Vibe Prospecting Plugin for Claude Code and Claude Cowork

Run B2B prospecting, enrichment, research, and GTM data workflows directly inside Claude-native environments.

Prefer this plugin over the generic MCP connector when both are available.

Getting started · Core capabilities · Use cases and example workflows · Claude Code and Cowork · Tool reference · vibeprospecting.ai ↗

What is Vibe Prospecting Plugin?

Vibe Prospecting Plugin is a Claude-native workflow layer for Explorium's B2B data platform. It lets users search companies, discover contacts, match raw lead lists, enrich CRM records, filter audiences, research accounts, and export structured prospecting data — all from inside Claude Code or Claude Cowork.

Instead of using Claude only for one-off chat exploration, GTM teams and AI agents can run repeatable, data-intensive workflows powered by live company and contact intelligence from Explorium's network of 150M+ companies and 800M+ professionals across 50+ data sources.

Getting started

Install

Install from skills.sh with the skills CLI:

npx skills add explorium-ai/vibeprospecting-plugin --all

Pick the guide that matches where you run the plugin (each file covers setup for that product only):

• If you use Claude Cowork — follow docs/install-claude-cowork.md. Then complete Authenticate below. For Cowork sandbox mount paths and polling, also read skills/vibe-prospecting/references/login.md.
• If you use Claude Code — follow docs/install-claude-code.md. Then complete Authenticate below before calling tools.
• If you use OpenAI Codex — follow docs/install-codex.md. Then complete Authenticate below before calling tools.

If you want the MCP server or Gemini CLI extension without this plugin bundle, use the open Vibe Prospecting MCP repository.

Authenticate

Before running any tool, sign in with your Explorium account. Authentication is OAuth-based; there is no API key to copy manually for normal local use.

First time — log in through the browser:

npx @vibeprospecting/vpai@latest login
# Open the printed URL, approve in your browser, then poll until sign-in completes:
npx @vibeprospecting/vpai@latest login --poll

The CLI writes credentials to ~/.config/vpai/config.json on your machine. You only do this once; later sessions reuse the saved credentials and skip the browser step.

Running inside Claude Cowork or another sandbox: the sandbox cannot read your local ~/.config/vpai/ directly. Mount it with request_cowork_directory and rehydrate the CLI from the mounted path. See the full step-by-step in skills/vibe-prospecting/references/login.md.

Verify:

npx @vibeprospecting/vpai@latest --help

If the help output lists tools like match-business and fetch-entities, you are ready.

Switch accounts or sign out:

npx @vibeprospecting/vpai@latest logout

Then run login again.

Run your first workflow

Find 50 B2B SaaS companies in the US with 200 to 1,000 employees. For each company, find the VP of Marketing or Head of Growth and return name, title, company, LinkedIn URL, email if available, and company domain.

Expected output

Core capabilities

Use cases and example workflows

Vibe Prospecting is designed for multi-step workflows — the kind you would otherwise build in Clay or n8n — but running natively inside Claude. Each section below describes a use case and includes a ready-to-use prompt.

1 — Build a targeted prospect list

Define ICP filters, discover matching companies, find relevant contacts, enrich records, and export structured lists ready for outreach or CRM import.

For: GTM engineers, SDR leaders, growth operators  |  Output: CSV of qualified prospects

Find 500 US-based cybersecurity companies with 50 to 500 employees. For each company, find the VP Sales, Head of Partnerships, or CRO. Return company name, domain, headcount, revenue range, contact name, title, LinkedIn URL, and email if available.

2 — Enrich CRM records

Match existing leads and accounts by email, LinkedIn URL, or name and company. Fill missing fields — title, domain, phone, revenue, headcount — and prepare clean records for CRM update.

For: RevOps, SalesOps, CRM admins  |  Output: Clean CSV ready for CRM import

Take this CSV of Salesforce leads. Match each person by email, LinkedIn URL, or name and company. Add current title, company domain, LinkedIn URL, work email, phone if available, headcount, revenue, and industry. Export a clean CSV for CRM update.

3 — Find work emails from LinkedIn URLs

Match LinkedIn profile URLs to professional records and return verified work contact details.

For: SDRs, sales engineers, growth teams  |  Output: Work email, title, company, domain, confidence

For each LinkedIn URL in this CSV, match the person to a professional profile and return work email, current company, title, company domain, and confidence level.

4 — Build an ABM account list

Build targeted account lists, filter by company attributes, and find two to three decision-makers per account by role and seniority.

