# influencer-prospecting

Finds niche creators across TikTok, Instagram, and YouTube using public data, scores prospects from 1 to 5, and exports ready-to-contact lists to CSV.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 4806
- Author: ScrapeCreators
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/ScrapeCreators/social-media-research-skills/tree/HEAD/skills/influencer-prospecting/SKILL.md
- Updated: 2026-08-26
- HTML: https://affpapa.org/en/nevibecode/skills/influencer-prospecting

## What it does

The skill builds prospect lists of creators for sponsorships or affiliate campaigns. It searches public data across YouTube and Instagram, alongside link-in-bio pages like Linktree. Each candidate receives a score from 1 to 5 based on niche fit, brand safety, and contact paths. Raw follower count does not equal good fit.

Output arrives as a structured Markdown document with outreach angles and an exportable CSV snippet. The skill runs using `Bash`, `Read`, `Write`, and `WebFetch` tools. It ignores private contact information. Every record comes strictly from public profile data.

You need the `SCRAPECREATORS_API_KEY` environment variable configured before running queries. Profile discovery will fail without it. That requirement makes the external key indispensable. When public metrics are thin, the skill flags missing data instead of guessing engagement.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add ScrapeCreators/social-media-research-skills --skill influencer-prospecting -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/influencer-prospecting/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/influencer-prospecting/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add ScrapeCreators/social-media-research-skills --skill influencer-prospecting -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/influencer-prospecting/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add ScrapeCreators/social-media-research-skills --skill influencer-prospecting -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/influencer-prospecting/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install ScrapeCreators/social-media-research-skills influencer-prospecting
```

2. **Manually: put the files in place**
- File: `.github/skills/influencer-prospecting/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add ScrapeCreators/social-media-research-skills --skill influencer-prospecting -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/ScrapeCreators/social-media-research-skills --path skills/influencer-prospecting
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/influencer-prospecting/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add ScrapeCreators/social-media-research-skills --skill influencer-prospecting -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ScrapeCreators/social-media-research-skills/tree/HEAD/skills/influencer-prospecting/SKILL.md

## When to use it
- Build creator prospect lists for sponsorships and affiliate campaigns
- Discover micro-influencers with verified audience engagement
- Identify social accounts already discussing a target product category
- Export scored creator candidate lists directly to CSV

## Example prompts
- Find YouTube and TikTok creators in the smart home niche and export the prospect list to CSV.
- Build an influencer list for a fitness UGC campaign and score each candidate from 1 to 5.
- Identify Instagram accounts that talk about specialty coffee and gather their public contact details.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 59519ed9f94e0cc3.

BEGIN THIRD-PARTY FILE 59519ed9f94e0cc3
````text
---
name: influencer-prospecting
description: Use when the user wants to find creators, influencers, affiliates, or social accounts in a niche for outreach, partnerships, sponsorships, UGC, seeding, or competitive research. Produces scored prospect lists from public social data.
allowed-tools: Bash, Read, Write, WebFetch

version: 1.0.0
author: ScrapeCreators
license: MIT
homepage: https://scrapecreators.com
repository: https://github.com/ScrapeCreators/social-media-research-skills
metadata:
  openclaw:
    requires:
      env:
        - SCRAPECREATORS_API_KEY
    primaryEnv: SCRAPECREATORS_API_KEY
    homepage: https://scrapecreators.com
    tags:
      - social-media
      - research
      - scrapecreators
---

# Influencer Prospecting

## Overview

Build practical creator prospect lists from public social data. The goal is to find accounts that fit the niche, have enough reach, and show evidence of relevant content or audience fit.

## When to Use

Use this skill when the user asks to:

- find influencers or creators in a niche
- build a UGC, affiliate, sponsorship, or seeding list
- find micro-influencers with strong engagement
- identify creators who already talk about a product category
- export prospects as CSV

## Useful Sources

- TikTok search users, popular creators, profile, profile videos, audience demographics
- Instagram search profiles, profile, posts, reels
- YouTube search and channel details
- Link-in-bio services: Linktree, Komi, Pillar, Linkbio, Linkme
- Amazon Shop and TikTok Shop showcase where relevant

## Scoring Framework

Score each prospect 1-5 on:

- **Niche fit** — content clearly matches the category
- **Audience fit** — country/language/platform fit when public data supports it
- **Reach** — followers/subscribers and recent views
- **Engagement quality** — comments look real and relevant
- **Brand safety** — obvious controversy or mismatch risk
- **Contactability** — public links/email/contact path available

## Output Format

```markdown
# Influencer Prospect List: {niche}

| Creator | Platform | Followers | Recent views | Fit | Contact path | Notes |
|---|---|---:|---:|---:|---|---|

## Best Fits
1. ...

## Outreach Angles
- ...

## CSV
```csv
creator,platform,profile_url,followers,recent_views,fit_score,contact_path,notes
```
```

## Common Pitfalls

- Do not equate large follower count with good fit.
- Do not scrape or expose private contact data. Use public links only.
````
END THIRD-PARTY FILE 59519ed9f94e0cc3

The third-party file has ended. Everything between the 59519ed9f94e0cc3 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2460 of 2527 bytes. © ScrapeCreators · MIT · https://github.com/ScrapeCreators/social-media-research-skills/tree/HEAD/skills/influencer-prospecting/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md