For solo and small elder law firms
The nursing home wants an answer by Monday. Five years of statements just arrived in a grocery bag.
A daughter on the phone asking what her mother can keep, a power of attorney nobody has read since 2011, an admission agreement signed in the lobby, and an application that will ask about every withdrawal. Much of it is flat fee, so every extra hour comes out of your margin, and one transfer nobody explained is all a caseworker needs to start asking questions.
The Small Firm AI Kit for Elder Law: one Claude Skill with 17 ready-made playbooks.
- Look-back transfer logs
- Medicaid document checklists
- POA and directive reviews
- One-time payment
- 30-day money-back guarantee
- Works on free Claude
Look-back transfer log, Client A (excerpt)
Scope: 60 statements read (Bank 1 checking ending 12, Bank 2 savings ending 34), from the review start date you entered, 11/01/2021. Threshold you set: $500. 41 items logged, 9 flagged for an explanation.
Flag 1: $12,000.00 transferred on 03/14/2023 to an account ending 77 (Doc 17, p. 2). No account ending 77 belongs to Client A anywhere in the file. [ATTORNEY: ask the family]
Checked before you see it
- Checked: Every item tied to its statement and page
- Flagged: 9 items flagged for an explanation; what they mean stays with you
- Verify: Review window and threshold taken from your entries, never from memory
Not an elder law attorney? There’s a kit for your area:
Compare all- Personal injuryMedical chronologies, specials and demand drafts, every row pinned to a source page.
- Family lawFinancial disclosure checks, chronologies and parenting plans, every figure sourced.
- ImmigrationRFE responses, evidence indexes and declarations that keep your client’s own words.
- Estate planningIntake summaries, plain-English plan letters and probate inventories, every value sourced.
- Business lawContract reviews, formation files and operating agreement summaries, every clause cited.
- Real estateTitle commitment reviews, contract deadlines and lease abstracts, every line sourced.
If this sounds like your week, keep reading
- Sixty statements spread across the conference table, a highlighter, and a $12,000 transfer from 2023 nobody in the family can explain.
- The son who called you is paying the fee and answering every question, and his mother hasn’t said a word yet.
- The facility’s business office wants a payment plan by Monday, and the admission packet has a “Responsible Party” page with his signature on it.
- The caseworker asks for one more bank letter, and the family email asking what happens now gets answered at 9 p.m.
Where the hours go
Roughly 12 hours a week go to the same five jobs
The same week with Claude and these playbooks: about 6 hours back
- Today
- With The Small Firm AI Kit for Elder Law
Reviewing five years of statements for the look-back
Today: 3 h/wkWith The Small Firm AI Kit for Elder Law: 1.5 h/wkIntake for Medicaid and long-term care planning
Today: 3 h/wkWith The Small Firm AI Kit for Elder Law: 1.5 h/wkClient and family updates, and time entries
Today: 3 h/wkWith The Small Firm AI Kit for Elder Law: 1.5 h/wkApplication checklists and letters to agencies and facilities (Pro)
Today: 2 h/wkWith The Small Firm AI Kit for Elder Law: 1 h/wkReviewing existing powers of attorney and directives
Today: 1 h/wkWith The Small Firm AI Kit for Elder Law: 0.5 h/wk
Today: ≈12 h a week, ≈576 h a year on this work.
Back in your week with Pro, our estimate
≈6 h
With Basic: ≈5 h
Example starting value: $275. Move it to your own number.
- Pro pays for itself after
- ≈22 min
- Time back, each month
- ≈$6,600
How we estimated these numbers
Only part of a small-firm lawyer’s week ever gets billed, and on a flat fee the extra hours never are. A big share of the rest goes to work that repeats on every file. This is a conservative picture for a practice that is mostly Medicaid and long-term care planning: a new planning or crisis client most weeks, about one Medicaid application a month with five years of statements behind it, a couple of powers of attorney and directives to read each week, and families who call often. If you file more applications, the statement hours grow.
