Dividend Analysis logo

Dividend Analysis

OrganizationPopular
HKUDS
dividend-analysis

Dividend stock analysis for income, dividend-growth, and shareholder-return strategies, including yield quality, payout sustainability, ex-dividend mechanics, and yield-trap checks.

Overview

PublisherHKUDS
RepositoryVibe-Trading
Skill namedividend-analysis
Stars
33.6K
Forks
5.5K
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 HKUDS on GitHub. Read the source before you install it.

Installation

Install the Dividend Analysis 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/HKUDS/Vibe-Trading.git /tmp/Vibe-Trading
mkdir -p .claude/skills
cp -r /tmp/Vibe-Trading/agent/src/skills/dividend-analysis .claude/skills/dividend-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dividend Analysis 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 Dividend Analysis 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 Dividend Analysis 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.

Dividend Analysis

Purpose

Use this skill when the user asks about dividend stocks, income portfolios, dividend growth, high-yield screening, payout safety, ex-dividend dates, or whether a dividend is sustainable. The goal is to separate durable shareholder returns from yield traps.

Dividend analysis should never stop at headline yield. A good answer explains how the dividend is funded, how stable the underlying business is, whether management has room to keep paying, and how valuation changes the expected total return.

Core Questions

  1. What is the current cash yield, and is it normal for this company or sector?
  2. Is the payout covered by earnings, operating cash flow, and free cash flow?
  3. Is the balance sheet strong enough to absorb a down cycle?
  4. Has management grown, held, cut, or suspended the dividend across cycles?
  5. Does the valuation still leave room for total return after taxes and reinvestment assumptions?

Key Metrics

MetricFormulaHealthy SignalWarning Signal
Dividend yieldannual DPS / current priceAbove peer median with stable coverageExtremely high vs history or peers
Earnings payout ratiodividends / net income, or DPS / EPS30-70% for mature non-financialsAbove 90%, negative earnings
Free-cash-flow payoutdividends / FCFBelow 70% through a cycleDividend exceeds FCF for 2+ years
CFO coverageoperating cash flow / dividends paidAbove 1.5xBelow 1.0x
Dividend CAGRDPS growth over 3/5/10 yearsPositive and below EPS/FCF growthGrowth funded by leverage
Net debt / EBITDAnet debt / EBITDASector-appropriate leverageLeverage rising while payout rises
Buyback plus dividend yield(dividends + net buybacks) / market capBalanced capital returnBuybacks funded by debt at high valuation

For REITs, utilities, banks, MLPs, and insurers, adapt the payout metric to the sector. For example, use AFFO payout for REITs, distributable cash flow for MLPs, and regulatory capital ratios for banks and insurers.

Analysis Workflow

Step 1: Normalize the Dividend

  • Use forward indicated dividend for recurring payments.
  • Separate ordinary dividends from special dividends.
  • Check whether the latest declared dividend is annual, semiannual, quarterly, monthly, or irregular.
  • For ADRs and cross-listed shares, account for depositary ratios, withholding tax, and FX conversion.
python
annual_dividend = regular_dividend_per_period * payments_per_year
dividend_yield = annual_dividend / current_price

Step 2: Check Coverage

Start with earnings coverage, then confirm with cash coverage.

python
earnings_payout = dividends_paid / net_income
fcf_payout = dividends_paid / free_cash_flow
cfo_coverage = operating_cash_flow / dividends_paid

Interpretation:

  • Good: net income, CFO, and FCF all cover dividends across multiple years.
  • Watch: earnings cover dividends but FCF does not, especially during capex-heavy periods.
  • Avoid: dividends are paid while both earnings and FCF are negative, unless there is a clear one-time reason and a strong balance sheet.

Step 3: Diagnose Dividend Growth Quality

Dividend growth is high quality when it follows business growth.

python
dividend_cagr = (dps_end / dps_start) ** (1 / years) - 1
eps_cagr = (eps_end / eps_start) ** (1 / years) - 1
fcf_cagr = (fcf_end / fcf_start) ** (1 / years) - 1

Quality rules:

  • Dividend CAGR below EPS and FCF CAGR usually leaves room for future increases.
  • Dividend CAGR above EPS/FCF CAGR means payout ratio is expanding.
  • Flat dividend with rising FCF may imply hidden capacity or conservative management.
  • Repeated small increases can still be fragile if leverage is rising.

