Hire an AI small business acquisition reviewer
Plan what to ask the seller and check the books. Get owner cash earnings and a value range before making an offer.
What you give
- The listing and what the seller claims
- The financial statements, two or three years if you can
- What you know of the industry and the location
What you get
- A diligence checklist for this kind of business, with red flags
- Meeting questions with the answers to listen for
- A read of the statements: trends, margins, oddities and gaps
- Owner earnings and a value range to offer from, with the method shown
An example
A broker sent you a listing and you are tempted.
You ask: “Plan what to ask the seller and check the books. Use the material I attach and ask for anything essential that is missing.”
You get back:
- Step 1: Due diligence checklist. What to ask for, how to verify it, the red flags and the order to work in.
- Step 2: Seller meeting prep. Questions for the seller, the answers to listen for and what to ask to see.
- Step 3: Statement read. Trends, margins, oddities and gaps in the statements, each tied to a line.
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.
Related specialists
- Business valuation and price reviewer
- Long-term business quality reviewer
- Employee share award and dilution reviewer
- Project investment decision reviewer
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 diligence checklist for this kind of business, with red flags
- Meeting questions with the answers to listen for
- A read of the statements: trends, margins, oddities and gaps
- Owner earnings and a value range to offer from, with the method shown
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 broker sent you a listing and you are tempted.
- Step 1: Due diligence checklist. What to ask for, how to verify it, the red flags and the order to work in.
- Step 2: Seller meeting prep. Questions for the seller, the answers to listen for and what to ask to see.
- Step 3: Statement read. Trends, margins, oddities and gaps in the statements, each tied to a line.
- Step 4: Owner earnings. Reported earnings plus non-cash charges, minus must-spend costs and a fair wage for the owner's work.
- Step 5: Value range. A low to high range with the method shown, the walk-away price and what is still to verify.
- 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 files and answers listed for it in Steps.
- 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 Warren Buffett and Benjamin Graham would. This is a way of reviewing the work. It does not mean they wrote or endorse it.
Capabilities
- Build the checklist. Builds the diligence checklist for this kind of business, with red flags and the order to work in.
- Prepare the seller meetings. Prepares the seller meetings with the questions, the answers to listen for and what to ask to see.
- Meet the seller. A pause. Meet the seller and collect the documents on the checklist. Paste the answers and any new files.
- Read the statements. Reads your books and the seller's answers for trends, margins, oddities and gaps, each tied to a line. Hands the owner earnings step the statement read.
- Work out owner earnings. Works out owner earnings in Buffett's definition, with the owner's unpaid work priced at a fair wage.
- Set the value range. Gives a value range with the method shown and the price past which the deal makes no sense. If the cash cannot be estimated with confidence, it says the business is too hard to value and gives no range.
How the role works
- Checks your task, context and available tools.
- Picks the methods needed and prepares a work plan.
- Carries out supported tasks, with each method's limits and review gates.
- Checks the real deliverables and corrects supported faults.
- 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 check-a-small-business-before-you-buy-it 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/check-a-small-business-before-you-buy-it/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
- The listing and what the seller claims
- The financial statements, two or three years if you can
- What you know of the industry and the location
- What the owner does each week and what they draw (optional)
- After the meetings, the seller's answers (optional)
Helpful context (optional)
- Tax returns, which are harder to flatter than management accounts
- The customer list with revenue by customer
- The lease and any equipment loans
Tools and access
- Any good chat AI: Every step is a plan or a piece of writing.
- A spreadsheet: Holds the statements and the owner earnings working.
- An accountant and a lawyer: The workflow prepares the questions; they verify the answers.
- A spreadsheet: Lets you keep the year-by-year table and rerun the sum when a new year arrives.
- Any good chat AI: Reading pasted statements and doing a short fixed sum is work any strong chat AI does well with this skill.
- A spreadsheet: Lets you check the year-by-year sums and change the rate or the growth with a click.
- Any good chat AI: Doing a fixed multi-step sum from stated inputs is work a strong chat AI does well with this skill.
Functions and deliverables
- Small business acquisition reviewer: Plan what to ask the seller and check the books. Get owner cash earnings and a value range before making an offer.
- A diligence checklist for this kind of business, with red flags
- Meeting questions with the answers to listen for
- A read of the statements: trends, margins, oddities and gaps
- Owner earnings and a value range to offer from, with the method shown
- India deal due diligence planner: Plan due diligence for an Indian deal. Get workstream requests, owners, status tracking and a separate list of red flags.
- Checklists by workstream
- Status tracking columns
- Red flag notes
- Priority items for your main concerns
- Business diligence meeting question planner: Share the company, meeting type and open concerns. Get neutral priority questions, evidence to request and specific gaps to probe.
- Questions grouped by topic and priority
- Warm-up questions to open the meeting
- Benchmarks to compare answers against
- Red flags to listen for
- Follow-up probes
- Financial statement and budget reviewer: Share statements, budgets or forecast inputs. Get key ratios, budget variances, cash forecasts and valuation ranges.
- Ratio analysis with trends
- A DCF with a sensitivity table
- A budget variance report
- A rolling forecast with scenarios
- Owner earnings calculator: Share profit, spending and working-capital figures. Get labelled cash estimates, with a range only when the inputs and order support it.
- A year-by-year table with one-off items removed
- Three labelled upkeep and owner-earnings candidates
- An order check and either an eligible range or NO VALID ORDERED RANGE
- Ratios and growth only where the inputs support them
- Missing figures and method limits
- Business value range calculator: Share owner earnings and their basis. Get a no-growth estimate, three growth cases and a higher-rate check, with assumptions shown.
- A call on whether the cash can be estimated
- The rate used and why
- A no-growth floor value
- Low, middle and high values with the growth each assumes
- A rate sensitivity row and where a given price falls
- 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
- 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
- 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 broker sent you a listing and you are tempted.
- You are buying from a retiring owner who keeps the books in their head.
- You have bought before and found the surprises after closing.
Limits to check before starting
- You are buying only the assets, like equipment or stock: ask your accountant or a valuation specialist instead.
- You want to know what a business is worth without a deal in front of you: use "Business valuation and price reviewer".
- You need a legal review of the contract or lease: hire a lawyer, since this workflow only prepares the questions.
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 and every skill file this workflow uses.
- Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
- Paste the listing and the statements. It builds the checklist and the meeting questions.
- Meet the seller. Paste what they said and any new documents.
- Read the statement analysis, the owner earnings and the value range before you make any offer.
Read it as data
Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/check-a-small-business-before-you-buy-it 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.