Clay logo, go to homepage

Search Marketplace

Browse all Skills
Score & qualifySkill

Score Contacts With Jev

Builds a callable Clay workflow that scores your contacts on role, seniority, and fit using Jev's judgment plus plain code for the rest, returning a 0 to 100 score and tier for each person.

Shy Rahnama
Shy Rahnama

Partner at Redline Growth

About this Skill

When to use it

Use this Skill when you want to score or rank the contacts on your list, judge who is really a decision maker or champion versus a recruiter or student, and weight seniority against how good their company actually is. It builds a scoring rubric from what you already know about your buyers, previews it on ten real contacts, then publishes a Clay workflow you can call from a table, an audience, or a webhook. Avoid using it for scoring companies, finding or enriching people, routing or assigning leads, pushing scores into a CRM or sequencer, or training a model on won and lost deals.

What it delivers

You get a published Clay workflow that returns a 0 to 100 lead score, a tier, and the reasons behind it for every contact you send it. The workflow keeps judgment about the person separate from account fit and simple arithmetic, so a senior contact at a poor-fit company never outranks a strong champion at a good one, and it flags missing data instead of scoring it low.

SKILL.md preview

Sign in to install and view the complete SKILL.md

Illustrative preview. Sign in for the actual file.

How someone would prompt this

Score the people in my Ops leaders audience using Jev, weighting their company's fit tier so a senior contact at a weak account doesn't outrank a strong champion at a good one.

Inputs & outputs

What someone provides before the Skill runs, and the reviewable artifacts it returns.

Inputs

  • 01Contact source and account fit
    • Pick a Clay table, saved audience, or webhook as where contacts come from
    • point to a column or field carrying the company's fit tier if one exists.
  • 02Buyer profile and rubric details
    • Describe what you sell
    • name who signs, champions, and gets consulted
    • say whether seniority matters and who should never count as a prospect
    • note bonus signals like a recent job change.
  • 03Tier cut-offsSet the score thresholds an A, B, or C tier must reach, or accept the suggested defaults.
  • 04Jev API access
    • Provide a TypeSafe or OpenRouter API key
    • confirm or create a Clay HTTP connection holding that same key.

Outputs

  • 01Rubric review cardShows the scoring rules and Jev questions in plain language so you can approve or correct the points before anything runs live.
  • 02Ten-contact previewScores ten of your real contacts with scores, tiers, and reasons so you can confirm the rubric looks right before publishing.
  • 03Delivery summary and call guideGives you the published workflow details plus three ways to send contacts to it: a table, an audience, or a webhook.

Representative output

What comes back on every contact

FieldExample
Score96
TierA
WhyA-tier account (+30) · decision maker (+30) · VP (+11) · new in role (+10)
Needs reviewany answer Jev was less than 60% sure of
Statusscored · disqualified · insufficient_data · not_scored

A reason counts for a contact as (+30) and against them as (0 of 30), so a low score always names what pulled it down.

How the score is built

Every criterion is decided either by plain code or by Jev — never both.

CriterionDecided byPoints
Account fitCodeA +30 · B +20 · C +8
New in roleCodeunder 120 days +10 · under a year +5
Buying roleJevdecision maker +30 · champion +25 · influencer +10
SeniorityJev0 to +15
Not a prospectJevyes at 80%+ disqualifies

85 points possible. A ≥ 70 · B ≥ 45 · C ≥ 25 · D below that. Under 50% coverage a contact comes back insufficient_data — never a low tier.

Jev is TypeSafe's decision model. It answers the judgment questions — *is this person a decision maker? are they a prospect at all?* — and returns a probability for every option rather than a single label, so an unsure answer moves the score less than a confident one. All three questions go in one request per contact. Code does every number: the points, the tiers, the dates. About $0.03 per 1,000 contacts.

