The AI Negotiator skill for Claude

You download the zip at the top of this page, put it in your Claude environment, and from that moment Claude prepares conversations following this logic. What a SKILL.md actually is, and why a text file steers an AI's behaviour, is explained in what Claude skills are NL.

Positional bargaining concentrates on stated offers: one party moves a number up and the other moves it down. That can leave underlying interests unexplored. Persistence alone does not determine the outcome. The method in this skill adds alternatives, interests, possible packages and relevant criteria to the preparation.

It is written for people who negotiate without it being their profession: freelancers and agencies who have to defend their rate, business owners renewing a supplier contract, employees having a salary conversation, anyone with an expiring contract on their desk. It is part of the skill library we make available for free through the AI and automation service, with no account and no sales email afterwards.

One thing you should know upfront: the skill does not negotiate for you. It prepares you for a conversation you have yourself. It delivers a strategy, not a pep talk, it does not invent a counteroffer you have never heard, and it does not promise that a particular outcome will be reached. What it does do is make explicit the two things most people leave implicit: what you do if there is no deal, and where the line sits above which a deal is better than no deal.

The position gets mistaken for the interest. The position is what someone asks for. The interest is why they ask for it. A 15 per cent request might reflect a fixed budget, a need to justify a purchase or a two-month cash-flow delay. Ask rather than infer the motive. Alternative packages require cost estimates; none is automatically free.

The BATNA is never spelled out. Your best feasible alternative is one source of negotiating power, alongside role, information and communication. And it is not what you hope, it is what you would actually do. Two outstanding proposals are not two clients. Assess feasibility, timing and costs before rating strength; it can remain unknown.

Brainstorming and deciding happen at the same time. The method says: first think up options that leave both sides better off, and only then choose. Separating those stages can make space to consider candidates before rejecting them; mutual benefit still needs checking.

There is no objective standard. Comparable market prices, benchmarks, quotations, indices or valuations can support a reasoned comparison. Check their source, date, scope and limits; they do not eliminate judgement or power differences.

Every concession is free. This is the mistake that runs deepest. You give something away to create movement, you ask for nothing in return, and the only thing you learn is that there is more to be had. In its review mode the skill therefore flags every concession made without a counter-ask, and it never proposes one itself either.

These are shortened planning examples consistent with the download. Proposed terms remain subject to cost, authority and counterpart checks; they are not received offers or measured results.

The four pillars separate people from the problem, distinguish positions and interests, generate possible mutual-gain options before evaluating them, and use relevant objective criteria. Criteria need sources, dates, comparability and limits; they support a discussion without eliminating judgement or power differences. BATNA and ZOPA keep alternatives and acceptable terms explicit.

The seven instructions begin with a diagnosis and both parties’ positions and interests. They distinguish a feasible fallback from a prospect, and rate BATNA strength only to the extent supported; unknown is a valid outcome. The other party’s possible alternatives remain labelled assumptions, followed by a proposed preparation action.

The instructions distinguish confirmed, hypothetical and unknown ZOPA, using the appropriate buyer or seller role. At least five proposed packages use variables beyond price; a price adjustment can be tied to duration, scope or another term. Each shows what is offered and requested, the period and relevant unknown costs. The opening asks about unconfirmed interests rather than pretending they were disclosed.

Before anything gets worked out, the skill runs through a mandatory input checklist: what is being negotiated and what is currently on the table, who the counterparty is and what role that person has within their own organisation, your goal in a number or a concrete condition, what you actually do if the deal falls through, your floor and whether that is yours or someone else's in your business, what you already know about the pressure the counterparty is under, and whether the relationship continues after this deal or is a one-off.

Ask for missing essentials together where practical, then produce a provisional analysis with explicit unknowns. Follow up if missing information would change a commitment. Do not guess the user’s authority, minimum or a confirmed offer simply to complete the template.

The eight output blocks remain: situation diagnosis, positions and interests, BATNA analysis, ZOPA and walk-away point, five or more proposed packages, objective criteria, opening and objections, and source and rationale. Packages identify offered and requested terms, price periods, calculable revenue differences and unknown costs. A discount is not automatically a profit calculation.

Here too, remarkably many rules are about language. The file requires the you-form, forbids dashes in running text, forbids rule-of-three lists, and keeps a list of AI words that may not be used. There is one more rule specific to this skill that makes the difference: conversation lines are written as spoken language, because you need to be able to say them out loud without cringing. You can hear that in the opening line in FIG.01, which sounds like someone talking, not someone reading aloud.

Finally, the file has a separate mode for reviewing existing work. Hand it a proposal, an email exchange or a planned approach, and you get five things back: a diagnosis of where the weakness lies, a marking per passage placing POSITION or INTEREST before the relevant sentences so you can see how positional your writing is, a list of what is missing from the checklist, a concession analysis flagging every concession made without a counter-ask, and a rewritten version in the standard output structure. If you want to learn how to set up an instruction file like this yourself, writing a SKILL.md NL explains how that structure works.