- Reviewing five years of statements for the look-back, 3 h/week: Our estimate: about 12 hours to read five years of statements for one Medicaid application and list the transfers to explain, one application a month. No published figure found.
- Intake for Medicaid and long-term care planning, 3 h/week: Our estimate: about 3 hours per new client to gather assets, income, family and the care situation, chase what is missing and write the summary, one client a week. No published figure found.
- Client and family updates, and time entries, 3 h/week: Our estimate: about 36 minutes a working day on status emails to clients and families and on time-entry narratives. No published figure found.
- Application checklists and letters to agencies and facilities, 2 h/week: Our estimate: about 2 hours a week assembling document checklists and writing to caseworkers, facility business offices and the VA. No published figure found.
- Reviewing existing powers of attorney and directives, 1 h/week: Our estimate: about 30 minutes to read one power of attorney or health care directive and note agents, powers and gaps, two a week. No published figure found.
These are our estimates, not measured results. No published study times these elder law tasks, so we started from the conservative hours above and assumed every task still needs you: checking each transfer against its statement, applying your state’s current rules, deciding eligibility and strategy, judging capacity, clearing every [VERIFY] and signing off. So we cut each task by half at most. For comparison, in the 8am 2026 Legal Industry Report 38% of legal professionals who use AI say it saves them 1–5 hours a week, and nearly one in four say six or more.
Week: A standard 40-hour week (our basis). Clio’s 2025 Legal Trends for Solo & Small Firms puts utilization at 27% for solos and 32% for small firms: at those rates only about 11–13 of the 40 hours get billed.. Yearly figures use 48 working weeks, monthly ones 4.
One Skill · 17 playbooks inside
Describe the file. Get the actual draft.
One Skill in Claude: you say what you need in plain words, its router opens the right playbook, and back comes a draft with every entry sourced. These are excerpts of what comes back, built on fictional, anonymized facts. You won’t see an eligibility answer or a penalty period here, because the kit doesn’t produce them.
Five years of statements, the intake and the agency’s list, turned into documents you can check.
You ask
“Client A goes into Facility 1 next week. Here are 60 statements from Bank 1 and Bank 2. Log every item over $500 from my review start date and flag what needs explaining.”
You get
Every transfer over your threshold, with its statement and page, the unexplained ones flagged.
Playbook: lookback-transfer-log.md · in every plan
elder-law-attorneys/
├─ SKILL.md
the router: reads your request, opens the right playbook
├─ your profile, saved at setup
└─ playbooks/
├─ citation-guard.md
├─ confidentiality-preflight.md
├─ engagement-letter-ai-clause.md
└─ … 14 more
See all 17 playbooks
In every planBasic · $49
- Every citation flagged before anyone else sees it
citation-guard.md - Client data anonymized before any work starts
confidentiality-preflight.md - Updates clients and families actually read
client-update-writer.md - Time entries clients don’t push back on
billing-narrative-cleaner.md - A look-back transfer log with every item sourced
lookback-transfer-log.md - One planning summary from a rushed family call
medicaid-planning-intake.md - Old powers of attorney and directives read in minutes
poa-directive-review.md
Added in ProPro · $99
- An engagement letter that says who the client is, with an AI clause
engagement-letter-ai-clause.md - A Medicaid document checklist built from your state’s list
medicaid-application-checklist.md - Admission agreement clauses flagged before the family signs more
care-facility-agreement-review.md - A guardianship petition scaffold, every fact sourced
guardianship-petition-scaffold.md - An Aid and Attendance document checklist
va-pension-checklist.md - A family meeting summary that keeps the client’s voice first
family-meeting-summary.md - A private-pay cost projection computed from your figures
care-cost-projection.md - A special needs trust the family can follow
special-needs-trust-summary.md - Your spend-down options organized into a memo outline
spend-down-options-outline.md - Letters to caseworkers, facilities and the VA, drafted from the file
agency-facility-letters.md
Why not just ChatGPT?
Why not just paste the statements into ChatGPT?
