# KOL Screener Agent Skill

> Automate KOL screening: clean messy CSV lists from Modash, Heepsy, etc., enrich missing data, calculate health scores, and output a ranked shortlist. Save hours of manual vetting. Start free in seconds.

- Canonical: https://nanoskill.ai/skills/kol-screener-agent-skill
- Markdown: https://nanoskill.ai/skills/kol-screener-agent-skill.md
- Author: jrr996shujin-png
- Published: 2026-10-20T03:30:00.000Z
- Updated: 2026-10-20T09:40:52.644Z
- Language: en
- Source type: github
- Popularity signal: 7

## Sources

- https://github.com/jrr996shujin-png/kol-ops-suite/tree/main/skill-1-kol-screener

## Install

```shell
npx skills add https://github.com/jrr996shujin-png/kol-ops-suite/tree/main/skill-1-kol-screener
```

## About

KOL screening is a critical step in influencer marketing that transforms raw, messy CSV exports from tools like Modash or Heepsy into a vetted, scored shortlist. Whether you're a brand marketer launching a campaign or an agency managing multiple creator rosters, this skill eliminates hours of manual data cleaning, enrichment, and scoring. It automatically turns chaotic spreadsheets into a clear, actionable ranking so you can focus on outreach, not data entry.

The KOL Screener skill goes beyond simple deduplication. It enriches your list by scraping public channel metadata—subscriber counts, engagement rates, recent activity, and even contact emails where available—then applies a multi-factor health scoring algorithm. The scoring weights activity, engagement, view consistency, follower authenticity, and category relevance, giving you a trustworthy 0-100 score per influencer. All results are delivered in a formatted Excel workbook with color-coded sheets for immediate decision-making.

Ideal for campaign managers, talent scouts, and agency ops teams, this skill fits straight into your existing workflow. Upload a spreadsheet from any major KOL discovery tool, and in one step you get a ranked shortlist, a list of flagged risks (like suspected fake followers or dead channels), and a preserved copy of your raw data. After screening, the skill can hand off directly to the next phase, such as automated outreach, making your influencer pipeline seamless from discovery to first contact.

## Key features

- **Automated Health Scoring**: Each KOL receives a 0-100 score based on activity, engagement, view consistency, and follower/view ratio, so you can instantly spot top performers and fraud risks.
- **Field Enrichment from Public Data**: Automatically fills missing data like country, activity metrics, average views, engagement rate, and email by scanning channel pages, reducing manual research.
- **Data Cleaning & Standardization**: Removes duplicates, normalizes follower counts (1.2M → 1,200,000), standardizes platform labels, and flags entries with missing critical info—all with one upload.
- **Formatted Excel Shortlist Report**: Produces a color-coded Excel workbook with three sheets: a scored shortlist sorted by health, a flagged issues list, and the original raw data for reference.

## Use cases

- **Screen KOL Lists for Media Campaigns**: Marketing teams upload raw influencer exports from Modash, Heepsy, or CreatorIQ and receive a clean, ranked shortlist ready for outreach, cutting vetting time by hours.
- **Audit and Clean Existing Influencer Databases**: Agencies use it to periodically review their influencer rosters, spotting inactive accounts, fake followers, and outdated contact info to keep their database healthy.
- **Build Category-Specific KOL Shortlists**: Campaign managers specify a brand category (e.g., beauty, tech), and the tool scores relevance alongside engagement, helping them surface the best-fit influencers for niche campaigns.

## Result preview

See a visual screening report about 8 KOLs ranked by health score, with duplicates removed, gaps flagged, and priority tiers for outreach.

![the demo of kol screener agent skill](https://file.nanoskill.ai/kol-screener-agent-skill-demo-1.png)

![the demo of kol screener agent skill](https://file.nanoskill.ai/kol-screener-agent-skill-demo-2.png)

![the demo of kol screener agent skill](https://file.nanoskill.ai/kol-screener-agent-skill-demo-3.png)

![the demo of kol screener agent skill](https://file.nanoskill.ai/kol-screener-agent-skill-demo-4.png)

## Result walkthrough

### Install

Add the KOL Screener Skill to your AI agent.

![the step of kol screener agent skill](https://file.nanoskill.ai/kol-screener-agent-skill-step-1.png)

### Upload Your KOL List

Give it a messy influencer CSV — the skill removes duplicates, normalizes formats, and fills what it can.

![the step of kol screener agent skill](https://file.nanoskill.ai/kol-screener-agent-skill-step-2.png)

### Get Your Ready-to-Contact List

Receive a scored, ranked shortlist with green/yellow/red tiers and flagged data gaps — skip hours of manual vetting.

