Hire an AI property net asset value and book-value checker

Everything it can hand back

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

• A book value per share roll-forward, with closing equity and closing shares tied to the equity statement
• A property NAV bridge using the same date and shares
• The NAV-to-book difference, explained line by line with its source
• Every appraisal input traced to its source and date
• Every MISSING input and any check 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 report quotes a property NAV per share and you want to see how it links to book value.

• outputs/step-1-book-value-per-share-rollforward.md. Closing equity, closing shares and book value per share, tied to the equity statement.
• outputs/step-2-investment-property-nav-bridge.md. Appraised property values taken to NAV per share on the same date and shares.
• NAV-to-book gap. The difference per share, split into appraisal, tax and debt parts, each with its source.
• HAND-BACK SUMMARY. Files saved, sources used, MISSING lines and checks missed.

How the work is checked

• Common shares and liability perimeters match; NAV-to-book differences reconcile to disclosed valuation/tax adjustments; appraisal inputs are sourced and no valuation is invented.
• Trace each material input to its source, date, currency, scale, sign and reporting period. Retain unresolved MISSING: lines.
• If a workbook is built, keep hardcoded inputs separate from live formulas and reopen the saved file.
• Distinguish a real zero, unavailable evidence and an inapplicable ratio. Never force a financial statement tie with an unexplained plug.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Benjamin Graham would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Book value per share roll-forward. Proves closing reported common equity and closing shares from the equity statement. Keeps the book value of every asset and liability used. Hands step 2 the date, share count and book values. Check before moving on, equity and shares tie to the statement.
• Investment property NAV bridge. Uses the same date and shares. Replaces only the property values that have appraisals, and reconciles tax and debt conventions. Explains the whole NAV-to-book gap and never treats uplift as earnings. Check before you rely on it, every difference has a source.

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 reconcile-property-nav-and-book-value 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/reconcile-property-nav-and-book-value/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

• Property appraisals with their dates (from the valuer's reports)
• The balance sheet and the equity statement for the same date (from the annual or quarterly report)
• Which other assets and liabilities belong in NAV, and any tax adjustments (from the notes)
• The closing share ledger or share count (from the equity note)
• The reporting date, currency and scale, such as millions

Helpful context (optional)

• The valuer's reports, not a summary of them.
• The equity note with the closing share count.
• The note that lists which assets and liabilities the company counts in NAV.

Tools and access

• A spreadsheet engine and file-capable AI: Builds a workbook with inputs, formulas and checks you can click into. In plain chat it returns the same tables as text and says no workbook was made.
• 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.
• Claude, ChatGPT or Gemini: Any of them can do these sums in a chat.
• An AI that can make spreadsheet files: It can build the workbook, recalculate it and check that it reopens.
• Node.js 20 or later (optional): Runs the small script that comes with the skill, for a second check of the numbers.

Functions and deliverables

• Property net asset value and book-value checker: Share appraisals, accounts and share records. Get a same-date bridge between property net asset value and reported book value per share.
  • A book value per share roll-forward, with closing equity and closing shares tied to the equity statement
  • A property NAV bridge using the same date and shares
  • The NAV-to-book difference, explained line by line with its source
  • Every appraisal input traced to its source and date
  • Every MISSING input and any check that could not run
• Book value per share calculator: Share equity, profit, dividends and share counts. Get book value per share with a checked balance breakdown.
  • A common-equity movement table and book-value-per-share bridge.
  • If you ask for one, an editable workbook of the book value per share roll-forward, with its inputs, formulas and test cases to rerun.
  • A tie-out of computed closing equity and the balance sheet, the inputs still missing and the checks that ran.
• Property net asset value calculator: Share property values, other assets, debt and shares. Get net asset value and the market discount or premium.
  • A bridge from property value to equity NAV, line by line
  • NAV per share
  • The discount or premium of the share price to NAV
  • A check that debt, tax and other net assets are each counted once
  • A list of missing facts and checks it could not run
  • A small workbook with the same sums, if your AI can make files
• Business asset value estimator: Share a balance sheet, earnings, share count and price. Get rough asset sale values, cash checks and gaps to investigate.
  • Tangible book value, net current assets and cash assets per share
  • Typical and harsh sale values with the markdowns shown
  • A comparison with the price
  • How many years of current losses the cushion could absorb
  • A cash strength rating of strong, adequate or weak
• 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
• Benjamin Graham: Learn to separate price from value using Benjamin Graham’s recorded frameworks. Check the evidence, the downside and the room for error.
  • Your problem worked on the way Benjamin Graham would: their questions, their method, their push-back
  • The answer or the work, in Benjamin Graham's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• A report quotes a property NAV per share and you want to see how it links to book value.
• Appraisals came in higher than book and you need the uplift shown as a bridge, not as earnings.
• The share count or liabilities in an NAV table do not match the balance sheet.
• A reviewer asks which tax and debt adjustments sit between NAV and book value.

Limits to check before starting

• You only need book value per share. Use the Book value per share calculator on its own.
• You only need the NAV bridge from supplied valuations. Use the Property net asset value calculator on its own.
• You want to value several businesses inside one group. Use the Group company valuation checker workflow.
• You have no appraisals. This workflow does not make up valuations, so get them first.

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. For a workbook, use one that can build spreadsheets.
• Attach the appraisals, balance sheet, equity statement and share ledger. Say the reporting date, currency and scale once at the top.
• After step 1, check closing equity and closing shares against the equity statement.
• After step 2, check the bridge uses the same date and shares, and that each difference has a source.
• Fill every MISSING line before anyone quotes a figure. A person who knows the company checks the tax and debt conventions.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/reconcile-property-nav-and-book-value 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.