← All runbooks
gooseworks-ai / capabilities-kol-engager-icp

KOL Engager ICP

Find ICP-fit leads from key opinion leader audiences on LinkedIn by selecting one relevant, high-engagement post per KOL, scraping reactors and commenters, filtering by role and ICP signals, enriching the strongest profiles, and exporting classified leads. This runbook keeps cost

agent codexmodel gpt-5.5snapshot python312-uveval programmatic7 stepsv1.0.0

Deploy KOL Engager ICP to your jetty.io

One-click installs this runbook into a collection on your Jetty account. You can run it from the Spot dashboard, schedule it, or pipe inputs in via the API.

Deploy on jetty.io →View source
The shape of the run

7 steps · start to finish.

  1. 1
    Step 1

    Environment Setup

    ▶

    Verify the required secret and create the output directories before collecting inputs.

    test -n "$APIFY_API_TOKEN" || { echo "ERROR: APIFY_API_TOKEN is not set"; exit 1; }
mkdir -p /app/results
mkdir -p skills/kol-engager-icp/configs
mkdir -p skills/kol-engager-icp/output

    Initialize /app/results/validation_report.json with a setup stage. Mark it failed and stop if the Apify token or pipeline script is unavailable.

  2. 2
    Step 2

    Intake

    ▶

    Ask for the ICP criteria and KOL input:

  3. 3
    Step 3

    Probe Engager Scraping

    ▶

    Run a probe before spending enrichment budget.

  4. 4
    Step 4

    Run the Pipeline

    ▶

    Run the pipeline in the selected mode. Start with test mode unless the user has confirmed cost and volume.

  5. 5
    Step 5

    Review Results

    ▶

    Present and record:

  6. 6
    Step 6

    Refine on Quality or Cost (max 3 rounds)

    ▶

    If the result quality is poor or the cost is too high, iterate up to max 3 rounds:

  7. 7
    Step 7

    Final Checklist

    ▶

    Run the final output verification and update `/app/results/validation_report.json`.