Resources / Lookalike Expansion
Live Sales Navigator Discovery

5 seed companies in, 500 lookalikes out.

Drop a list of 3 or more seed companies. The skill profiles them, derives the latent axis that actually ties them together (not just "fintech"), confirms with you, then expands the list. Sales Nav CSV out, with an audit trail.

Download skill Install instructions
v1.0 Web search required Outputs CSV ≤1,000 rows per file
LL
lookalike-expansion.zip
17.8 KB · Bundle: .skill file + SKILL.md inside · v1.0
Download skill
Want to read what it does first? View source ↓
What it does

"More like these" usually means something specific.

Lookalike expansion is a two-step problem disguised as one. First, you have to figure out what these seeds actually have in common (the implicit profile). Then you discover more companies that match. Most tools skip step one and silently pick an axis. Wrong axis, wrong list.

The seeds Stripe, Plaid, Mercury, Brex, and Ramp all share surface attributes (US, fintech, venture-backed). The latent axis is "B2B financial infrastructure for other businesses." Expansion on the surface attribute returns consumer fintech noise. Expansion on the latent axis returns the right shape.

The skill surfaces the latent axis it derived and waits for you to confirm or correct before running discovery. That single step is the difference between a useful list and a directionally-wrong one.

Try saying

Any of these will work.

Find 200 lookalikes of: Stripe, Plaid, Mercury, Brex, Ramp
Expand this list: Linear, Notion, Figma, Vercel
More accounts that match our top 10 customers
Who else is like Datadog and Snowflake?
How it works

Five steps. Surfaces the latent axis.

01

Resolve the seeds

Disambiguates names (Apex could be six companies), fetches each seed's canonical name and domain.

02

Profile each seed

Industry, sub-vertical, headcount, geography, business model, funding stage. Builds the seed matrix.

03

Derive the latent axis

Looks past surface firmographics for what actually ties the seeds together. Often the most consequential decision.

04

Confirm before discovery

Surfaces the derived profile and the latent axis. You say yes or correct. No silent expansion on a wrong axis.

05

Discover and audit

Cross-references 3+ sources, de-duplicates, excludes the seeds themselves. Outputs Sales Nav CSV plus a sister audit CSV.

Why it doesn't lie to you

Built around the things that usually go wrong.

!

Latent axis or bust

The latent axis is always surfaced and confirmed before expansion. It's the single most consequential decision and the skill refuses to make it silently.

@

Seeds excluded from results

Stripe never appears in its own expansion. Auto-excluded. Same for any parent companies and direct competitors (those are surfaced separately if you want them).

?

Single-source expansion is a smell

If all the lookalikes came from one "Top 50" article, that's a brittle list. The skill diversifies across 3+ sources or flags the limitation.

×

3 seeds is the floor

With 1 to 2 seeds, lookalike is ill-defined. The skill tells you it needs more, or redirects to criteria-based discovery instead.

The output

Two CSVs. Upload one, audit the other.

The main CSV is Sales Nav upload-ready (two columns: Account Name, Website URL). The companion audit CSV shows which seed each lookalike maps to, the source URL, and the confidence level. Same row order, easy to spot-check.

Sample output
Account Name,Website URL Adyen,adyen.com Bill.com,bill.com Modern Treasury,moderntreasury.com Unit,unit.co Lithic,lithic.com # audit.csv Adyen,adyen.com,"Stripe,Plaid",HIGH,... Bill.com,bill.com,"Ramp,Brex",HIGH,...
CSV contract
Output
CSV (.csv) x2
Header
Account Name, Website URL
Audit columns
Matches Seeds, Confidence, Source
Row limit
1,000 (Sales Nav cap)
Domain shape
bare apex
Seat tier
Sales Nav Advanced+
Install

Pick your Claude. Drop in the skill.

The download is a zip containing two things: the .skill file (what you upload to Claude) and a SKILL.md sidecar (the human-readable instructions). Unzip first, then follow the steps for your Claude.

⌘
Most people

Claude.ai or Desktop

  1. Download and unzip the bundle.
  2. Open or create a Project in Claude.
  3. Go to Project knowledge, click Add content.
  4. Upload the .skill file from the unzipped bundle.
  5. Start a new chat in that project. Ask it to run the skill.
Download bundle ↓ No restart needed
›_
Developers

Claude Code

  1. Download and unzip the bundle.
  2. Unzip the inner .skill file too (it's also a zip).
  3. Move the resulting folder into ~/.claude/skills/
  4. Restart Claude Code.
  5. Type a prompt that fits the trigger. The skill loads automatically.
Download bundle ↓ macOS / Linux / WSL
{ }
Builders

API or Agent SDK

  1. Download and unzip the bundle.
  2. Open the SKILL.md sidecar to read the full instructions.
  3. Load via the Skills API, or paste the instructions into your agent's system prompt.
  4. Make sure your agent has web_search and file output enabled.
  5. Ship it.
View SKILL.md ↓ v1.0
Source

Read the full instructions.

This is exactly what Claude reads when the skill triggers. No hidden prompts, no separate config. What you see here is what you get.

MD
lookalike-expansion-SKILL.md 12.2 KB · the full skill instructions
⌄
Loading SKILL.md...

Need help implementing this on your team?

We'll install the skills, customize them to your workflow, and run the output through your team's combined LinkedIn network. Skills do the research, Linkd does the motion.

Book a demo