Around 70% of solo and small-firm legal professionals already use AI (8am 2026 Legal Industry Report; Clio 2026), but only 9% of those 8am surveyed say their firm has an AI policy and actually enforces it. A plain chatbot is fast, but it doesn’t know your state’s Medicaid rules as they stand this month, your agency’s document list or where its figures came from. Fiduciary and family disputes, the kind elder law files can turn into, already have AI failures on the record.
Generic AI
- Ibach v. Stewart (Alabama Supreme Court, April 2026): in a family dispute over a trustee’s fiduciary duties, the appellants’ briefs cited cases and quotations that don’t exist. The court dismissed the appeal, ordered the lawyer to pay the other side $17,200 in fees and costs (counting a check he had already sent) plus double the appeal costs, barred him from filing in that court unless another lawyer co-signs, and referred him to the State Bar.
- Matter of Weber (Saratoga County Surrogate’s Court, New York, October 2024): in a dispute over a trustee’s handling of a trust property, an expert used Microsoft Copilot to cross-check his damages figures but couldn’t say what prompts he used. The court ran its own Copilot query on three computers, got three different answers, found his calculations unreliable and held that counsel has an affirmative duty to disclose the use of AI.
- Estate of Acciavatti (Arizona Court of Appeals, July 2026): a self-represented son challenging his sister’s appointment as personal representative filed a brief in which six of eight citations were deficient and two cases didn’t exist. He was ordered to pay the fees they caused, in what was reported as Arizona’s first published opinion on AI in court filings. Not a lawyer’s mistake, but the same failure.
- A chatbot will state a look-back period, an asset limit or an income cap with confidence, and it won’t tell you the figure is out of date. California shows how fast that happens: Medi-Cal brought its asset limit back on January 1, 2026, after two years without one, and is phasing its look-back back in. In this kit those figures come only from what you enter, marked [VERIFY].
The Small Firm AI Kit for Elder Law
Why this works where a plain chatbot didn’t
- 1
Anonymized before anything starts
Confidentiality Pre-Flight runs first on every task: it offers anonymized mode, swaps names for Client A and Facility 1, masks Social Security, Medicare and account numbers, and reminds you to use a business plan that doesn’t train on your data.
- 2
Every transfer sourced, every total computed with code
Look-Back Transfer Log ties each withdrawal, check and transfer to its statement and page and totals them with code, inputs shown. Anything without a source is marked [NO SOURCE], and every unexplained item is flagged for you.
- 3
No eligibility call, no rule from memory, your signature last
Look-back windows, asset figures and income caps come only from what you enter in your Firm Profile, each marked [VERIFY]. No playbook decides eligibility, computes a penalty period or judges capacity. Every output ends with a verification block and a line for your sign-off.
How it works
Set up once. Then just ask.
No coding, no prompts to copy. You install it the way you would add a document to Claude.
- 1
Download the ZIP
Right after checkout you get one ZIP, ready to download on the page: a single Claude Skill for your practice with every playbook in your plan inside. No account, no login, no subscription.
- 2
Upload it to Claude
Add it once in Claude’s settings. After that you just ask for the work: the Skill reads your request and opens the right playbook, so you never pick a file yourself. It runs on every Claude plan, including Free with code execution turned on. For real client files, use a business plan that doesn’t train on your data.
- 3
Answer the 5-minute Firm Profile interview
State, your Medicaid program’s name and agency, the court that hears guardianships, house style, signature, and the windows and figures your state applies, entered from your agency’s current rules and never guessed. Update them when the agency publishes new ones. Saved once and read by every playbook, so no file starts with last year’s numbers.
Compare your options
What the other options cost
These are the real alternatives a solo or small elder law firm has today, at the prices reported for them. None of them is wrong, and the kit doesn’t replace your drafting software. They are priced for a different job, or a different firm.
- Elder law drafting software (e.g. WealthCounsel’s Elder Docx)Price on request: WealthCounsel says membership is priced by number of users and productsBuilt to draft Medicaid and special needs trusts, caregiver agreements and client letters, and good at it, so keep it. Reading five years of statements and an admission agreement are still your hours.
