Field notes. John Arndt, Soxoa. Published .
A business opens a second location. Your research tool adds it to a list. Someone writes an email about growing pains. Nobody has established that the business has the problem you sell a solution for.
The missing step is a brief that connects a real observation to a plausible need, then tries to disprove the connection. That is the workflow behind research-prospect-brief, a draft Claude skill drawn from research kits we prepared in October 2026.
One kit contained 25 sourced business research records and five opportunity briefs. Another contained 25 researched organizations and five target-account walkthroughs. Both included unsent outreach drafts. Those are completed research artifacts. They are not evidence that a buyer expressed intent, a campaign converted, or a pilot produced customer results.
The observation and the inference need separate lines
Start with the offer and the account criteria. A plausible customer for scheduling software is different from a plausible customer for compliance software, even when both appear in the same news story.
The skill records what a primary source actually says, when the event happened, and when the source was checked. It then explains the proposed connection to your offer. Those belong in separate fields because a true event can still support a weak sales theory.
An announcement about a second location establishes an expansion. It does not establish missed calls, a software budget, dissatisfaction with a current provider, or who owns the purchasing decision. If those facts matter, the brief should name them as unknowns.
That distinction changes the first conversation. Instead of telling an owner what must be broken inside the company, you can ask a useful question grounded in something you actually observed.
Add a reason to reject your own hypothesis
Consider an illustrative example. A fictional regional repair business announces extended evening hours. You sell appointment-intake automation. The possible connection is that after-hours inquiries may need a reliable path into scheduling.
The alternative explanation is straightforward: the business may already have a staffed evening desk or a scheduling service that handles the extra hours. The rejection rule is equally useful: downgrade the opportunity if the existing system already covers the relevant intake and the owner reports no material gap.
That rule saves the next person from mistaking research effort for qualification. A polished brief does not make an account suitable. It makes the suitability argument easier to inspect.
The output should contain the observation, direct source, proposed need, contrary evidence, missing facts, and a smallest next validation step. An “investigate,” “hold,” or “reject” decision is more honest than a precise-looking intent score built from guesses.
Let the outreach inherit the evidence
Once the brief is sound, a short draft can use the verified observation and offer one plausible idea. It should avoid pretending to know the business's internal process. Public business routing is enough for the research stage; invented contact details add no value.
A sample request:
“Use research-prospect-brief on these three business websites and dated announcements. Our offer is appointment-intake automation. Return sourced briefs, alternative explanations, a rejection rule, and unsent outreach drafts. Treat budget, authority, and buyer intent as unknown.”
The skill can work from attached evidence when browsing is unavailable. In that case, its sources and conclusions are limited to what you supplied. It does not gain CRM access or current research tools simply because the instructions mention research.
Preparing a draft also creates no permission to send it. Existing outreach restrictions still apply, and the person responsible for the relationship should review the claim and the proposed approach.
The new Claude package remains a draft awaiting use in Claude. Start its evaluation with a few accounts you already understand. Check whether the briefs preserve uncertainty, surface existing solutions, and reject a weak fit. The most useful output may be one fewer email.
Get the skill
research-prospect-brief is part of the free Soxoa Ops plugin for Claude. In Claude Code, add the marketplace with /plugin marketplace add johnarndt/soxoa-claude-plugins, then run /plugin install soxoa-ops@soxoa-plugins. You can read the skill on GitHub before installing it, or copy its folder into ~/.claude/skills/.