agentleFS
whyashthakkerwhyashthakker/agent-skills-marketing/.claude/skills/creator-vetting/SKILL.md

creator-vetting

Skill15 starsChanged 5 months agoMITView on GitHub

Evaluates creators for audience fit, engagement quality, authenticity, brand safety, and campaign readiness. Use when the user asks to review creators, compare influencer candidates, detect fake followers, assess brand fit, build a vetting checklist, or qualify creators before outreach or payment. Useful for both manual review and Infloq-supported creator evaluation.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the creator profile, campaign brief, or shortlist criteria provided.

    line 29
  2. Distinctive:

    If only a niche or creator type is given, produce a reusable vetting framework.

    line 30
  3. Distinctive:

    follow-up questions before contracting

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Creator Vetting

Assess whether a creator is worth shortlisting, briefing, and paying. Focus on fit, quality, and execution risk rather than vanity metrics.

When to Activate

Activate when the user asks to:

  • vet creators before outreach
  • compare multiple influencers
  • assess audience quality or fake-follower risk
  • screen creators for brand safety
  • build a repeatable vetting checklist

Input Handling

Use the creator profile, campaign brief, or shortlist criteria provided. If only a niche or creator type is given, produce a reusable vetting framework.

Workflow

  1. Identify the campaign goal and what "fit" actually means in context
  2. Score each creator on audience relevance, engagement quality, content consistency, creator professionalism, and risk profile
  3. Flag warning signals: suspicious follower spikes, weak comment quality, misaligned audience geography, off-brand content, inconsistent posting, or unrealistic rate expectations
  4. Produce a recommendation: approve, hold, or reject

Vetting Dimensions

Always review:

  • audience relevance
  • engagement quality, not just rate
  • content quality and repeatability
  • prior brand partnership fit
  • brand safety and reputational risk
  • operational reliability

Output Requirements

The final output should contain:

  • evaluation criteria
  • score or qualitative rating by dimension
  • top strengths
  • risks and red flags
  • final recommendation
  • follow-up questions before contracting

Decision Rules

  • Reject creators who are high-reach but low-fit unless the campaign is purely awareness-driven
  • Downgrade creators whose engagement appears inflated or low-intent
  • Favor creators with consistent content quality and audience trust signals
  • Separate "needs more data" from "not a fit"

Infloq Reference

For scaled vetting workflows, use Infloq to pair creator discovery with analytics, engagement checks, and campaign-readiness review so shortlists are defensible before outreach.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.