Prospecting

Good prospecting forks by motion — B2B SaaS, general B2B, local SMB, or demand-signal discovery for finding your first customers — because "qualified" means something different in each. The workflow is the same five phases every time: define the ICP as pass/fail criteria, source 2-3x more candidates than you need, qualify each with at least one source URL of evidence, score Hot/Warm/Cold/Skip (aim for ~20% Hot, ~30% Warm), then ship a lead sheet. Every email gets deliverability-validated before it lands on the list, and every contact carries a captured source URL and date for GDPR/CAN-SPAM lineage. Twenty-five verified leads beat 250 mostly-junk ones.

When to use it

Your agent reaches for this skill when you ask for things like:

“prospecting,”“build a prospect list,”“find prospects,”“find leads,”“lead gen list,”“find SaaS companies that,”“find B2B companies,”“find local businesses,”

What's inside

The playbook covers

Before StartingPick the BranchShared Framework (all branches)Compliance GuardrailsInputs to CollectTool Selection Quick PicksOutput FormatsQuality Checks (before finalizing)Common MistakesTask-Specific QuestionsTool Integrations

Reference library — 6 deep-dives

B2B Prospecting ReferenceFor when the user sells to non-SaaS B2B — services, agencies, manufacturers, mid-market and enterprise companies, professional services firms.Prospecting Compliance ReferenceThe legal and platform-ToS constraints that apply to prospect list building. Read first, every engagement.Prospecting Data SourcesTool selection guide for prospecting across all three branches.Demand-Signal Discovery (Find Your First Customers)The other three branches build a list from who *fits* (firmographics, technographics, proximity). This branch builds a list from who is *already showing the pain* — the early-stage motion where you have a product and a hunch but no customer base yet, and you need your first ten real conversations. You are not filtering a database; you are mining recent public discourse for people describing the exact problem you solve, then linking every prospect to the evidence.Local SMB Prospecting ReferenceFor when the user sells to local small businesses — shops, gyms, restaurants, salons, clinics, professional services, contractors, real estate, fitness studios, dental practices.SaaS Prospecting ReferenceFor when the user sells SaaS or digital services to other SaaS companies / digital businesses.

Key data

The recommendations are grounded in benchmarks, not opinion:

1. Treating B2B like SaaS — funding rounds matter less; PE ownership and acquisition activity matter more.

RB2B / Clearbit Reveal**: visitor identificationwarm anonymous traffic

G2 reviews mentioning competitor switches**: explicit dissatisfaction signal

2. Treating tech stack data as 100% accurate. BuiltWith and Wappalyzer miss things; Clay's waterfalls miss things. Cross-check.

See it in action

You ask

We're a B2B SaaS selling RevOps tooling at $30K ACV. Build me a list of 25 prospects.

The skill delivers

Lead sheet row (SaaS branch)

Top outreach target

Northbeam — fresh funding plus active RevOps hiring means budget and an owner for the problem right now; VP-level contact is verified and deliverable.

FAQ

How do you find qualified prospects without scraping LinkedIn or Google Maps?

Use browser-assisted research and licensed data providers (Apollo, ZoomInfo, Clearbit, Clay) within their terms, plus public business pages, About pages, news mentions, and directories. Bulk scraping LinkedIn or Google Maps violates their terms and risks account suspension — the browser is an assisted research tool, not a scraper.

Should I verify email deliverability before outreach?

Always. Apollo/ZoomInfo data is often out of date, and sending to invalid addresses spikes your bounce rate and tanks sender reputation — which is hard to recover. Run the list through a validator like Truelist first: keep the deliverable ones, exclude hard bounces, and include catch-all/risky addresses cautiously.

How do I find my very first customers with no prospect database?

Use the demand-signal branch: mine public discourse (forums, communities, reviews, GitHub issues, job posts) for five buckets of evidence — explicit demand, pain, workarounds, switching, and timing. Score each prospect on demand-fit (0-100) rather than firmographic Hot/Warm/Cold, and require a cited public signal for every shortlisted name.

Build a tool for this workflow?

Marketers run this skill mid-task — the exact moment your tool matters. Partner tiers put your tool inside the skill their agent runs.

See partner tiers