- Legal AI subscription (CoCounsel Legal)Roughly $490–850 per attorney a month, depending on firm size and term (no published price; third-party reports, 2026)Built for legal research and billed every month per user. It doesn’t build a transfer log from five years of statements.
- Your own hours, or a paralegal’sYour hourly rate, every statement page and every checklistDone again on every application, and on a flat fee those hours aren’t billed.
- A generic chatbotAbout $20 a monthNo document references, no verification, and it will state a look-back period or an asset limit that sounds right. Medical and account details pasted into a consumer account can breach confidentiality.
- Claude’s official legal pluginsFree to install, paid Claude plans onlyNo elder law plugin, and nothing that drafts an engagement letter AI clause.
- The Small Firm AI Kit for Elder Law$49 or $99, once$49 or $99, paid once. Even Pro costs less than one month of a CoCounsel Legal seat as third parties report it, and it never renews.
Pick your plan
One payment. Yours to keep.
Less than one month of a legal AI research subscription, with no renewal after it. One payment, yours to keep.
Pro costs, once
$99
Basic: $49 once
It pays for itself after
≈22 min
of time won back, at $275 for an attorney hour
Get back just 1 hour a month
$275
a month, against a one-time $99. Our estimate is ≈6 h a week.
Break-even = plan price ÷ the hourly value set in “Where the hours go” above.
Basic
The core kit plus the three elder law essentials.
$49one-time
7 ready-made playbooks
Try it on real work. Not for you? Full refund within 30 days.
- 4 core playbooks: Citation Guard, Confidentiality Pre-Flight, Client Update Writer, Billing Narrative Cleaner
- Look-Back Transfer Log, every item tied to its statement and page
- Medicaid Planning Intake with a list of missing documents
- POA & Directive Review: agents, powers and gaps
- Firm Profile interview: set your state, program and house style once
- Verification block at the end of every output
Pro
The full elder law workflow, from the first family call to the agency letter.
$99one-time
All 17 playbooks
Only $50 more than Basic: +10 playbooks and the Pro bonuses below.
Try it on real work. Not for you? Full refund within 30 days.
- Everything in Basic
- Medicaid Application Checklist from your state’s list
- Care Facility Agreement Review
- Guardianship Petition Scaffold, no capacity conclusions
- Aid and Attendance Document Checklist
- Family Meeting Summary
- Care Cost Projection computed from your figures
- Special Needs Trust Summary in plain English
- Spend-Down Options Outline, never a recommendation
- Agency & Facility Letters
- Engagement Letter + AI Clause, with who the client is when family pays
- Word templates for your transfer log, planning summary and agency letter
- Firm Style Guide: your house style, applied by every playbook
- Sample outputs from every playbook, to compare against your own
- 12 months of fixes and adjustments to the included playbooks
30-day money-back guarantee
Run the kit on a real, anonymized file. If it doesn’t earn its place in your practice within 30 days, email us and we refund every cent. No conditions.
- One-time payment, no subscription
- Works on free Claude
Practice in a different area? Personal injuryFamily lawImmigrationEstate planningBusiness lawReal estateTell us yours →
No Claude account yet?
No Claude yet? You’re 2 minutes away
Claude is Anthropic’s AI assistant. Its free plan runs The Small Firm AI Kit for Elder Law: you create the account, switch on one setting and upload the kit, in about two minutes and without a credit card.
- The free plan works: no subscription and no credit card to start
- About two minutes from sign-up to your first request
- Paid plans only add more usage, for when you want it
Client confidentiality comes first. Every task starts with Confidentiality Pre-Flight, which offers anonymized mode and swaps names for placeholders like Client A and Facility 1. Try the kit free on anonymized facts, then run real files on a Claude business plan, which doesn’t train on your data.
- 1
Create a free account
Go to claude.ai and sign up with your email, Google or Apple account. It’s free and ready right away.
- 2
Turn on one setting
In Settings → Capabilities, switch on “Code execution and file creation”. Skills need it, and it’s free.
