Best Claude Skills for Legal Teams in 2026 (And the Checks They Don't Replace)

Five KissMySkills legal skills cover most day-to-day in-house work: Leon (In-House Counsel) for general questions and drafting, Marco (Contract Reviewer) for redlining, Rex for NDAs, Nina for GDPR and data processing, Victoria for legal admin. Each is $14.99 one-time and installs into Claude in about two minutes. None of them is a lawyer. Every case, statute and clause reference one produces has to be checked before it leaves your desk.

Last updated: August 2026 · Prices and vendor terms checked August 2026 · By the KissMySkills team

Read this before you use any of them

This page is not legal advice. Neither is anything a Claude skill writes. These are drafting and review aids, not counsel, and they carry no professional responsibility for what they produce.

The model will cite cases and statutes that do not exist, in the same confident tone it uses for real ones. Fabricated citations read perfectly: correct court, plausible year, a reporter volume that looks right. They are now a documented cause of court sanctions. Every authority has to be opened in a real research database before you rely on it.

Putting privileged client material into a third-party AI tool is a real decision. It needs a deliberate answer about which plan you are on, what happens to the data, and whether the client agreed. See the confidentiality section below before you paste a single agreement.

Nothing goes to a client, a counterparty or a court until a qualified lawyer has read it end to end.

Which Claude skill should a legal team buy first?

If you only take one, take Leon. He handles the widest spread of questions and drafts. Add Marco the moment contract volume becomes the bottleneck.

Skill Best for Price
Leon - In-House Counsel General legal questions, first drafts, risk framing $14.99
Marco - Contract Reviewer Redlining, spotting one-sided and missing clauses $14.99
Rex - NDA Specialist NDAs and confidentiality agreements $14.99
Nina - GDPR Compliance Privacy notices, DPAs, data-processing review $14.99
Victoria - Legal Assistant Summaries, intake, matter admin, chasing signatures $14.99

What do the top two actually do?

Best overall for legal teams
Leon - In-House Counsel AI Skill
Leon - In-House Counsel AI Skill
$14.99this skill vs $210,383/yraverage us gc salary

Leon answers legal questions in plain English, produces first drafts and redlines, and separates the points you can settle yourself from the ones that need outside counsel. He is at his most useful on the second question - the one where you already know the rule and want the argument on both sides written out.

View Leon - In-House Counsel →
Best for reviewing contracts
Marco - Contract Reviewer AI Skill
Marco - Contract Reviewer AI Skill
$14.99this skill vs $349/hraverage us lawyer rate

Paste a contract and Marco returns a clause-by-clause read: what is one-sided, what is missing, what the counterparty's draft quietly assumes. The output you actually use is the priority list - the three points worth spending negotiating capital on, separated from the twelve that are standard.

View Marco - Contract Reviewer →

Comparison figures: average US general counsel salary $210,383 per ERI SalaryExpert (June 2026); average US lawyer billable rate $349/hour per Clio's Legal Trends Report (January 2025 data). Both vary widely by state, company size and practice area - corporate litigation averages $460/hour, juvenile law $133.

Rex, Nina and Victoria are narrower by design. Rex knows the shape of a mutual versus one-way NDA and where the survival period usually hides. Nina works through Article 28 processor terms, lawful basis and transfer mechanics. Victoria handles the admin layer - matter summaries, intake forms, chasing signatures. See them all in the Legal & Finance skills collection.

Where do AI legal skills fail?

Fabricated authorities. This is the failure that ends careers, not just drafts. In December 2025 a US Magistrate Judge in the District of Oregon imposed a $110,000 penalty on two lawyers whose briefs contained references to cases that did not exist and quotations that were never written - reported by the ABA Journal. It is not an isolated event: researcher Damien Charlotin maintains a running database of court decisions in which fabricated AI citations were caught. Treat every case name, statute section and quoted passage as unverified until you have opened it yourself.

No jurisdiction sense unless you supply it. Ask a general question and you will often get a US-flavoured answer. If you are working under English, Polish or German law, say so in the first line of the prompt and name the statute you expect to be applied.

No knowledge of what changed last month. The model has a training cutoff. Recent amendments, new case law and regulator guidance published after that date are simply absent unless the skill is used in a Claude session with web access - and even then, retrieval is not a substitute for a proper research database.

No access to your matter history. It does not know what you agreed with this counterparty last year, which fallback positions your business will actually accept, or that your CFO has already refused an uncapped indemnity twice.

No privilege, no insurance, no accountability. A skill cannot sign off on advice, cannot be sued, and carries no professional indemnity cover. Whoever sends the output still owns it.

Confident when wrong. There is no tone difference between an answer the model is sure of and one it invented. Calibration is your job, not its.

Can you put client documents into Claude?

This deserves a decision, not a shrug.

