In simple English
This tool reads customer reviews from an online store and builds a deep report. It sorts comments into twenty-two categories like price, comfort, and service. It finds what buyers love and what makes them angry. It writes fifteen chapters of insights and draws visual dashboards without needing paid API keys. You run it inside an AI coding assistant and get ready-to-read marketing files.
What it is
A Python-based AI agent skill that processes e-commerce review CSV files and outputs structured markdown reports and styled HTML dashboards. It runs locally using your existing AI coding assistant to handle the heavy analysis work.
What it is good for
Solo e-commerce sellers and marketers who need to study hundreds of Amazon or shop reviews to find product flaws and winning angles without paying for expensive analytics software.
- Runs without any external API keys by using your AI coding assistant.
- Generates six visual dashboard themes for sharing with teams.
- Syncs findings directly to Feishu documents and boards.
- Requires Python 3.10 or higher and a compatible AI coding assistant.
- Feishu sync requires an extra command-line tool installed on your computer.
- Processing hundreds of reviews takes time and consumes your assistant tokens.
manual customer review reading and spreadsheet tallying
Claude Code
- BerriAI/litellm62k stars
Provides a proxy for language model calls, though it focuses on routing rather than review analysis.
- cybertec-postgresql/pg_timetable1.4k stars
A job scheduler for PostgreSQL whose jobs and schedules live in the database itself.
- PrefectHQ/prefect24k stars
Adds scheduling, retries and a run history to Python functions you already have.
git clone https://github.com/buluslan/review-analyzer-skill.git cd review-analyzer-skill pip install -r requirements.txt python3 main.py examples/reviews_sample.csv --max-reviews 200