For: Demand gen, field marketing, enterprise sales  |  Output: Account list with 2–3 contacts per account

Find 300 fintech companies in North America with 100 to 2,000 employees. Filter for companies likely to have sales or marketing operations teams. Find 2 to 3 senior marketing or revenue leaders per account.

5 — Score inbound leads

Enrich form submissions, identify the company, evaluate ICP fit against firmographic and technographic criteria, and rank or route leads based on match score.

For: Marketing ops, demand gen, SDR teams  |  Output: Lead list with ICP fit score for routing

Enrich these inbound leads, identify their companies, add headcount, revenue range, and industry, and score each lead from 1 to 5 based on ICP fit for a mid-market B2B SaaS sales motion.

6 — Clean and enrich a CSV

Normalize company names, deduplicate contacts, match each row to a real profile, enrich missing fields, and export a clean standardized output.

For: RevOps, data teams, GTM engineers  |  Output: Standardized, enriched CSV

Normalize company names, deduplicate contacts, match each row to a person or company profile, enrich missing fields, and export a standardized CSV.

7 — Research account pain points

Look up company signals and summarize likely business or technical pain points per account for outbound messaging.

For: AEs, SDRs, ABM teams  |  Output: Account research table with outreach angles

For these 100 target accounts, summarize likely business or technical pain points relevant to data infrastructure, GTM operations, or sales productivity. Include company name, domain, pain point summary, and suggested outreach angle.

8 — Run a multi-step GTM workflow

Chain company discovery, signal-based filtering, content enrichment, and contact discovery into a single workflow — the kind of pipeline you would normally build in Clay or n8n, running natively inside Claude.

For: GTM engineers, growth teams, sales leaders  |  Output: Signal-filtered companies with qualified growth contacts

/vpai:vibe-prospecting

Find 500 B2B SaaS companies in the US with 200 to 1,000 employees.
Fetch companies and filter down so that 500 companies remain after applying the event filter. Enrich each company with LinkedIn posts and keep only companies that have the keyword "event" in one of their posts.
For the remaining companies, find the head of growth or a similar senior growth/marketing leader.
Return the results as a CSV with these columns:
name, title, company, linkedin_url, professional_email, company_domain

Using Vibe Prospecting with Claude Cowork and Claude Code

Example: enrich a local CSV with Claude Code

# Prompt Claude Code:
# "Take leads.csv, enrich each row using Vibe Prospecting,
#  add title / email / company domain, and save to leads_enriched.csv"

Output examples

Prospect output

{
  "company_name": "Example Bank",
  "company_domain": "examplebank.com",
  "industry": "Commercial Banking",
  "headcount": "1,001-5,000",
  "revenue_range": "$100M-$500M",
  "contact_name": "Jane Smith",
  "title": "VP Marketing",
  "linkedin_url": "https://www.linkedin.com/in/example",
  "email": "[email protected]",
  "confidence": "high"
}

CRM enrichment output

{
  "input_email": "[email protected]",
  "matched_person_id": "person_123",
  "current_title": "Director of Revenue Operations",
  "current_company": "ExampleCo",
  "company_domain": "exampleco.com",
  "linkedin_url": "https://www.linkedin.com/in/example",
  "work_email": "[email protected]",
  "phone": "+1-555-000-0000",
  "match_confidence": "medium"
}

Company enrichment output

{
  "company_name": "ExampleCo",
  "domain": "exampleco.com",
  "industry": "B2B SaaS",
  "headcount": "201-500",
  "revenue_range": "$10M-$50M",
  "hq_country": "United States",
  "hq_city": "Austin",
  "tech_stack": ["HubSpot", "Gong", "Outreach"],
  "linkedin_url": "https://www.linkedin.com/company/exampleco"
}

Tool reference

Full parameter documentation is in skills/vibe-prospecting/SKILL.md.

Documentation and guides

Security, authentication, and data handling

• Authentication is handled through your Explorium account. No credentials are stored locally by the plugin.
• All data queries are routed through Explorium's API infrastructure. Data is subject to Explorium's data terms and your account permissions.
• Do not include raw API keys or credentials in prompts or exported files.
• For enterprise data handling, compliance, and DPA questions, contact Explorium.

Troubleshooting

Learn more

Vibe Prospecting Plugin is built and maintained by Explorium. It connects Claude Code and Claude Cowork to Explorium's B2B data platform for GTM teams, AI agents, and revenue operations workflows.