Clay logo, go to homepage

Search Marketplace

Browse all Skills
Score & qualifySkill

Account Priority Buckets

Decide which target accounts to work this week

Scores and sorts a target account list into action, research, monitor, and deprioritize buckets using verified pain quotes, fit, and timing signals. Each priority account gets an account context with evidence and a draft outreach message for human review.

Jonathan Kvarfordt
Jonathan Kvarfordt

GTM and Revenue AI Strategiest at Revenue AI Report

About this Skill

When to use it

Use this Skill when you need to decide which accounts your team should work this week, sorting a target list into action and research buckets with a clear why-now reason for each. It separates real buyer pain, backed by a quote, from guessed intent, so reps never personalize outreach around a problem nobody actually said out loud. Avoid using it for building a list from scratch, filling in missing firmographics, scoring inbound leads or individual people, sending or sequencing outreach, or writing scores back into a CRM.

What it delivers

You get a ranked priority board sorting every account into one of five buckets, plus a detailed Account Context for each account worth working, including a verified pain quote, timing signals, a hypothesis, and a draft message labeled for human review. Every score stays auditable back to its evidence, and nothing is sent or written to a CRM without a person approving it first.

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

Help me figure out which of our target accounts to work this week by scoring fit, verified pain, and timing signals so my team knows exactly who to prioritize.

Inputs & outputs

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

Inputs

  • 01Account data and evidence
    • Give your account list as a CSV, table, or pasted rows with at least one domain per row
    • share any call quotes, CRM notes, reviews, or engagement data you already hold
    • say which system holds that evidence and provide any public URL that shows buyer pain in their own words.
  • 02ICP definition
    • Define your ideal customer profile with employee and revenue bands, target industries, regions, and tools you replace
    • choose which dimensions must be true to count at all
    • set the weight of each dimension and the Fit Score cutoff for High FIT.
  • 03Timing and signal weights
    • Name the champion and economic-buyer titles per motion
    • set how many days back a change still counts as recent
    • confirm or replace the default point values for each signal type.
  • 04Spend limitSet the maximum Clay credits you allow this run to spend before paid enrichment starts.
  • 05Proof points for messaging
    • Supply your own product claims or case studies if you want them included in outreach draft messages
    • without them those lines are left as marked gaps.

Outputs

  • 01Priority boardGives you a sorted table of every account placed into Action high, Action standard, Research, Monitor, or Deprioritize so you know who to work first.
  • 02Account ContextGives you a detailed brief per priority account with the verified pain quote, recent signals, a hypothesis, reasons it might be wrong, and a draft outreach message for a human to review.

Representative output

Priority board

AccountFitMomentumPainBucketNext action
northwind.example8.719 · 3 inferredVerifiedAct nowoutreach today
contoso.example8.111 · none inferrednot foundResearchfind the pain, else drop at 30d
fabrikam.example3.2——Drop140 employees, under the 500 floor

— means not scored: gated before momentum and pain ran.

Why Northwind is "Act now"

Fit 87/100 — employee band 35/35 (1,200, exact), industry 30/30 (fintech), region 22/22 (Canada), replacement target 0/13 (none detected).

Momentum 19 — the public pain quote carries 10 (Verified), the new Head of Data 6 (Supported). Two CTO pricing-page visits add 3, Inferred from an IP match, so they count toward the score but stay out of any draft until a human confirms them. The Series C is 97 days old and scored 0 against the 90-day window.

We're spending 30% of our data team's time on spreadsheet reconciliations. That is not why I hired them.

— VP Analytics, LinkedIn, 12 days ago

Hypothesis. A new Head of Data with modern infrastructure experience, and a VP Analytics who has named the pain in public. Analytics Modernization motion, VP Analytics as champion, CTO as economic buyer.

Why we might be wrong.

  • The new data leader may already have a preferred vendor.
  • Post-funding scaling often freezes evaluations.
  • The pricing visits are unverified and may be diligence.

Message angle — two of six components need installer inputs that weren't supplied, so this is the argument, not a sendable draft.

  • Signal. Your post about the team spending 30% of its time on reconciliations.
  • Pain. That is the loss data teams describe before they switch.
  • Consequence. Board dashboards go stale and trust in the numbers erodes.
  • Value. [installer's claim — not supplied]
  • Proof. [installer's case study — not supplied]
  • Action. Worth 20 minutes next week to compare notes?

How the Skill runs

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

01
Check platform and explain scope

The Skill confirms it can access Clay, then tells you it only reads your account list and Clay enrichment data, writing a priority board and Account Context drafts in this session without touching your CRM or sending anything.

Step
02
Interview for your inputs

The Skill asks you one question at a time for your account list, ICP definition, FIT weights, High FIT cutoff, MOMENT window, personas, MOMENT weights, first-party evidence, and credit ceiling, without assuming any defaults.

Step
03
Explain the scoring model

The Skill walks you through how FIT, PAIN, MOMENT, and CONFIDENCE are each calculated and how they combine into the five priority buckets before any scoring begins.

Step
04
Run free checks first

The Skill grades accounts against firmographics you already supplied, matches your first-party evidence by domain, and flags dead or acquired companies, all before spending any credits.

Step
05
Test a small batch, then pause

The Skill enriches 10 surviving accounts, reports the actual cost and any issues found, then stops and waits for your approval before spending more on the rest of the list.

Step
06
Enrich remaining signals

The Skill gathers firmographics, tech stack, executive hires, job postings, funding, and any public pain evidence you name, tagging each signal with a confidence level.

Agent
07
Grade and sort accounts

The Skill applies the scoring rules exactly, placing every account into one of the five buckets, a cannot-score list, or a liveness-doubt list.

Step
08
Write account briefs and deliver

The Skill writes a full Account Context for each Action and Research account, including a draft outreach message labeled for human review, then delivers the board and all supporting lists.

Action

Connections required

No connections listed.

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

Score Contacts With JevBuilds a callable Clay workflow that scores and ranks your contacts on role, seniority, and buyer fit using Jev's judgment plus plain code for the numeric parts, returning a 0 to 100 score, tier, and reasons for each person.View Skill →Score Accounts With JevBuilds a Clay workflow that scores and tiers your target accounts, combining plain numeric rules with Jev's judgment calls on qualitative fit, and returns a 0 to 100 score with reasons for each account.View Skill →10k Value Prop MatchCompares a seller's value proposition against a target company's own 10-K language and returns matched initiatives with the literal supporting quotes, flagging whether each need looks open or already solved in-house.View Skill →

Related searches

Score & qualify skills