Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →gooseworks-ai/kol-engager-icp
Find ICP-fit leads from KOL audiences on LinkedIn. Given a list of KOLs, scrapes their most relevant high-engagement post from the last 30 days, extracts engagers (reactors + commenters), pre-filters by position, enriches top profiles, and ICP-classifies. Cost-controlled: 1 post per KOL.
Passed 17 of 22 test cases with the skill, and 6 of 22 without it.
and 11 more in the full report
12 fixed6 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
When scanning for recent content published by a LinkedIn thought leader in Step 1, what is the default lookback period in days and maximum posts scanned per profile?
| Checked | Without skill | With skill |
|---|---|---|
| Sets lookback window to 30 days. | Passed | Passed |
| Scans a maximum of 20 posts per KOL. | Missed | Passed |
The instructions your model reads when the skill loads.
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.
Ask the user these questions:
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",
test cases passed, vs 6 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.