Skip to content
SkillModel-led416 tokens in use

Influencer Prospecting

Finds creators and influencers in a niche from public social data and scores each prospect on six factors, with a CSV export for outreach.

6,856 stars on the repository MIT LicenseScrapeCreators/social-media-research-skills · skills/influencer-prospecting
npx skills add ScrapeCreators/social-media-research-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Influencer Prospecting costs

53tokens idle
416tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldeclarednetworkdeclaredwrites filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter15/15
  • Structure12/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity24
  • Maintenance8
  • Community40
  • Maturity24
  • Momentum40

Influencer Prospecting helps an agent build prospect lists for sponsorships, UGC, affiliate programs and product seeding. It searches creators on TikTok, Instagram and YouTube, checks link-in-bio pages and shop showcases, and looks at recent views and audience data.

Each prospect is scored from 1 to 5 on niche fit, audience fit, reach, engagement quality, brand safety and contactability. The output is a table, best fits, outreach angles and a CSV.

What You Get

  • A prospect table with platform, followers, recent views, fit score, contact path and notes
  • A short list of best fits and outreach angles
  • A CSV block with creator, platform, profile URL, followers, recent views, fit score, contact path and notes
  • Scores on niche fit, audience fit, reach, engagement quality, brand safety and contactability

Common Use Cases

  • Building a UGC or affiliate creator list for a product
  • Finding micro-influencers with strong engagement in a niche
  • Identifying creators who already talk about a product category
  • Exporting a prospect CSV for an outreach sequence

What Makes It Unique

The skill scores contactability and brand safety next to reach, and it warns against treating a large follower count as good fit. It limits contact data to public links, and it tells the agent to state uncertainty when a profile exposes little public data.

Under The Hood

The skill is one SKILL.md of instructions with no scripts. The agent calls the ScrapeCreators REST API with the SCRAPECREATORS_API_KEY environment variable to search users, read profiles and posts, and open link-in-bio services such as Linktree, plus Amazon Shop and TikTok Shop showcases. Its frontmatter allows the shell, file reading and writing, and web fetches, so the agent can run commands, make network calls and write the prospect list to a file.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers