This is taking longer than expected.

Try againBrowse the library
AI Blocks

All AI specialists

Hire an AI company quality and share-price screener

Check company records and share prices under the seven-test method. Get a research shortlist and draft holding rules with gaps visible.

What you give

  • Ten years of figures for each company, with profit and dividends per share
  • The latest balance sheet and the share price
  • Book value per share

What you get

  • A pass, fail or unknown on each quality test, with the figure
  • Restated earnings, if one-off items or share counts were hiding in them
  • A pass or fail on three price ceilings, with every sum shown
  • A spread list, caps for any one name and industry, and a holding plan

An example

You want a list of sound companies to hold for years with little fuss.

You ask: “Check company records and share prices under the seven-test method. Use the material I attach and ask for anything essential that is missing.”

You get back:

  • Step 1 quality screen. A pass, fail or unknown on size, strength, profit record, dividends and growth for each company, with the figure.
  • Step 2 earnings check. Reported and restated earnings per share, with a call of clean, adjusted or avoid.
  • Step 3 price test. Price to three-year earnings, price to book, their product and earnings yield, with every sum shown.

An example, not your task.

Hire this specialist

It is free and needs no account. Download the pack, give it to your AI and tell it the job. Your AI asks for anything it is missing, then does the work and checks it.

Download the specialist

Related specialists

Skills and workflows for this job: Research investments and business value

Details

Everything it can hand back

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

  • A pass, fail or unknown on each quality test, with the figure
  • Restated earnings, if one-off items or share counts were hiding in them
  • A pass or fail on three price ceilings, with every sum shown
  • A spread list, caps for any one name and industry, and a holding plan

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: You want a list of sound companies to hold for years with little fuss.

  • Step 1 quality screen. A pass, fail or unknown on size, strength, profit record, dividends and growth for each company, with the figure.
  • Step 2 earnings check. Reported and restated earnings per share, with a call of clean, adjusted or avoid.
  • Step 3 price test. Price to three-year earnings, price to book, their product and earnings yield, with every sum shown.
  • Step 4 spread list. The names that passed everything, how many to hold, caps per name and industry, and a review date.
  • Step 5 holding rules. Facts that must stay true, reasons that do not count, and the only reasons to act.
  • HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

  • Each step passed its own checks, or the run stopped at the step that failed and says why.
  • The steps ran in order, and each one used the result of the one before.
  • Nothing was invented to fill a gap. Every gap is a MISSING: line.
  • Nothing was sent, published or paid for without a clear yes.
  • 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 and Warren Buffett would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

  • Tests the company. Checks size, strength, a profit in each of ten years, a long dividend record and growth measured with three-year averages.
  • Checks the earnings. Looks for special charges, share count changes and other items that make one year's profit unreliable.
  • Tests the price. Sets the price against three-year average earnings and book value, and against the two together, and compares the earnings yield with safe bonds.
  • Builds the list. Keeps only full passes, spreads them over ten to thirty names, caps names and industries, and offers a broad fund if too few pass.
  • Writes the holding rules. Lists the facts that must stay true, the reasons that do not count and the only reasons to act.

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 defensive-stock-screen 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/defensive-stock-screen/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

  • Ten years of figures for each company, with profit and dividends per share
  • The latest balance sheet and the share price
  • Book value per share
  • What safe bonds pay now, if you know it

Tools and access

  • A free company data site or annual reports: The tests need ten years of figures, and the filings are the source.
  • A spreadsheet: A table with a row per company and a column per test makes the group easy to see.
  • Any good chat AI: Reading statements and linking years is text work. It cannot fetch filings.
  • A spreadsheet: Handy for the restated earnings and share counts.
  • A licensed financial adviser: Needed for a large or personal decision. This skill is a method, not advice.
  • A spreadsheet: The sums are small, and a sheet with a row per company shows who passes.
  • Annual reports or a free data site: Earnings per share and book value per share come from there.
  • Any good chat AI: Sorting a short list and applying caps is text work any strong chat AI does well with this skill.
  • A spreadsheet: A sheet with name, industry and size makes the caps easy to see.
  • Any good chat AI: Turning picks into a fixed template and doing simple cost sums is text work any strong chat AI does well.
  • A calendar: Put the review dates in as repeating events so you look on those days and no others.

Functions and deliverables

  • Company quality and share-price screener: Check company records and share prices under the seven-test method. Get a research shortlist and draft holding rules with gaps visible.
    • A pass, fail or unknown on each quality test, with the figure
    • Restated earnings, if one-off items or share counts were hiding in them
    • A pass or fail on three price ceilings, with every sum shown
    • A spread list, caps for any one name and industry, and a holding plan
  • Defensive stock quality screener: Share company figures and a size floor. Check five quality rules, with the sums and any missing evidence clearly marked.
    • A pass, fail or unknown on each of the five tests
    • The figure behind each result, with the sum shown
    • A list of companies that passed all five
    • A list of what is still unknown and where to find it
  • Reported earnings adjustment reviewer: Review accounting choices that may change reported profit. Get sized findings, an adjusted earnings view and questions to resolve before relying on it.
    • Each finding with year, amount, direction and share of reported profit
    • Reported and restated earnings by year
    • A read of the pattern
    • A clean, adjusted or avoid call
    • Questions to put to the company
  • Stock purchase price checker: Test a stock's price against three ceilings. Paste share price, earnings and book value, and get pass or fail with every sum shown.
    • A pass or fail on each of the three ceilings
    • The sums behind each result
    • The earnings yield against the bond yield
    • A note on how far the price is from passing
  • Defensive stock list builder: Build a defensive stock list from companies that passed your tests. Get 10 to 30 names, size limits and a yearly review date.
    • A list of the companies to hold, with a size for each
    • Industry limits and a cap for any one name
    • A plan for when too few pass
    • A yearly review date and the only reasons to change the list
  • Investment holding rule writer: Write sit-still rules for your investments: the facts that must stay true, fixed review dates, what acting costs you, and the only reasons to act.
    • Two to four checkable facts for each pick
    • Fixed review dates and a holds, weaker or broken marking
    • A cost-of-acting line with numbers
    • Three reasons to act, the reasons that do not count, and a cooling line
  • 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
  • Warren Buffett: Review a business using Warren Buffett’s recorded principles. Check how it earns, what protects it, how managers use cash and which facts remain uncertain.
    • Your problem worked on the way Warren Buffett would: their questions, their method, their push-back
    • The answer or the work, in Warren Buffett'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

  • You want a list of sound companies to hold for years with little fuss.
  • Someone gave you a stock tip and you want to test it against plain rules.
  • You have a long list and need a repeatable way to cut it.

Limits to check before starting

  • You want to trade in and out within days or weeks: this is a hold-for-years method, so use a trading plan or talk to a licensed adviser.
  • You cannot find ten years of figures: buy a broad index fund instead, since the tests need that record and unknown years stop a pass.
  • You are screening banks or insurers: the tests do not fit them, so set them aside or ask a licensed adviser. Utilities need the debt tweak.

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 handoff pack. It's a zip with HANDOFF.md plus one skill file for each step.
  • Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
  • Paste the figures. Mark any year you cannot find, since a gap is marked unknown, not guessed.
  • Read the cuts first. Most companies fail at least one test.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/defensive-stock-screen 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.