How to Use Claude for Business Development: The Connor Skill Guide

Updated
Skill · .md

The skill behind this guide: Connor - Business Development Manager AI Skill. Holds your offer, your target thesis and your partner pipeline between sessions, so the tenth conversation starts where the ninth finished - $19, one payment, yours permanently.

View the Connor skill →

Almost every piece of advice about using AI for business development is actually advice about cold email, which is a different job. Business development creates channels and partnerships that do not exist yet, and the hard part is not writing the message. It is working out why the other side would say yes, and that is precisely the thing a model will invent for you, confidently, in a well-formatted table. This guide is about getting the structure without the fabrication.

Business development is not sales, and conflating them is the whole problem

Both end in a signature, which is why they get treated as one thing. They are not, and the difference determines what a model can usefully do.

Sales Business development
The offer Already defined. You sell the thing Partly invented in the conversation. What you build together does not exist yet
The counterparty A buyer with a budget and a problem An organisation with its own strategy, quota and existing partners, buying nothing
What decides it Value against price, against alternatives Whether it helps someone inside their company hit a number they are already measured on
The cycle Weeks to months, with stages Months to years, with long silences that mean nothing in particular
How it dies You lose to a competitor or to no decision It quietly stops in month four because the champion moved team and nobody else cared
What AI is for Volume, personalisation, follow-up discipline Structuring a thesis, finding the questions, stress-testing the logic. Not volume

Read the last row and the practical instruction follows. If your BD problem is "I need to contact more people", you want the SDR guide or the lead generation guide, and you should stop reading this one. If your problem is "I do not know which twenty companies are worth a year of my attention, or what I would even propose", that is a thinking problem, and it is where a model earns its place.

The thing it will invent, which is also the entire job

Ask a model why a target company would partner with you and it will produce an answer. The answer will be fluent, plausible and generic: they would gain expanded distribution, access to a new segment, an enhanced offering for their customers. None of that is wrong. None of it is a reason anybody signs anything.

Real partnerships turn on facts a model does not have. Whether they already have three partners doing exactly this. Whether their strategy this year is expansion or margin. Whether the team you would work with is being grown or quietly wound down. Who inside gets credit if it works, and whether their bonus depends on it. A model has none of that and will not tell you it has none of it.

It gets worse with firmographics. Ask for headcount, funding, revenue, the name of the head of partnerships, or who their existing partners are, and you will get specific-looking answers that are sometimes right and sometimes fiction. An outreach email containing one wrong fact about the recipient's own company is disqualifying in a way a generic email is not. Generic reads as lazy; wrong reads as careless, and partnerships run on the belief that you will be careful.

The scoring trap

This one deserves its own warning because it looks so much like rigour. Paste a list of fifty companies, ask for a partnership fit score out of ten, and you will get fifty scores, ranked, with one-line justifications. It will look like analysis and it is closer to astrology: the numbers come from the vibe of the company name and whatever the model half-remembers about the brand.

The fix is not to abandon scoring. It is to make the model build the frame and leave every cell empty. Criteria you agree with, an evidence source named for each one, and blanks you fill from that source. Then the ranking means something, because you know where each number came from.

Prompt 1 - the thesis, before any names

The mistake is starting with a target list. The list is an output. The input is a defensible claim about what you have that is scarce to somebody else.

Help me build a partnership thesis. Interview me one question at a time and push back when my answer is generic. Do not name any target companies yet. Work through: 1. What we have that is genuinely scarce: distribution, data, a customer relationship, a licence, a capability, a physical asset. Push me until I name something a competitor could not assemble in a quarter. 2. Who structurally lacks that thing. Describe the type of organisation, not the brand names. 3. What they have that we cannot easily build. Be specific. 4. The exchange: what each side gives, what each side gets, and who does more work in year one. 5. Why this is not just a customer relationship or a reseller agreement. If it is one of those, say so plainly, because those are easier and we should do the easy thing. 6. What would have to be true about the market for this to be a bad idea. Then write the thesis in under 150 words, in a form I could say out loud on a call. Then list the three assumptions in it that are load-bearing and untested, and how I would test each one cheaply.
Skill spotlight
Connor - Business Development Manager AI Skill
Connor - Business Development Manager AI Skill
$19 · one payment

Holds the thesis, the criteria you settled on and where each partner sits in the pipeline, between sessions - which matters more here than in most jobs, because a BD cycle runs for months and the context is the asset. It asks for the exchange before it drafts anything, and marks a fact it does not have rather than supplying one.

View Connor - Business Development Manager →

Prompt 2 - a scoring frame with the cells left empty

Build me a partner scoring frame from the thesis below. Do not score anything and do not name any companies. Produce 6-8 criteria that would actually predict whether a partnership works, given this specific thesis. For each one: - the criterion, phrased as a question with a checkable answer - why it predicts success or failure HERE, not in general - where I find the answer: their website, their job ads, their earnings call, their existing partner page, a conversation - what a strong answer looks like and what a disqualifying one looks like - the weight you would give it, and your reasoning Then output an empty table: criteria as rows, [COMPANY 1..N] as columns, every cell marked [FILL]. Finally, tell me which criterion I will be tempted to skip because it is hard to research, and why skipping it is the expensive mistake. THESIS: [PASTE]

Their job ads are the single most underrated source in that list. What a company is hiring for tells you what it is actually investing in this year, in a way its marketing does not, and it is public.

