
This is the free skill layer; full 22-section deep dives with DCF models and competitive matrices are available on xvary.com with subscription.
❓ FAQ
Do I need an API key to use this skill?
No, it uses public data sources like SEC EDGAR and Yahoo Finance without requiring an API key.
What commands are available?
The main commands are /analyze {ticker}, /score {ticker}, and /compare {A} vs {B}.
How is this different from raw data tools?
It provides a verdict, named kill criteria, and composite scores across four dimensions, rather than just raw data.
Can I use it as a Claude Code plugin?
Yes, you can add the marketplace from this repo and install the plugin, or use the skill directly.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.