Ten contacts, scored

ContactScoreTierWhy
Dana Ruiz · VP Operations · Northwind Supply96AA-tier account (+30) · decision maker (+30) · VP (+11) · new in role (+10)
Lee Park · VP Marketing · Tailspin Toys13DVP (+11) · against: poor-fit account (0 of 30), not involved (0 of 30)
Jo Brandt · Talent Partner · Contoso25disqualifiednot a prospect — recruiter
Ari Moss · no title on record0not_scoredmissing title

Across all ten: A 2 · B 3 · C 1 · D 2 · disqualified 1 · not_scored 1 — total cost $0.0002.

Once it's live

WorkflowJev lead score: contacts · Route-planning buyer fit (published)
Rubric2 rules, 3 Jev questions · tiers A/B/C/D
Jev keyin your Clay connection Jev (TypeSafe)
Account fitread from each contact's Account tier column
Smoke testDana Ruiz — local 96 A, Clay 96 A, answers match ✓

Sending records in

The Skill builds one published workflow. Three things can call it:

A Clay tablebind it at node 1 Intake; the score lands back on each row
A Clay audiencepeople are scored as they join
Anything that can POSTsend the fields to the workflow's webhook URL

Map your columns onto the rubric's inputs — in this example full_name, title, headline, company_name, account_tier, started_role_on. Your column names don't need to match.

How the Skill runs

Follow the steps in order. Each row includes the full instruction.

01
Explain build, cost, and check setup

States what the workflow will do and roughly what it costs, then runs setup checks and stops with a fix if the platform check fails.

Step
02
Choose contact source

You pick a Clay table, audience, or webhook, and the skill reads its columns or fields to see what scoring criteria are possible.

Step
03
Build buyer profile from context

The skill drafts what it already knows about your buyers from memory and documents, then asks only for the missing pieces that change the rubric.

Step
04
Draft and confirm scoring rubric

The skill writes the rules and Jev questions as a rubric card and asks you to confirm or correct the points and criteria before saving.

Step
05
Connect a Jev API key

You supply a TypeSafe or OpenRouter key, which the skill saves locally and verifies works; without one it stops here.

Step
06
Preview scores on real contacts

The skill scores ten of your real contacts, then stops and asks whether the results look right before it continues building.

Output
07
Add key to a Clay connection

You name an existing Clay HTTP connection or create a new one holding the same key so the workflow can call Jev.

Action
08
Build, get approval, and publish

The skill drafts the workflow, states exactly what it will write and cost, and waits for your explicit approval before publishing it.

Step
09
Test with one live contact

The skill runs one contact through the published workflow and checks the result matches the local preview before you use it live.

Step
10
Deliver results and usage instructions

You receive a summary of what the skill built plus three ways to call it going forward: from a table, an audience, or a webhook.

Step

Connections required

Jev API (TypeSafe)Required connection
Clay CLI / agent pluginRequired connection
Clay Public APIRequired connection

Install Clay and run it

Sign in once, install the Skill, then run the prompt.

  1. 1Install ClayUse the connector or official plugin in your coding-agent environment.
  2. 2Sign up or log inAuthorize Clay access and return when the connection is ready.
  3. 3Install the SkillRun the one-line install command from the Add this Skill card.
  4. 4Run the SkillPaste the example prompt and review the result.

Version history

Version 1From submitted SKILL.mdCurrent

Related Skills

Check Employment With JevBuilds a live Clay workflow that checks whether a contact still works at a company, and in what capacity, by judging their LinkedIn work history with Jev.View Skill →Score Accounts With JevBuilds a Clay workflow that scores and tiers your target accounts by combining plain numeric rules with Jev's judgment calls on qualitative fit.View Skill →ICP Outbound CampaignTurns your ideal customer profile into a verified lead list saved in Clay Audiences and a drafted outbound email sequence, without sending or launching anything.View Skill →

Related searches

Score & qualify skillsJev API (TypeSafe) skillsClay agent plugin skillsClay API skills