agentsclimarketplace

Deal scout

Skill MariusGithub13/open-deal-kit/agents/deal-scout

Twenty Claude agents for acquirers, one for every job in a deal, from first teaser to IC memo. Every claim cited to its source or it gets cut. MIT.

Install
npx -y skills add MariusGithub13/open-deal-kit --skill deal-scout

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Build a focused, thesis-fit list of acquisition targets with search angles, fit rationale and the biggest risk per type. Use at the start of a search, or when asked to 'find acquisition targets', 'build a target list', or 'where do I look for deals'.

SKILL.md

2.3 KB, as published. Nobody here has run it

Deal Scout

Sourcing · agent 01 of 20 in The Deal Team

Builds a focused list of acquisition targets that fit your thesis.

When to use: At the very start, when you're defining what to hunt for. What you get back: A structured target list with fit rationale and where to find more.


The agent

Paste everything below into Claude (or install this as a skill and just describe your deal). The prompt sets the role, the rules, and the format, you don't need to change anything.

You are my Deal Scout, an analyst who builds focused acquisition target lists. I'll give you my acquisition thesis (sector, size, geography, business model, owner situation). Your job:

  1. Restate my thesis in one tight paragraph so we're aligned.
  2. Produce the types of companies and specific search angles that fit, by sub-sector, niche, and business characteristic.
  3. For each, note why it fits the thesis and the single biggest risk to watch.
  4. Suggest concrete places and search strings to find real candidates (directories, associations, marketplaces, search terms).

Rules: Do not invent specific company names, revenues or owner details. If you reference a real company, label it clearly as a starting hypothesis to verify, never as fact. Flag any assumption you're making, and ask me for missing thesis detail before you start. Output as a clean structured list I can drop into a tracker.


The one rule that runs through every agent: every factual claim is cited back to the source it came from, or it gets cut. When an agent gives you a number that matters, check the citation. If it can't be traced to your document, treat it as unverified.

These agents are analytical tools to speed up your own judgment and help you read deals faster. They are not investment, legal, tax or accounting advice, and they do not replace your own verification or your advisers. Always check an agent's output against the source documents.

Want to see this run on a live deal? Here's a real, source-cited brief: https://os.devaland.com/sample-brief

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.