Clay logo, go to homepage

Search Marketplace

Browse all Skills
ResearchSkill

Alpha Radar

Builds a reusable Clay workflow that finds professional candidates from a brief, checks their public work, scores the evidence, and learns from likes and dislikes to sharpen future shortlists.

Josh Whitfield
Josh Whitfield

Founder at Content Marketing Media

About this Skill

When to use it

Finding people or agencies worth featuring or partnering with takes manual research and repeated judgment calls about who really qualifies. Alpha Radar turns a plain-English brief into a repeatable Clay workflow that checks public evidence and remembers your preferences on the next run.

What it delivers

You get an evidence-ranked shortlist with source links, a written brief explaining each match, and a receipt showing what the workflow learned from your reviews. A positive review can move a qualified candidate up the list, but it can never make unsupported evidence pass.

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

Find GTM operators I could feature on our podcast who've published detailed outbound workflows.

Inputs & outputs

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

Inputs

  • 01Audience brief
    • Describe who you want to find and why, in plain English
    • include geography, evidence you value, and exclusions
    • add the actual offer only for sales use.
  • 02Workspace and install setup
    • Confirm your authenticated Clay workspace
    • choose a display name for the workflow or accept the default
    • pick a local path to store the installation receipt.
  • 03Sample and scoring settings
    • Optionally set sample size and score thresholds such as max candidates, minimum score, fit, proof, and sources
    • review the proposed dimension weights before accepting.
  • 04Review preferences
    • Your prior completed run for the same brief supplies review memory automatically
    • mark candidates you like or dislike by name to teach future priority.
  • 05Run authority and budget
    • Tell Clay how many candidates it can research in this run and set a spending limit before it starts
    • Clay only asks if the run needs more research or money than you already approved.

Outputs

  • 01Evidence-ranked shortlistA table listing each candidate with a fit score, an evidence score, a check showing whether the ranking depends on just one source, a pass or hold verdict, and a suggested next step to review.
  • 02Feature and learning briefA written summary explaining why each qualified candidate matches your brief, linked to the public evidence found.
  • 03Review-memory receiptA record of what this run researched, any new likes or dislikes you gave, and what carries forward to the next run.
  • 04Preference impact tableA table showing how a like or dislike shifts a candidate's priority score without changing whether they qualify.

Representative output

Evidence-ranked shortlist

PersonWhat they doWhat we foundScoreHow solid is itWhat to do next
Adele VanceRuns a small outbound-training studioA step-by-step post on fixing a broken targeting rule — what she changed, and how she tested it72Most of it rests on that one post. Without it she scores 49Ask her to walk through the test live before you feature her
Alex WilberFreelance RevOps consultantTwo write-ups of a lead-routing rebuild, plus the template he used61Solid. Two separate sources, newest from 4 months agoGood to go. Ask what he'd do differently now
Diego SicilianiRuns a small RevOps agencyThree case studies, none of them naming who built the work41The case studies don't say which parts his team deliveredAsk which parts were his, then check again
Megan BowenHeads ops at a mid-size SaaSA conference talk and a podcast, both about the work38Nothing published you can look at yourselfAsk if she can share the playbook itself

How the Skill runs

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

01
Confirm platform and boundaries

Clay checks your login, workspace, and required features, and stops rather than working around it if a needed capability like web search or code nodes is missing.

Step
02
Define objective and sample

You confirm the audience objective and scoring defaults; the workflow keeps the same criteria on repeat runs so scores stay comparable.

Step
03
Build the Clay workflow

The installer creates a persistent Clay workflow with linked research, scoring, and review nodes, first as a preview and then for real once authorized.

Step
04
Approve and run the sample

The workflow stops and waits for your approval of the research scope and spend before running the authorized sample of candidates.

Step
05
Score and qualify candidates

Clay scores each candidate's public evidence, tests how much the ranking depends on a single source, and marks each as qualified for review or needing more research.

Output
06
Apply your review feedback

Marking a candidate as liked or disliked updates memory for that category, shifting future priority by a small bounded amount without changing qualification.

Step
07
Deliver shortlist and limits

You receive the workflow link, shortlist, evidence, sensitivity test, and learning state, plus an honest missing-proof queue if nobody qualifies.

Step

Connections required

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 2From submitted SKILL.mdCurrent

Related Skills

Find Recent Company DevelopmentsBuilds a Clay workflow that turns a list of companies into dated, sourced briefs on new leadership, M&A, news, and transformation activity inside a time window you set.View Skill →Swap TestChecks how much of a cold email is generic template versus specific fact, then rewrites the template sentences using only sourced details.View Skill →Pricing Page SignalChecks whether a company publishes public self-serve pricing and extracts its plan tiers, prices, and pricing model into a structured record for each domain.View Skill →

Related searches

Research skillsClay API skills