- 3
Upload your package
In Customize → Skills, click “+”, choose “Upload a skill” and select the ZIP you received. Then just ask.
Fair questions
What elder law attorneys ask before buying
Is it ethical to use AI on client matters?
ABA Formal Opinion 512 doesn’t forbid it. It asks you to understand the tool, verify its output, protect confidentiality (informed consent may be needed), communicate with the client, supervise staff and charge reasonable fees. Elder law adds two duties the kit keeps in view: Model Rule 1.14 on clients with decision-making limitations, which it flags but never judges, and Model Rule 1.8(f) when a family member pays the fee. The kit gives you an AI clause for your engagement letter, anonymize-first by default and a human-verification block on every document. It is aligned with the guidance; it doesn’t certify compliance.
Is my clients’ health and financial data safe?
Every task starts with Confidentiality Pre-Flight, which offers anonymized mode, swaps names for placeholders like Client A and Facility 1 and masks Social Security, Medicare and account numbers. Use Claude’s Free plan only to try the kit with anonymized or fictional data; for real client files, use a business plan that doesn’t train on your data.
Will it tell me whether my client qualifies for Medicaid?
No, and that is deliberate. Medicaid rules vary by state and change, and the answer depends on facts and judgment that are yours. The kit organizes the statements, the intake and the agency’s document list, and flags what needs you. It never determines eligibility, never computes a penalty period and never states a look-back period, asset limit or income cap from memory: those come only from what you enter, marked [VERIFY].
I already have drafting software. Why would I need this?
Keep it. The kit doesn’t draft the Medicaid trust or the special needs trust. It works on everything around them: the intake, five years of statements, the old powers of attorney, the admission packet, the agency checklist and the letters to families, facilities and the VA.
Doesn’t Anthropic already do this?
Claude’s official legal plugins, announced in May 2026, focus on commercial, corporate, employment, privacy, IP and litigation work. None is built for elder law, and none drafts an engagement letter AI clause. These playbooks fill that gap and run on Claude’s Free plan, while the plugins need a paid plan. We are independent and not affiliated with Anthropic.
Built for your rules
Built for your state’s Medicaid program and courts
Pick your state in the Firm Profile and the playbooks switch program names, document lists and court vocabulary. Every window, limit and cap comes from what you enter and stays marked [VERIFY], because these rules vary by state and change.
Your setup
Every state
The federal frame every state works within, with your state’s own rules entered on top.
- Federal law sets a 60-month look-back for transfers made on or after February 8, 2006 (42 U.S.C. § 1396p(c)); your state applies it through its own rules, so the review start date is yours to enter [VERIFY]
- Resource figures, income caps and spousal allowances entered from your agency’s current published figures, never from memory
- Nursing facility admission agreements checked against the federal rules for certified facilities; assisted living contracts against the state rules you enter
Guardrails
Verification isn’t a disclaimer. It’s the product.
Every output ends with the same verification block: key statements, the source of each, the items marked [VERIFY], the human checks this document requires and a line for your signature. We never promise zero errors. We promise every citation, every rule and every figure you rely on is flagged for you to check.
Sample verification block
From: Look-back transfer log, Client A (excerpt)
- Checked: Every item tied to its statement and page
- Flagged: 9 items flagged for an explanation; what they mean stays with you
- Verify: Review window and threshold taken from your entries, never from memory
- Checked: No penalty period computed, no eligibility call made
- 01
No eligibility call, ever
No playbook says whether a client qualifies for Medicaid or VA benefits, computes a penalty period or designs a spend-down. They organize the documents and flag what needs you. Medicaid rules vary by state and change; that judgment is yours.
- 02
No rule from memory
Look-back windows, resource figures, income caps and spousal allowances come only from what you enter in your Firm Profile, each marked [VERIFY]. With nothing entered, the field stays blank.
- 03
A source on every transfer
Every withdrawal, check and balance carries its statement and page. Anything without one is marked [NO SOURCE], and every sentence of a trust or document summary points to the article it explains.
