skills.rest
gooseworks-ai
gooseworks-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

customer-discovery

Identify customers of a target company from public data sources and output a deduplicated report with confidence scores and CSV.

1.1k|200|Updated Mar 2, 2026
Search Tags:#research#deduplication#web-scraping#competitive-intelligence#public-data#customer-discovery#confidence-scores
One-click install
npx skills add https://github.com/gooseworks-ai/goose-skills --skill customer-discovery-gooseworks-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: customer-discovery
Source: https://github.com/gooseworks-ai/goose-skills/tree/main/skills/capabilities/customer-discovery
Command: npx skills add https://github.com/gooseworks-ai/goose-skills --skill customer-discovery-gooseworks-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

Find all customers of a company by scanning multiple public data sources. Produces a deduplicated report with confidence scoring.

Core Features & Use Cases

  • Scans multiple public data sources (website logos, case studies, press, social posts, job postings) to identify customers.
  • Deduplicates results and assigns confidence scores.
  • Outputs a structured report with evidence URLs and sources, and supports different depth tiers (quick/standard/deep).

Quick Start

Enter a company name to generate a deduplicated customer report with confidence scores.

Frequently Asked Questions about customer-discovery

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find a company's customers from public data sources?▼

Customer discovery maps a target company's customers by scanning websites, case studies, press, social posts, and job postings to produce a deduplicated report with confidence scores and evidence URLs.

What is the best way to deduplicate customer intelligence gathered from web scraping?▼

Deduplicating customer intelligence is handled automatically by aggregating public data sources, cross-referencing mentions, and outputting a clean structured report and CSV with assigned confidence scores.

Can I control the depth of competitive intelligence research for customer discovery?▼

Yes, customer discovery supports quick, standard, and deep depth modes to control the breadth of scanning across public data sources based on your competitive intelligence research needs.

Do I need to install external libraries to run scripts for public data customer discovery?▼

You only need the requests library installed to run the scripts that execute customer discovery, fetch public data, and generate the final structured report.

What sources are scanned to identify customers during competitive intelligence gathering?▼

Competitive intelligence gathering scans website logos, case studies, press releases, social media posts, and job postings to identify customers and aggregate evidence URLs into a structured report.

How are confidence scores calculated for discovered customer lists?▼

Confidence scores are assigned to each discovered customer during the deduplication process, reflecting the reliability of aggregated public data sources and evidence URLs before outputting the structured report and CSV.

Related Skills

Explore More Data & Analytics Skills→
nicoarbelaeznicoarbelaez

python-executor

Execute Python code in a sandboxed environment with pre-installed libraries.

Community
Intermediate
hoanghn61hoanghn61

Evidence Formatter Skill

Format correlated technology evidence into structured, citation-ready documentation.

Community
Intermediate
name-iffatname-iffat

competitor-profiling

Scrape competitor websites and analyze SEO metrics to generate structured profiles.

Community
Advanced
AvihusittonAvihusitton

customer-research

Extract customer insights from research assets and public online sources.

Community
Advanced