Account/Lead Scoring

Tier inbound leads by fit and engagement before routing

This Skill scores inbound contacts on two separate axes, account fit from firmographics and engagement from your own product usage and Audiences signals, then sorts each contact into one of four tiers with the reasons written back to the record.

Greyson Lampley

Solutions at Clay

About this Skill

When to use it

Use this Skill when you need to score inbound leads or PLG signups on both account fit and real engagement, then route each one to Target Accounts, Marketing Nurture, Opportunistic Sales, or De-Prioritize. It produces a tiered contact list with a written reason for every tier assignment. Avoid using it for tiering a static account list with no engagement signal, judging whether someone is a buyer, or finding and validating work emails on their own.

What it delivers

You get a scored contact record showing fit, engagement, tier, and the reasons behind each score, plus a run summary of tier distribution and cost. The tier decides which play a contact receives, and the Skill never writes to a CRM or routes anyone until you approve the write.

SKILL.md preview

# SKILL.md

The full Skill file is available after sign-in.
This is an illustrative preview, not the source.

## Inputs and setup

Required inputs and setup details appear here.
Sign in to read the complete instructions.

## Workflow instructions

The Skill's execution steps appear here.
This placeholder contains no actual Skill content.

## Outputs and examples

The full file includes its source documentation.
Sign in to view and copy the original file.

## Notes and requirements

Additional source details appear after sign-in.
The actual SKILL.md is not loaded in this preview.

Illustrative preview. Sign in for the actual file.

How someone would prompt this

Score our inbound signups on fit and engagement, using our Audiences data on product usage and seats invited, and tell me who sales should work first.

Inputs & outputs

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

Inputs

Contact source & trigger
- How contacts arrive: manual entry, a signup webhook, or an Audiences segment
- every contact needs at least an email
Ideal customer profile & fit rules
- Headcount sweet spot, industry keywords, and revenue bands that count as fit
- points per fit rule and where each fit band starts
- the borderline range where an agent double-checks the score
Engagement data & mapping
- Which product-usage and signal facts exist and which Audiences fields hold them
- which events count as activity and their point values
- which topics count as intent
Matrix thresholds & tier plays
- The fit and engagement scores that define 'high' on each axis
- names for the four tiers and what each one triggers
Record fields & agent model
- Which Audiences fields receive the score, status, tier, and reason
- which model runs the two agent steps

Outputs

Scored contact recordA contact record with fit score, engagement score, status, tier, and a reason listing every rule that fired, so a rep can see why a contact landed where it did.
Run summaryA plain-language recap of the batch showing tier counts, how many contacts weren't scored and why, and the per-contact cost before you approve a full run.

Representative output

Scored contact record

Contact	Fit	Engagement	Status	Tier	Position	Reason
Priya Nandakumar, VP Sales, northwind.example	100 / 100	58 / 100 (account 18, contact 40)	Engaged	Target Accounts	fit +40 vs line, engagement +8 vs line	838 employees in the 50 to 5,000 band (+40); software (+25); $10M+ revenue (+20); work email resolved (+10); profile verified (+5). Three workspaces created (+10); signup on file (+5); one account signal (+3). Executive buyer (+15); GTM function (+5); demo request and pricing visit (+15, capped); 4 seats invited (+6).
Tomás Rivera, CTO, contoso.example	100 / 100	15 / 100 (account 0, contact 15)	Passive	Marketing Nurture	fit +40, engagement −35	Same fit rules. Executive but not in a GTM function (+15); no activity; company not in Audiences, so no first-party engagement on file.
Mei Okonkwo, CMO, fabrikam-bank.example	53 / 100	53 / 100 (account 10, contact 43)	Engaged	Opportunistic Sales	fit −7, engagement +3	Rules fit 65: 11,600 employees near band (+20); banking is outside core industry (+10); $10M+ (+20); email (+10); profile (+5). Agent judged Weak, −12: "a large bank outside B2B tech poorly matches the target." Two account signals (+5); one surging company topic (+5). Executive in GTM (+20); demo request and pricing visit (+15); one surging person topic (+5); one person signal (+3).
Sam Varga, general manager, litware-hotels.example	45 / 100	13 / 100 (account 5, contact 8)	Passive	De-Prioritize	fit −15, engagement −37	84,000 employees outside the band (+0); hospitality (+10); $10M+ (+20); email (+10); profile (+5). Manager (+8); no activity; two account signals (+5).

The tier is one of exactly four values, plus a separate Not scored list for invalid emails and contacts where no identity resolved.

Run summary

10 contacts scored · 2 Target Accounts · 4 Marketing Nurture · 1 Opportunistic Sales · 3 De-Prioritize · 0 not scored. 7 of 10 matched an existing Audiences record and were updated; 3 were created. Agent consulted on 3 of 10 (fit in the borderline band). Person intent skipped on 2 of 10 (no LinkedIn URL from any source). Cost as reported by the runs: 1.6 credits and 1 action execution per contact on average; the full population of 420 at that rate is about 670 credits before approval.

How the Skill runs

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

Confirm Clay connection and scope

Verifies your Clay sign-in and connection, then states that this run only reads Audiences records and writes score fields, never a CRM.

Interview for scoring rules

Asks for your ideal customer profile, which engagement fields you actually have, topic intent lists, activity types, and tier names, rather than guessing any of them.

Choose manual or automatic trigger

Decides whether you'll run scoring by hand or let a signup, webhook, or segment trigger it automatically going forward.

Run free checks first

Classifies each email, matches existing Audiences records, and resolves a profile URL before any paid enrichment runs.

Test batch and approval gate

Runs ten real contacts, reports their tiers, costs, and the exact fields and records it will create or update, then stops and waits for your explicit approval before anything paid or written proceeds at scale.

Build the scoring workflow

Creates the full workflow in your Clay workspace with every scoring and routing step in deterministic code or rules, not in the agent steps.

Assign the final tier

Gives each contact exactly one tier from the four options, or marks it not scored when the email is invalid or no identity resolved.

Deliver scores and summary

Writes the five score fields to each Audiences record and gives you a batch table, tier counts, and the adjustable scoring constants.

Connections required

No connections listed.

Install Clay and run it

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

Version history

Version 1From submitted SKILL.mdCurrent