![the step of kol screener agent skill](https://file.nanoskill.ai/kol-screener-agent-skill-step-3.png)

## Skill definition

# Skill 1: KOL Screener

Takes a raw, messy CSV export from KOL discovery tools and transforms it into a clean, enriched, scored shortlist ready for outreach.

## When to Use
- User uploads a CSV/Excel of KOL names or channel URLs
- User says "clean up this influencer list" or "screen these KOLs"
- User wants to format or standardize a creator database

## Input
A CSV or Excel file with some combination of: channel names, URLs, follower counts, emails, categories, etc. Expect messy data — inconsistent formats, missing fields, duplicates.

## Process

### Step 1: Data Cleaning
- Remove duplicate entries (match by URL or channel name)
- Standardize URL formats (ensure full URLs, not partial handles)
- Normalize follower/subscriber counts (convert "1.2M" → 1200000)
- Flag rows with critical missing data (no URL = cannot proceed)
- Detect and standardize platform labels (YT, YouTube, youtube → YouTube)

### Step 2: Field Enrichment
For each KOL with a valid channel URL, attempt to gather publicly available data:

| Field | Source | Priority |
|-------|--------|----------|
| Channel Name | From URL/page | Required |
| Platform | From URL pattern | Required |
| Subscriber/Follower Count | Public page | Required |
| Country/Region | Channel info or content language | High |
| Content Category | Inferred from recent video titles | High |
| Avg Views (last 30 videos) | Public video data | High |
| Avg Engagement Rate | (likes+comments)/views × 100% | High |
| Last Upload Date | Most recent video | Medium |
| Total Video Count | Public page | Medium |
| Email (if public) | Channel about page | Medium |

If data cannot be retrieved automatically, mark the cell as `[MANUAL]` in yellow highlight for the user to fill.

### Step 3: Health Scoring
Calculate a preliminary health score (0-100) for each KOL:

| Metric | Weight | Scoring Logic |
|--------|--------|---------------|
| Activity | 20% | Last upload within 7 days = 100, 30 days = 70, 90 days = 30, 90+ days = 0 |
| Engagement Rate | 25% | Platform benchmarks: TikTok >5% = 100, YouTube >3% = 100, IG >2% = 100 |
| View Consistency | 20% | Low std deviation in views = high score (stable performer) |
| Follower/View Ratio | 20% | Views/Followers > 30% = 100, 10-30% = 60, <10% = 20 (fake follower indicator) |
| Content Relevance | 15% | How closely recent content matches the brand's category (user must specify category) |

### Step 4: Output
Generate a formatted Excel file with:
- **Sheet 1: Scored Shortlist** — All KOLs sorted by health score descending, color-coded (green >70, yellow 40-70, red <40)
- **Sheet 2: Flagged Issues** — KOLs with suspected fake followers, inactive channels, or missing critical data
- **Sheet 3: Raw Data** — Original import preserved for reference

## Output Location
Save to: `campaign-workspace/01-screening/screened-shortlist.xlsx`

## Handoff
After screening, ask user:
"Your shortlist is ready with [X] KOLs scored. Want me to proceed to outreach (Skill 2), or do you want to review and filter first?"

## FAQ

### What is KOL screening and why do I need it?

KOL screening is the process of vetting key opinion leaders (influencers) by cleaning their data, filling missing information, and scoring their performance. It helps you quickly separate high-value partners from inactive or fraudulent accounts before you invest in outreach.

### How does this skill clean my influencer list?

It automatically removes duplicates, normalizes follower counts, standardizes URL formats and platform labels, and highlights rows with critical missing data. You just upload a CSV and get a polished spreadsheet.

### What data can be automatically enriched?

For each KOL with a valid public channel URL, the skill attempts to retrieve: channel name, platform, subscriber count, country/region, content category, average views, engagement rate, last upload date, total videos, and email (if publicly available). Unavailable fields are marked for manual entry.

### How is the health score calculated?

The score (0-100) combines five weighted metrics: activity recency (20%), engagement rate vs. platform benchmarks (25%), view consistency (20%), follower/view ratio (20%), and content relevance to your brand category (15%). Weights are based on industry-tested priorities.

### Is this skill free to use?

Yes, the KOL Screener is an open-source skill accessible via npx skills add. There is no paid subscription, and you can run it using your own API keys if data enrichment is needed.

### What output do I get?

You receive an Excel file with three sheets: Scored Shortlist (all KOLs ranked by health, color-coded green-yellow-red), Flagged Issues (suspicious accounts and incomplete records), and Raw Data (your original import preserved).