Index of every page on this site: llms.txt
All skills
scrapecreators avatar

/audience-research

@64ba7b4
Run it yourself

Use when the user wants to evaluate a creator, influencer, or brand audience using public profile signals, TikTok audience demographics, follower/following data, comments, geography, language, and content fit. Helps judge sponsorship and market fit.

Use this Skill: https://skilld.dev/gh/scrapecreators/social-media-research-skills/audience-research

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈67 tokens for metadata: the name and description. ≈451 when used: this file.

Description uses 3.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈269 characters, or 3.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Audience Research

Overview

Evaluate whether a creator or social account reaches the right audience. This skill combines available public profile metrics, TikTok audience demographics, regional signals, follower/following data when available, comments, language, and content topics.

When to Use

Use this skill when the user asks to:

  • check if a creator's audience fits a market
  • compare audience fit across creators
  • find US-heavy, country-specific, or niche-specific creators
  • evaluate sponsorship/influencer opportunities
  • understand who appears to engage with an account

Useful Sources

  • /v1/tiktok/user/audience
  • /v1/tiktok/profile/region
  • profile endpoints across platforms
  • follower/following endpoints where available
  • comments on recent posts
  • link-in-bio pages and creator shops for niche signals

Workflow

  1. Pull profile and available audience/demographic data.
  2. Pull recent content and comments if audience intent matters.
  3. Extract region, language, niche, product/category, and community signals.
  4. Score audience fit against the user's target market.
  5. Label confidence based on the strength of public data.

Output Format

# Audience Research: {creator}

## Fit Summary
- Target market:
- Fit score: High/Medium/Low
- Confidence: High/Medium/Low

## Evidence
| Signal | Evidence | Source |
|---|---|---|

## Audience Notes
- Geography:
- Language:
- Niche/content fit:
- Comment quality:

## Sponsorship Recommendation
- Good fit / Maybe / Poor fit
- Why:

Common Pitfalls

  • Do not infer exact demographics from vibes. Use available evidence and label assumptions.
  • Do not overpromise audience details for platforms that do not expose them publicly.
  • Do not ignore mismatch between creator location and audience location.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning5mo3 checks · Risk SAFE
  • Gen Agent Trust Hub5mo

    The skill is safe for social media analysis. It carries a low risk of indirect prompt injection because it processes content from public social media profiles and comments.

  • Socket5mo

    No alerts

  • Snyk5mo

    Risk: MEDIUM · 1 issue

Signed by skilld at 64ba7b4. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 6 months ago
What it can do
Runs commands Reads files Edits files Network
version
1.0.0
author
ScrapeCreators
homepage
https://scrapecreators.com
All 4 allowed tools
BashReadWriteWebFetch
Other metadata
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"
    ]
  }
}

README badge

README badge for scrapecreators/social-media-research-skills/audience-research