Installation
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 "performance-analyzer" skill by following the instructions at https://skill123.me/install/performance-analyzer.
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/performance-analyzer.sh | bash
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 12 KBAbout this skill
Overview
Use when the user asks to "analyze influencer campaign performance", "compare influencers", or "find what content worked"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math — use roi-calculator. 达人营销效果分析/投放复盘
Source
- Repo: https://github.com/aaron-he-zhu/aaron-marketing-skills
- Path: influencer/report/performance-analyzer
Evaluation
AI-evaluated 2026-09-03: An eight-step dependency-aware analysis with deduplicated attribution buckets, a preregistered measurement protocol before any winner is named, and a worked example plus free YouTube connector. Campaign retro analysis is a real need and it runs on pasted exports, though the Retro Card and tracker-state gating add significant suite machinery; safety is strong with no invented scores or rankings and opaque creator refs throughout.