The question that decides most partnerships

Not "does this company benefit". Companies do not sign things; people inside them do, and they do it when saying yes helps them personally. So the operative question is: who inside this organisation gets promoted if this works, and what is their boss measuring them on this quarter?

If you cannot name that person and that number, you do not have a partnership opportunity yet, you have an interesting idea. A model cannot tell you who that person is. It can help you work out what kind of role it would be, what their incentives probably look like, and what you would need to ask in a first call to find out, which is most of the way there.

Prompt 3 - outreach that may only use what you paste

Draft outreach to a potential partner. I will paste: my thesis, and everything I have personally verified about this company and this person. Hard rules: - Use ONLY the facts I paste. Do not add a headcount, a funding round, a customer name, a product detail, an existing partnership or anything about their strategy. If a line needs a fact I have not given you, write [VERIFY: what] and leave it. - Open with what is in it for them, in their language, in the first two lines. - Name the exchange explicitly. What we give, what we want. - Ask for one specific, small thing. Not "a chat to explore synergies". - Under 130 words, no attachment, no link stack. - No flattery, no invented admiration for their work, no fake urgency. Give me three versions: to the person who would own this, to someone senior enough to sponsor it, and a warm-intro request I could forward to a mutual contact. Then list every claim in the drafts and where it came from, so I can check nothing was added. THESIS AND VERIFIED FACTS: [PASTE]

Prompt 4 - the pre-mortem, run before you commit a quarter

Partnerships rarely fail loudly. They go quiet. Running this before you invest the time is cheaper than discovering it in month four.

It is twelve months from now and this partnership produced nothing. Explain why, in detail. Do not hedge and do not give me a balanced view. Write the five most likely failure stories, ordered by probability, each as a short narrative with a specific month where it went wrong. Cover at least: - the champion left or changed team - it was never anyone's priority, so it was never resourced - legal or procurement took longer than the enthusiasm lasted - the economics only worked for one side once real volumes hit - both sides did the easy half and nobody did the integration For each story: the earliest signal I could have seen, and the one question I could ask in the next two weeks that would surface it now. Then tell me which of these I am personally most likely to ignore, based on how I described this deal. THE DEAL: [PASTE]
Complementary prompt pack
Sales & Marketing Prompt Library
Sales & Marketing Prompt Library
$9 · one payment

The repeatable revenue work around a BD motion - follow-ups, launch sequences, co-marketing copy once a partnership is signed, the material a partner needs to sell you internally - as ready prompts rather than a persona you load.

View Sales & Marketing Prompt Library →

Where it fails

  • Firmographics. Headcount, funding, revenue, exec names, existing partners. Specific-looking and sometimes fiction. One wrong fact about their company ends the conversation.
  • Fit scores. Fabricated rigour. Make it build the frame and leave the cells blank.
  • Their internal politics. It cannot know who is ascendant, who is leaving, or which team is being quietly wound down, and that decides more deals than the commercial logic does.
  • Market sizing. Ask how big a segment is and you get a confident number with no source. Use it as a search term, never as a slide.
  • Agreeableness. Ask whether your partnership idea is good and you will be told yes, at length. Ask what a sceptical head of partnerships would object to in the first five minutes.
  • Contract terms. It will happily draft revenue share, exclusivity and termination language. That goes to a lawyer, every time. Reviewing what you were sent to understand it is a different and legitimate use.
  • Volume. The tool makes it easy to contact two hundred companies. In BD that is not scale, it is noise, and it burns the small number of relationships that mattered.

How do you install the Connor skill?

The download is a ZIP with SKILL.md at the root of the archive, not inside a nested folder - that folder structure is the usual reason an upload fails. In the Claude desktop app, open Customize → Skills, upload the ZIP and toggle it on. Claude loads it whenever your request matches what it covers.

Skills need code execution enabled, under Settings → Capabilities. Anthropic's help centre currently lists Skills on Free, Pro, Max, Team and Enterprise, while its Academy tutorial lists Pro, Max, Team and Enterprise - so if you are on the free plan, check Settings → Capabilities for your own account rather than taking either page's word for it. On Team and Enterprise that switch sits with an owner, which is why the menu is sometimes greyed out on a work account. The full walkthrough is in the skill installation guide.

In ChatGPT or Gemini there is no upload step: open SKILL.md, copy the contents, and paste them into custom instructions. You lose automatic triggering and keep the method.

Who is this for?

Founders opening their first partnerships, business development and partnerships leads, and salespeople moving from one-off deals into channels. It works in Claude, ChatGPT or any AI chat.