Step 4: Check Balance Sheet Flexibility

Look for the ability to maintain dividends during stress.

ItemWhy It Matters
Cash and short-term investmentsNear-term cushion
Net debt / EBITDADebt burden against operating earnings
Interest coverageAbility to service debt before shareholder returns
Debt maturity wallRefinancing risk in high-rate environments
Credit rating or covenant languageExternal constraints on payout policy

Step 5: Separate Dividend Yield from Total Return

Dividend stocks can underperform if the yield comes from a falling price. Always connect income to valuation and growth.

python
expected_total_return = dividend_yield + expected_eps_growth + valuation_rerating

Do not present this as a guarantee. Use it as a scenario framework.

Yield-Trap Checklist

Flag a potential yield trap when several of these are true:

  • Dividend yield is more than 2x the company's 5-year median or sector median.
  • Payout ratio is above 90%, or FCF payout is above 100%.
  • Revenue, EPS, or FCF has declined for 2+ years.
  • Net debt / EBITDA is rising while interest coverage is falling.
  • Management has recently issued equity or debt while maintaining dividends.
  • The stock price fell before the yield became attractive.
  • Dividend history includes cuts, suspensions, or frequent special dividends labeled as ordinary income.
  • Sector faces structural pressure, regulation risk, or commodity down-cycle exposure.

Strategy Types

Dividend Growth

Prioritize moderate yield, strong dividend CAGR, low payout ratio, and durable business quality.

Good for users seeking compounding and lower cut risk.

High-Yield Quality

Prioritize yield, but require cash coverage, balance sheet resilience, and sector-aware payout norms.

Good for users seeking current income, but the answer must discuss cut risk.

Shareholder Yield

Combine dividends, net buybacks, and debt reduction.

Useful when companies return capital mostly through buybacks rather than cash dividends.

python
shareholder_yield = dividend_yield + net_buyback_yield + debt_paydown_yield

Dividend Capture

Buying before the ex-dividend date only to collect the dividend is not a free-money strategy. Prices usually adjust around the ex-dividend date, and taxes, spreads, and slippage can erase the gross dividend.

Use this only as an event-risk analysis, not as a default recommendation.

Data Sources

MarketUseful Fields
A-sharesTushare dividend, daily_basic.dv_ttm, fina_indicator, cashflow
US/HKyfinance Ticker.dividends, Ticker.info, financial statements, cash flow
ETFsdistribution yield, SEC yield, holdings yield, expense ratio, distribution history
REITsFFO, AFFO, occupancy, debt maturities, AFFO payout

When live data is unavailable, state the limitation and provide the analysis template instead of inventing dividend figures.

Output Template

markdown
### Dividend Analysis: [ticker/company]

**Verdict:** [sustainable / watchlist / yield-trap risk]

| Metric | Value | Interpretation |
|--------|-------|----------------|
| Dividend yield | ... | ... |
| Earnings payout | ... | ... |
| FCF payout | ... | ... |
| Dividend growth | ... | ... |
| Balance sheet | ... | ... |

**What supports the dividend**
- ...

**What could break the dividend**
- ...

**Scenario view**
- Base: ...
- Downside: ...
- Upside: ...

**Research note:** This is investment research, not live trading advice.

Common Mistakes

  • Treating high yield as cheap valuation without checking why the price fell.
  • Mixing special dividends with regular dividends.
  • Comparing REIT payout ratios to ordinary industrial companies.
  • Ignoring withholding tax, ADR ratios, currency conversion, or ETF expense drag.
  • Forgetting that ex-dividend capture is usually offset by price adjustment and transaction costs.
  • Recommending a dividend stock without discussing total return and dividend-cut risk.

Frequently asked questions

What does the Dividend Analysis AI skill do?

Dividend stock analysis for income, dividend-growth, and shareholder-return strategies, including yield quality, payout sustainability, ex-dividend mechanics, and yield-trap checks.

Why use Dividend Analysis on TypingMind?

Because you install it once and use it with any model. Dividend Analysis 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 Dividend Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/dividend-analysis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dividend Analysis?

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 Dividend Analysis?

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

Is the Dividend Analysis AI skill free?

Yes. It is published on GitHub by HKUDS 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 👇