← Back to list
influencer-discovery ✓ Security reviewed
Use when the user asks to "find influencers", "build an influencer list", or "discover creators i…
⚡ Productivity By aaron-he-zhu Version v1.0.0 Updated 2026-09-03
7.0Overall rating

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "influencer-discovery" skill by following the instructions at https://skill123.me/install/influencer-discovery.
⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/influencer-discovery.sh | bash
📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 19 KB

About this skill

Overview

Use when the user asks to "find influencers", "build an influencer list", or "discover creators in [niche]"; produces a multi-platform candidate pool, per-influencer evidence profiles, authenticity red-flag screening, and a Fit-readiness queue without action ranking. Not for STAR scoring or ranking a known shortlist — use fit-scorer. 达人挖掘/找达人/创作者名单

Source

  • Repo: https://github.com/aaron-he-zhu/aaron-marketing-skills
  • Path: influencer/scout/influencer-discovery

Evaluation

AI-evaluated 2026-09-03: Six templated steps with field-level evidence labels, freshness triage queues, and practical keyless tricks (oEmbed metadata, free-key YouTube metrics with an explicit ToS no-bulk-harvesting boundary). The strictly non-ranked queue output and opaque-ref identity machinery add friction to a routine find-influencers request; it never invents candidates, keeps raw locators transient, and refuses auto-merging identities.

Score breakdown

Quality
7.0
Usability
6.0
Security
8.0
Popularity
7.0