The catalogue keeps the neighbouring revenue jobs separate rather than bundling them into one vague sales assistant:

The wider set is the sales & marketing growth skills, the shortlist is in AI sales skills for Claude, and if you want the function as running agents the Sales Agent Bundle is five for $99 instead of $195.

In summary:

Business development is not sales, so do not use AI here for volume. Use it to build a thesis about what you have that is scarce, to construct a scoring frame whose cells you fill from named sources, to work out who inside the partner gets promoted if this works, and to run the pre-mortem before you commit a quarter. Never let it supply a fact about their company, and never let it score anything. For the thesis and the pipeline held between sessions, Connor - Business Development Manager AI Skill ($19); for the repeatable revenue work around it, the Sales & Marketing Prompt Library ($9). Both work in Claude, ChatGPT and any AI chat, with a 30-day money-back guarantee.

Skill · .md · Works with Claude & ChatGPT

Connor - Business Development Manager AI Skill

One file that asks for the exchange before it drafts anything, builds scoring frames instead of inventing scores, refuses to supply a fact about a company it cannot check, and carries the thesis and the pipeline across a cycle measured in months. No subscription. Yours permanently.

$19
Get the Connor skill →

KissMySkills is a marketplace of 1,900+ AI skills, 60+ prompt packs, 90+ agents & free tools for Claude, ChatGPT & any AI chat.

Related Skill Guides

Put this into practice

Or get every skill with Unlimited See plans →

Frequently asked questions

Can I use Claude for business development?+

Yes, but not for what most guides suggest. Almost all advice about AI for business development is really advice about cold email, which is a different job. Use it to build a partnership thesis, to construct a scoring frame, to work out the questions to ask on a first call, and to stress-test a deal before you commit a quarter to it. Do not use it for volume outreach, and never let it supply a fact about the other company.

What is the difference between business development and sales?+

In sales the offer is already defined and you are talking to a buyer with a budget and a problem, over weeks or months, and you lose to a competitor or to no decision. In business development what you build together does not exist yet, the counterparty is buying nothing, the cycle runs for months or years with long silences that mean nothing, and it dies quietly in month four when the champion moves team. That difference decides what AI is good for: volume and follow-up discipline in sales, structure and stress-testing in BD.

Why does AI give generic partnership advice?+

Because the real answer depends on facts it does not have. It will tell you a target would gain expanded distribution or access to a new segment, which is fluent and true of almost anyone. What actually decides a partnership is whether they already have three partners doing exactly this, whether their strategy this year is expansion or margin, whether the team you would work with is growing or being wound down, and who inside gets credit if it works. A model has none of that and will not tell you it has none of it.

Can AI score potential partners for me?+

It will, and the scores are close to astrology. Paste fifty companies and ask for a fit score out of ten and you get fifty ranked numbers with one-line justifications that look like analysis and come from the vibe of the brand name. The fix is not to abandon scoring but to make the model build the frame and leave every cell empty: criteria you agree with, a named evidence source for each, and blanks you fill from that source. Then the ranking means something.

What should I never let AI invent in business development outreach?+

Firmographics. Headcount, funding, revenue, executive names, product details, and especially who their existing partners are. These come back specific-looking and are sometimes fiction. One wrong fact about the recipient's own company is disqualifying in a way a generic email is not: generic reads as lazy, wrong reads as careless, and partnerships run on the belief that you will be careful. Instruct the model to write VERIFY and leave a gap rather than filling it.

What actually decides whether a partnership happens?+

Not whether the company benefits. Companies do not sign things, people inside them do, and they do it when saying yes helps them personally. The operative question is who inside the organisation gets promoted if this works, and what their boss is measuring them on this quarter. If you cannot name that person and that number, you do not have a partnership opportunity yet, you have an interesting idea.

How do I stop a partnership dying quietly?+

Run a pre-mortem before you commit the time. Ask the model to write the five most likely failure stories twelve months out, each with the month it went wrong: the champion left, it was never anyone's priority so it was never resourced, procurement outlasted the enthusiasm, the economics only worked for one side at real volume, or both sides did the easy half and nobody did the integration. For each, the earliest signal and the one question you could ask in the next two weeks to surface it now.

How do I install the Connor Business Development skill?+

The download is a ZIP with SKILL.md at the root of the archive, not inside a nested folder. In the Claude desktop app open Customize then Skills, upload the ZIP and toggle it on. Skills need code execution enabled, under Settings then Capabilities, or by an owner in organisation settings on Team and Enterprise. Anthropic's help centre currently lists Skills on Free, Pro, Max, Team and Enterprise, while its Academy tutorial lists Pro, Max, Team and Enterprise, so if you are on the free plan check Settings then Capabilities for your own account rather than trusting either page. In ChatGPT or Gemini, paste the contents of SKILL.md into custom instructions instead.

~/get-started

Skills that work. No fluff.

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

Browse all skills →Or try the free tools