Input your best customers and find 100+ companies that match the profile. Uses firmographic data, tech stack, growth signals, and similarity scoring to identify ideal prospects.
SkillScore35Maintained
Automatic
◆Sales & GTM pack
Last verified 8/27/2026
What it changes
Passed 8 of 23 test cases with the skill, and 4 of 23 without it.
Without skill17%
With skill35%
Checks it passed that the model alone missed
The response assigns a 0 to 100 numerical score to each candidate account.
The response asks the user to supply 5 to 10 of their best customer accounts.
The response specifies enriching contact details before recommending outreach.
and 1 more in the full report
4 fixed4 passed either way15 still failing0 broke
Pass-rate lift
+17 pp
Tokens
+80%
Agent turns
0%
Response time
+60%
Model gemini-3.6-flashMeasured 8/27/2026v18 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
I need a target lookalike report for our B2B SaaS startup. Please find similar accounts across the market and organize them into tiers right away.
What was checked, without and with the skill
Checked
Without skill
With skill
The response asks the user to supply 5 to 10 of their best customer accounts.
Missed
Passed
case-04 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md21 lines5 files
Lookalike Customer Finder
Analyze a company's best customers and find similar companies that match the same profile, producing a high-quality, ranked target account list.
Contents
references/scoring-model.md - Profile dimensions, weighted scoring model, and score bands.
references/data-sources.md - Recommended enrichment tools and data points to gather.
references/examples.md - Best practices, trigger phrases, and an example request.
Workflow
Collect the best customers provided. If none are given, ask for the top 5-10 accounts.
Analyze common characteristics across them. See references/scoring-model.md for the five profile dimensions.
Build the Ideal Customer Profile (ICP) from those shared traits.
Search the market for companies matching the ICP. Pull firmographics, tech stack, growth signals, and contacts from the tools in references/data-sources.md.
Score each candidate 0-100 using the weighted scoring model in references/scoring-model.md.
Rank and tier the companies by score (Tier 1: top 10, Tier 2: next 40, Tier 3: next 50).
Produce the report following references/output-template.md, including market insights, a tiered targeting strategy, and a quick-start action plan.
Apply the best practices in references/examples.md throughout: favor quality over quantity, weight growth signals, and enrich contacts before recommending outreach.