Skip to content
SkillModel-led389 tokens in use

Audience Research

Judges whether a creator or brand reaches the right market, from public profile data, TikTok audience demographics, regional signals and comments.

6,856 stars on the repository MIT LicenseScrapeCreators/social-media-research-skills · skills/audience-research
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 Audience Research costs

54tokens idle
389tokens 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
  • Structure22/25
  • Examples6/15
  • 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

Audience Research helps an agent evaluate a creator or social account against a target market. It combines public profile metrics, TikTok audience demographics, regional signals, follower data where available, comments, language and content topics.

The output is a fit report with a High, Medium or Low fit score, a confidence label tied to how strong the public data is, an evidence table and a sponsorship recommendation.

What You Get

  • A fit summary with the target market, a fit score and a confidence level
  • An evidence table listing each signal, what it showed and its source
  • Audience notes on geography, language, niche fit and comment quality
  • A sponsorship recommendation of good fit, maybe or poor fit with the reason

Common Use Cases

  • Checking whether a creator’s audience sits in the market a sponsor wants
  • Comparing audience fit across several creator candidates
  • Looking for US-heavy or country-specific creators in a niche
  • Understanding who appears to engage with an account before a partnership

What Makes It Unique

The skill ties every fit claim to evidence and a confidence label, and tells the agent to warn when a platform does not expose audience data publicly. It also flags a mismatch between a creator’s own location and where the audience appears to be, a gap that follower counts hide.

Under The Hood

The skill is one SKILL.md of instructions with no scripts. The agent calls the ScrapeCreators REST API using the SCRAPECREATORS_API_KEY environment variable, reading TikTok audience and region endpoints, profile and follower endpoints, comments and link-in-bio pages. Its frontmatter allows the shell, file reading and writing, and web fetches, so the agent can run commands, make network calls and write the report 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