The ABA's Formal Opinion 512, issued 29 July 2024, is direct about it: a client's informed consent is required before their confidential information goes into a self-learning generative AI tool, and informed consent means an actual explanation of the risk - not a boilerplate line buried in the engagement letter.

Then check which plan you are on, because the terms differ. Under Anthropic's consumer terms, conversations on the Free, Pro and Max plans can be used to improve Anthropic's models unless you switch that off in Privacy Settings; where it is left on, retention runs to five years, against 30 days if you opt out. Those terms do not apply to Claude for Work (Team and Enterprise), Claude for Government, Claude for Education, or API use including via Amazon Bedrock and Google Cloud Vertex AI. If privileged material is going in, that distinction is the whole ballgame - and you should confirm the current terms yourself rather than take a blog's word for it.

The practical middle path most in-house teams land on: redact names, figures and identifying details before pasting, or run the skill against a template rather than the executed document. You lose very little review quality and the confidentiality question stops being live.

How do you install a KissMySkills skill?

Each skill downloads as a ZIP file with a SKILL.md at its root.

  1. Open the Claude desktop app and go to Customize → Skills.
  2. Upload the ZIP.
  3. Toggle the skill on. It is now available in your conversations.

Skills work on every Claude plan - Free, Pro, Max, Team and Enterprise - but they depend on code execution being switched on. If the Skills menu is greyed out, go to Settings → Capabilities and enable Code execution and file creation. On Team and Enterprise, that toggle sits in organization settings and an owner has to turn it on before anyone can upload. Anthropic documents this in its Skills help article.

If you work in ChatGPT or Gemini instead, or you cannot get code execution enabled, use the fallback: open the SKILL.md file, copy its contents, and paste them into your chat tool's custom instructions. The behaviour is close enough that most people never notice the difference.

The full catalogue runs to 1,000+ skills, 158 prompt packs and 55 agents. Skills are $14.99, prompt packs $9, agents $32 - all one-time, all with a 30-day money-back guarantee.

In summary:

For broad legal support start with Leon (In-House Counsel); for contract volume add Marco (Contract Reviewer); for NDAs Rex; for privacy and GDPR Nina. All are $14.99 one-time with a 30-day money-back guarantee, install into Claude in minutes, and work in ChatGPT and Gemini via the paste-in fallback. They speed up drafting and review. They do not replace a qualified lawyer, and every authority they cite has to be verified before you rely on it.

Related: Best Claude skills marketplaces (compared) · Best Claude skills for CFOs & finance · Best Claude skills for executives

Frequently asked questions

Can Claude review a contract for me?+

Yes. With the Marco — Contract Reviewer skill you paste in a contract and Claude returns a clause-by-clause read: which terms are one-sided, what is missing, and a priority list of the few points worth negotiating hard. It is fast and genuinely useful on first-pass review, but it is not advice — a qualified lawyer signs off before anything goes back to the counterparty.

Will Claude invent case citations?+

Yes, and it will do it confidently. Fabricated citations come back with a plausible court, year and reporter volume, and there is no tone difference between a real authority and an invented one. Courts have sanctioned lawyers over exactly this — in one December 2025 Oregon federal case, two lawyers were hit with a $110,000 penalty. Open every case, statute and quotation in a real research database before relying on it.

Is it safe to put client documents into Claude?+

Treat it as a decision, not a default. ABA Formal Opinion 512 (July 2024) says a client's informed consent is needed before confidential information goes into a self-learning generative AI tool, and boilerplate in the engagement letter does not count. Anthropic's consumer terms (Free, Pro, Max) allow chats to be used for model improvement unless you opt out in Privacy Settings; Claude for Work, Government, Education and API use are governed separately. Many in-house teams simply redact names and figures first, or run the skill against a template rather than the executed document.

Do AI legal skills replace a lawyer?+

No. They have no privilege, no professional indemnity cover, no accountability, and no knowledge of your matter history or of anything that changed after the model's training cutoff. They accelerate drafting, review and research. The person who sends the output still owns it.

How do I install a KissMySkills legal skill?+

Each skill downloads as a ZIP file containing a SKILL.md at its root. In the Claude desktop app go to Customize → Skills, upload the ZIP, and toggle it on. Skills are available on all Claude plans — Free, Pro, Max, Team and Enterprise — but they require code execution to be enabled. If the Skills menu is greyed out, turn on 'Code execution and file creation' under Settings → Capabilities; on Team and Enterprise an organization owner has to enable it first.

Do these skills work with ChatGPT and Gemini?+

Yes, via the fallback method. Open the SKILL.md file, copy its contents, and paste them into the custom instructions of ChatGPT, Gemini or any AI chat that accepts them. This is also the route to use if you cannot get code execution enabled on your Claude account.

~/get-started

Skills that work. No fluff.

Browse every skill, prompt pack, and agent in the store.

Browse all skills →Or start with free skills