Hire an AI shareholder return calculation reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• EPS and share counts restated to one split basis
• The price change split into an earnings effect and a multiple effect, adding to the observed change
• Shares and ending wealth from reinvested dividends
• The cash-held case beside it, and the gap between the two
• Missing facts, and checks that could not run

How it does the job well

• Reconcile to source documents, such as bank statements, ledgers and invoices, before reporting.
• Show the calculation, inputs and period for every figure.
• Label actuals, estimates and forecasts clearly.
• Send tax, legal and regulatory questions to a qualified professional.

Mistakes it avoids

• Mixing cash and accrual figures, or different periods, in one comparison.
• Rounding or formula errors that do not tie back to totals.
• Giving personal investment advice.

What a good result looks like

An example, not your task: A stock has risen or fallen over a period and you want to know how much was earnings and how much was the multiple.

• SPLIT BASIS. EPS and weighted shares on one split basis, with unadjusted prices and dividends kept as recorded.
• PRICE BRIDGE. Earnings and multiple effects that add exactly to the observed price change, with the order used.
• REINVESTMENT. Shares added from dividends, ending wealth, and the cash-held case for comparison.
• SOURCES. Each input with its source, date, currency and scale.
• MISSING and CHECKS MISSED. Each gap and the line it stops, and every check that failed or could not run.

How the work is checked

• Price effects sum to observed price change; explicit dividends are not added to already-adjusted return series; reinvested wealth reconciles to shares and cash with fees/withholding disclosed.
• Trace each material input to its source, date, currency, scale, sign and reporting period. Retain unresolved MISSING: lines.
• Reconcile opening shares, shares added by reinvestment and closing shares, and opening cash, dividends and closing wealth.
• Keep hardcoded inputs separate from live formulas. Inspect changed inputs, actual recalculation, exported formulas and saved-file reopening.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Stock-split EPS restatement. Puts past EPS and weighted shares on the confirmed split basis. Keeps unadjusted prices and dividends so the return is not double counted. Hands step 2 EPS on one basis. Check before moving on: the split factor is confirmed, not guessed.
• EPS and multiple return bridge. Derives each date's price from EPS times P/E. Holds the opening multiple to find the earnings effect, then applies the ending EPS to the multiple change. States the order, so the part from both moving together is not lost. Divides each effect and dividends by the opening price and ties to the simple return.
• Dividend reinvestment share schedule. Takes each dividend, less fees or withholding, and divides by your reinvestment price to add shares. Compares ending wealth with holding the cash. Reconciles separately from the simple, non-reinvested return.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id explain-observed-shareholder-return only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/explain-observed-shareholder-return/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Unadjusted share prices at the start and end dates (from exchange records or your broker)
• EPS and P/E at both dates, on a comparable basis, with EPS above zero (from the company's filings)
• Confirmed split terms and dates (from company announcements)
• Dividend payment dates and amounts per share (from company records or your broker)
• Reinvestment dates and prices, plus any fees and tax withheld (from your broker statements)
• The shares held at the start, and the currency and scale

Helpful context (optional)

• Unadjusted price history from an exchange or your broker, not an adjusted chart series.
• The company's own EPS table and split notice.
• A named reviewer who knows the holding.

Tools and access

• A spreadsheet engine and file-capable AI: Builds a workbook with inputs, formulas and a checks tab you can click into. In plain chat it returns the same tables as text and says no workbook was made.
• Any good chat AI: The sums are short, so the AI can show the table in the chat.
• A file-capable AI or a spreadsheet app: Needed only if you want an editable workbook with a checks tab.
• Node.js 20 or later (optional): Runs the bundled script that repeats the sums, as a second check.
• A spreadsheet engine and file-capable AI: Create, recalculate, render and reopen the requested native workbook.
• Node.js 20 or later: Run the bundled dependency-free reference calculation against explicit numeric inputs.

Functions and deliverables

• Shareholder return calculation reviewer: Check historical share returns using matching split, price and dividend records. Show price changes and reinvested shares without counting dividends twice.
  • EPS and share counts restated to one split basis
  • The price change split into an earnings effect and a multiple effect, adding to the observed change
  • Shares and ending wealth from reinvested dividends
  • The cash-held case beside it, and the gap between the two
  • Missing facts, and checks that could not run
• Stock split earnings adjustment calculator: Share the confirmed split and past earnings figures. Get restated shares and earnings per share on one basis.
  • The split factor, in new shares per old share
  • Restated weighted shares and restated EPS for each year, beside the originals
  • A check that earnings are the same before and after
  • Notes on any year where the split falls before or after the period
  • A list of missing figures and terms to confirm
• Share price return analyst: Share earnings, price multiples and dividends. See how each contributed to the change in your investment's value.
  • A sequential price-return attribution that reconciles exactly to the observed change.
  • An editable workbook of the price return bridge, with its inputs, formulas and test cases to rerun.
  • A tie-out of the two effects and the observed price change, the inputs still missing and the checks that ran.
• Dividend reinvestment calculator: Share dividend and share purchase details. Compare shares and final value with a cash-held alternative.
  • The dividend cash, net cash and shares added.
  • Your ending value next to the keep-the-cash case.
  • An editable spreadsheet with live formulas.
  • A list of missing inputs and checks that did not run.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• A stock has risen or fallen over a period and you want to know how much was earnings and how much was the multiple.
• A split happened in the period and old EPS no longer lines up with today's.
• You reinvested dividends and want to know the shares and wealth they added.
• A reviewer wants the return pieces to add up to the observed price change.

Limits to check before starting

• You want to know what to buy, hold or sell. This explains a past return and gives no advice.
• EPS was zero or negative at either date. The bridge needs positive, comparable EPS.
• A discounted rights issue was involved. Use the Stock split and rights EPS checker workflow.
• You want what a buyback did to EPS and book value. Use the Share buyback accounting checker workflow.
• You want a valuation. Use the Equity valuation scenario reviewer workflow.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the workflow pack and give it to an AI that can read files, such as Claude, ChatGPT or Gemini. Use one that can make spreadsheets if you want a workbook.
• Attach your price records, the filings with EPS, the split announcement and your broker statements. Say the start and end dates.
• After step 1, check the split factor is the confirmed one and that prices and dividends were left unadjusted.
• After step 2, check the earnings effect and multiple effect add up exactly to the observed price change, and that the order is stated.
• After step 3, check shares and cash reconcile, and that fees and withholding are shown. Fill every MISSING line. This is not advice.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/explain-observed-shareholder-return for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.