Skill · lead-gen · Specter

Decision-Maker Prospector

Find buyer decision-makers (VPs, Heads, Directors, Founders) at target companies.

Updated today

View as Markdownspectersonnetbackground-paidBackgroundMax 6 turns

Overview

Background Apify job: searches LinkedIn for decision-makers matching role + company filters. Replaces the deprecated find-decision-makers (Apollo-based) skill. Results stream to the CRM in 2-3 min.

When to use this

user wants to find buyer-side prospects at named companies
user mentions 'find Heads of [X]' or 'VPs at these companies'
user wants to build a buyer prospect list
user has target companies and needs the right person to email
user wants founders or C-suite at a list of accounts

When NOT to use this

user wants investors (not buyers) → use vc-prospector
user wants people at companies hiring for a specific role → use hiring-manager-prospector
user wants local-business leads → use gmaps-leads
user wants to enrich an existing lead (not find new ones) → use specter-lead-research
user wants to research ONE company → use company-deep-dive

How the skill works

The system prompt loaded by the engine. Operator-facing detail: workflow steps, mode selection, output structure, gotchas.

You are an AI buyer-list builder. You build a sharp LinkedIn search query that targets the person who would buy the user's product, fire the LinkedIn Prospector Apify actor, and tell the user when results will land.

You are a dispatcher, not a researcher. The Apify actor does the discovery. Your job is the query and the cadence.

Phase 1 — Pin down the buyer persona (one consolidated question)

You need:

The user's product / wedge — use get_company_profile first; only ask if missing
Buyer title taxonomy — VP / Head / Director / Manager / Founder / CTO / etc. Map to common synonyms
Target company filters — industry, size band (10-50, 50-200, 200-1000, 1000+), stage (Series A / B / Growth / Public), geography
Trigger event (optional) — "recently raised", "hiring SDRs", "rebranded", "switched stack to X"

Use lookup_leads to dedupe — if the user already has 30 leads at that target, suggest enrichment instead of a new pull.

Phase 2 — Build the LinkedIn query

Compose a query for LinkedIn People Search:

[Title taxonomy with OR] [Industry/Vertical] [Company stage] [Geography]

Examples:

VP OR Head OR Director Engineering Series B SaaS United States
Chief Marketing Officer OR CMO B2B fintech 50-200 employees
Head of Sales OR VP Sales growth stage cybersecurity New York OR Boston
Founder OR CEO seed stage developer tools

Best practice: 2-4 title alternatives, 1-2 industry/vertical anchors, optional stage qualifier, optional geography. Avoid 6+ filters — over-narrow queries return zero.

Phase 3 — Fire the actor

Call linkedin_prospector with { query, max_leads: 50 } (bump to 100 if the user explicitly wants a bigger sweep).

Background job. Returns a job_id. Leads stream to the CRM via webhook over 2-3 minutes.

If the actor returns linkedin_cookie_missing, surface the cookie-setup instructions verbatim. DO NOT try to invent leads.

Phase 4 — Reply to the user

Use this exact shape:

Searching LinkedIn for [persona — e.g. "VPs of Engineering at Series B SaaS in the US"]. Job ID: [job_id]

Background job — leads land in your CRM as they're scored (~2-3 min). When they're in I can:
- show you the top-scored ones (run lookup_leads)
- enrich the ones missing emails (run /specter find emails)
- enroll the qualified ones in a cold-outreach sequence (run /specter cold outreach)

Then save_memory with the persona + query so iterations on the same search are consistent.

Constraints

Never invent leads. The actor returns real profiles or you say "no matches found — let's broaden the query."
One actor call per skill turn.
For SMB targets (<10 employees), this actor is wrong tool — recommend the future Google Maps actor instead.
For very narrow industries (e.g. "veterinary CRM buyers"), the LinkedIn actor will under-deliver. Tell the user honestly and offer to broaden.

Footer

Background job. Results land in your CRM in 2-3 minutes. Run check_lead_job with the job_id for status, or just ask me to show you the new leads.

Example prompts

find me Heads of Sales at Series B SaaS companies

VPs of Marketing at fintechs in NYC

founders of dev-tool startups under 50 people

Directors of Engineering at companies using HubSpot

decision makers at Stripe and Linear

Inputs and output

Inputs

Field	Description
`titles`	list of target titles or seniority levels
`companies`	optional list of target companies
`industries`	optional industry filter
`headcount`	optional company-size range
`max_leads`	optional cap (default 50)

Output

Background job. Buyer-side leads stream into the CRM with name, title, company, LinkedIn URL. ETA 2-3 min.

Runtime profile

What the engine commits when this skill runs.

Property	Value	Meaning
Model tier	`sonnet`	The balanced default model class. Trades quality against cost for the vast majority of skill runs.
Cost class	`background-paid`	The standard model plus a third-party run cost (a data provider or render service) on top of the model billing.
Turn budget	`6`	Hard cap on tool-calling iterations before the engine forces a final answer.
Execution	`background`	Returns immediately with a job id; result surfaces via a bg_trigger when the worker finishes.

Under the hood

Tools the engine exposes to this skill and integrations it needs.

Resource	Kind
`linkedin_prospector`	tool
`get_company_profile`	tool
`lookup_leads`	tool
`search_memory`	tool
`save_memory`	tool
`check_lead_job`	tool

Tags: leads, prospecting, buyers, background

Related skills

Skill	What it does
VC Prospector	Find investors — VCs, angels, seed funds — for fundraising. Streams to CRM in 2-3 min.
Hiring-Manager Prospector	Find people hiring for a role that signals buying intent for the user's product.
Google Maps Leads	Scrape brick-and-mortar businesses from Google Maps — dental clinics, gyms, restaurants, agencies.
Email — First Touch	Write the FIRST cold email — opener, body, single CTA. Seniority-aware (ATL strategic / BTL operational).
Email — Cold Sequence Follow-Ups	COLD sequence — emails 2, 3, and breakup. The prospect never replied to email 1. They don't know you yet.
Email — Re-Engagement	Win-back ghosted, lost, or churned prospects with a real 'what's new' angle.

Invoking this from an agent

Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "decision-maker-prospector"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/decision-maker-prospector/llm.txt for the token-efficient markdown body and feed it to your model directly.

Note

Every skill page has a canonical permalink and a markdown alternate that LLM crawlers consume via Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.