Amazon Seller Agent Skills

Amazon Seller Agent Skills

Open-source Agent Skills for Amazon sellers: product research, feature validation, listing audits, ads search-term analysis, and CVR diagnosis.

Install command

npx skills add https://github.com/zach22-1999/amazon-skills
Added on Popularity 3

Details

Overview

Amazon Seller Agent Skills is an open-source collection of AI Agent Skills for Amazon sellers. It bundles product research, feature validation, listing audits, ads search-term analysis and CVR diagnosis into composable Skills that run inside an AI agent like Claude.

Key Features

  • Composable Skills: drop individual Skills into an agent workflow without writing code.
  • Listing audits: automated checks against Amazon style guide and keyword coverage.
  • Product research: structured searches and competitor snapshots.
  • Ads search-term analysis: break down Sponsored Products search-term reports into actions.
  • CVR diagnosis: combine traffic and conversion data into root-cause hypotheses.
  • Open-source: fork, customize and extend the Skills for your niche.

Pricing

Open-source and free. You pay only for the AI agent runtime that runs the Skills (e.g. Claude API tokens).

Integrations

  • Claude and other MCP-compatible agents
  • Amazon Selling Partner API for live data
  • CSV/JSON export for spreadsheet workflows

Best For

Technical Amazon sellers who already use AI agents and want repeatable, automatable building blocks instead of one-off prompts.

FAQ

Do I need to know how to code?

No — the Skills are pre-built. You just point your agent at them.

Can I extend it with my own Skills?

Yes — it's open-source, so you can fork and add your own Skills for niche workflows.

How to Use

  1. Use a Skill-compatible agent such as Claude Code, Cursor, or Codex.
  2. Install from the terminal (Node.js required):
npx skills add https://github.com/zach22-1999/amazon-skills

Or paste the install prompt from this tool page into your agent and ask it to install for you. 3. Restart / reload the agent so the new Skill is loaded. 4. Invoke the Skill with its slash commands or by asking the agent to run the workflow described in Overview / Key Features. 5. Review outputs before publishing — treat model-generated copy, images, and data as drafts.