The method comes from Getting to Yes, 1981. Roger Fisher and William Ury described the work of the Harvard Negotiation Project in that book, in later editions together with Bruce Patton. The method is also known as principled negotiation and is explicitly meant as an answer to positional bargaining: two parties inching towards each other from an opening bid, which can keep attention on stated offers rather than underlying interests; persistence alone does not determine the outcome.

BATNA comes from the same source. The term is generally credited to the Harvard Negotiation Project without asserting an unverified citation ranking. The core is simpler than the acronym suggests: a feasible alternative is one source of power, alongside role, information and communication. Improving it does not replace careful preparation or guarantee an outcome.

Getting Past No covers the difficult counterparty. Ury wrote that follow-up in 1991, for situations where the other side attacks, blocks or uses tricks. As an addition, it comes in if the other side threatens to walk away or keeps adding new demands after you have given in: it adds a block on naming that behaviour without answering it.

3-D Negotiation widens the field of play. David Lax and James Sebenius described in 2006 that the table is only one of three dimensions. Alongside what you say at the table, the setup of the deal itself and the question of who you invite to the table also matter. If a conversation gets stuck on the table itself, it reaches for this: look at who else should be sitting there, or how you could carve up the deal differently.

Never Split the Difference supplies the tone. Chris Voss described tactical empathy, labelling and calibrated questions in 2016, based on his work as a hostage negotiator. For emotionally charged conversations it draws on this, for example a salary conversation or a conflict with a long-running client, with labels like it sounds like this is mainly about timing.

Distributive versus integrative. Finally, the file uses the distinction between dividing a fixed pie and growing it. That distinction sits in step 1 of the skill for good reason: it determines the whole approach. A one-off sale of a used asset can still involve timing, delivery or other interests. Consider distributive tactics for a predominantly fixed-price issue, without ranking anchoring above understanding interests in every case.

Even without installing the skill, you can use these principles to prepare your next conversation better: write down what you do if there is no deal, find an objective standard to go with it, and make sure there is more than one variable on the table before you sit down.

After that, using it is simple: describe the negotiation in plain sentences, as in FIG.01. What is on the table, who the counterparty is and what role that person has, your goal in a number, what you do if it falls through, your floor, and whether the relationship continues afterwards. If you do not know something, just say so: the skill can prepare a provisional analysis with explicit unknowns, and follows up where a missing fact would change a commitment. If you get stuck on the installation itself, the full route is in installing Claude skills NL. Want your team to learn how to set this kind of work up? That is the subject of our AI training.

The file itself names, per situation, which addition applies. When a counterparty attacks, threatens to walk away or keeps adding new demands after you have given in, Getting Past No comes into play, with a block on naming that behaviour without answering it. If the deal gets stuck on the table itself, it switches to 3-D Negotiation: look at who else should be sitting at the table, or how you could carve up the deal differently.

Tactical empathy may help prepare an emotionally charged conversation. Distributive tactics may suit a predominantly fixed-price issue, including some one-off sales, but a one-off relationship can still involve delivery, timing or other interests. The file does not rank anchoring above understanding interests in every such case.

There are also situations where you are better off leaving it be, and those are stated in the file itself. Legal advice on contract clauses is one: preparing for a conversation is a different thing from writing down what becomes binding, and for that you need a lawyer. Labour disputes with a formal legal procedure are the second. And mediation between two parties where you do not take a side is the third: this skill by definition takes your side, so it is no good as a neutral mediator.

The biggest limitation is a different one, and it is not technical. It prepares the negotiation, it does not conduct it. You are the one sitting at the table, and all sorts of things happen there that no preparation catches: the other side names a number you did not expect, it turns out someone else has a say who you did not know about, or the conversation suddenly turns to something completely different. What the preparation gives you is that in those moments you know where your line sits and which variables you can still use, and that is exactly what disappears first under pressure.

One more honest limit: the quality of the analysis depends entirely on the quality of your description. If you do not mention that your contact does not decide alone, the skill will not account for that. If you name a floor that actually belongs to your business partner, it builds a strategy on a number that is not yours. The checklist asks about this on purpose, and that is not a formality but exactly where most preparations quietly go wrong.

The most honest way to negotiate better is not found in a conversation technique. It is found in your diary. Enquiries may create opportunities, but they are not secured alternatives. Assess feasibility, timing and costs before treating them as a strong BATNA. If too few enquiries come in, that is where the real work sits. The free SEO scan shows in seconds where your site stands. And if you want to talk further about what else AI can do for your business, from loose skills to full automation, we simply do that in a conversation.