- 04
Numbers computed with code
Transfer totals, cost projections and invoice totals run as code with the inputs shown. Nothing is assumed: no rate increase, no benefit amount, no figure you didn’t supply.
- 05
Capacity: flagged, never judged
If notes show confusion, a relative answering for the client or a sudden change of agent, the playbooks flag it. Under your state’s version of Model Rule 1.14, which the ABA revised in February 2026 as “Client with Decision-Making Limitations”, judging capacity and any protective action stay with the lawyer.
- 06
Who the client is, written down
When an adult child pays and attends, the engagement letter says who you represent. Model Rule 1.8(f) allows payment from someone else only with the client’s informed consent, no interference with your independent judgment or the client-lawyer relationship, and the client’s information protected under Rule 1.6.
- 07
Anonymize first
Before any task, anonymized mode is offered: names become Client A and Facility 1, Social Security, Medicare and account numbers are masked. Consumer plans are for trying the kit, not for client files.
- 08
No unreviewed advice to clients, families or agencies
Client updates, family summaries and letters carry an “Attorney review required before sending” banner. Nothing goes out as legal advice without you.
FAQ
Everything else
Didn’t find your answer? Email us:hello@summonskills.com
What exactly is in the ZIP?
One Claude Skill for your practice. Inside: a router file (SKILL.md) that reads each request and opens the right playbook, one Markdown playbook per job (7 in Basic, 17 in Pro), each with its instructions, templates and verification block, and the Firm Profile interview every playbook reads. Pro also includes the Firm Style Guide inside the Skill, plus a bonus pack: Word templates for the transfer log, the planning summary and the agency letter and sample outputs from every playbook. 12 months of fixes and adjustments to the included playbooks are included (new playbooks for future rule changes are not part of that).
Does it work on Claude’s Free plan?
Yes. The Skill runs on every Claude plan, including Free, as long as code execution is turned on. Free is fine for trying the kit with anonymized or fictional facts. For real client files, use a business plan that doesn’t train on your data.
I use ChatGPT. Will this work there?
No. The kit is built as a Claude Skill, and ChatGPT has no equivalent way to install it once and have it open the right playbook for each request. Claude’s free plan is enough to try it, an account takes a minute, and you can keep ChatGPT for everything else.
Which states does it cover?
Any US state. Your Firm Profile records your state, your Medicaid program’s name, your agency’s document list, your guardianship court and the windows and figures your state applies, and every playbook uses them. It comes with notes for California, New York and states with their own program names, such as MassHealth, ALTCS and TennCare. Rules always come from what you enter, marked [VERIFY].
Will it compute the penalty period or the look-back?
No. The transfer log lists every item from the review start date you enter, with its statement and page, and totals them with code. Whether an item is a transfer for less than fair value, whether an exception applies and what penalty follows are your calls under your state’s current rules.
I also do estate planning. Which kit do I need?
The estate planning kit covers plans, probate and trust administration: intake for a plan, plain-English plan summaries, inventories and accountings. This kit covers long-term care: Medicaid files, the look-back statements, powers of attorney and directives, admission agreements, guardianship and benefits. If your practice does both, they are separate Skills and both can be installed in Claude.
Does it connect to my practice management or drafting software?
No connector needed. Export the statements, questionnaire or documents as PDFs or Word files from whatever system you use and upload them to Claude.
What if it isn’t right for my practice?
Email us within 30 days and we refund the full price. No conditions.
Is this legal advice?
No. The kit is for licensed lawyers and their staff. It drafts and organizes; you review, decide and sign. You remain responsible for every application, filing and letter that leaves your office.
Your next Medicaid file, every transfer logged and sourced before the caseworker asks.
Statements, intake notes and old documents in; every item tied to its page, totals computed with code, rules only from what you enter, no eligibility call, and your sign-off last. About 6 hours a week back, by our estimate. $49 or $99, paid once. Use it on a real, anonymized file, and if it doesn’t earn its place within 30 days, we refund every cent. Not legal advice; for licensed lawyers.
One payment, yours to keep · 30-day money-back guarantee