kol-engager-icp

KOL Engager ICP

Find ICP-fit leads by scraping engagers from KOL posts on LinkedIn. This is the second half of the KOL pipeline — given KOLs (from kol-discovery or manually), it finds their best post, scrapes who engaged, and filters for your ICP.

Core principle: 1 post per KOL. Pick the most relevant, highest-engagement post from the last 30 days. This controls costs while maximizing lead quality.

Phase 0: Intake

Ask the user these questions:

ICP Criteria

1. What does your product/service do?
2. Topic keywords for post relevance filtering (3-5 terms the KOL posts should be about)
3. Target industries/verticals
4. Target job titles/roles (e.g., "VP Operations", "Head of Logistics")
5. Titles to EXCLUDE (e.g., "Software Engineer", "Data Scientist")
6. Competitors to filter out
7. Geographic focus (e.g., "United States")

KOL Input

1. KOL list — LinkedIn profile URLs (from kol-discovery output or manual list)

Save config:

skills/kol-engager-icp/configs/{client-name}.json

Config JSON structure:

{
  "client_name": "example",
  "topic_keywords": ["freight automation", "dispatch operations"],
  "topic_patterns": ["freight.*automat", "dispatch.*oper"],
  "icp_keywords": ["freight", "logistics", "3pl"],
  "target_titles": ["vp operations", "head of logistics", "coo"],
  "exclude_titles": ["software engineer", "data scientist"],
  "tech_vendor_keywords": ["competitor-name", "saas founder"],
  "country_filter": "United States",
  "kol_urls": ["https://www.linkedin.com/in/kol-1/"],
  "days_back": 30,
  "max_posts_per_kol": 20,
  "max_kols": 10,
  "max_enrichment_profiles": 200,
  "mode": "standard"
}

Phase 1: Run the Pipeline

python3 skills/kol-engager-icp/scripts/kol_engager_icp.py \
  --config skills/kol-engager-icp/configs/{client-name}.json \
  [--test] [--probe] [--yes] [--kols "url1,url2"]

Flags:

• --config (required) — path to client config JSON
• --test — limit to 3 KOLs, 50 enrichment profiles
• --probe — test engager scraping with one post URL and exit
• --yes — skip cost confirmation prompts
• --kols — override KOL URLs from config (comma-separated)
• --max-runs — override Apify run limit