claude-fba
Your Amazon seller ops team in the terminal — Claude Code skills for store audits, review automation, safe listing edits, and impact tracking via SP-API + He…
Install with your AI
Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.
Install and set up claude-fba (git-clone project) into my current project. Found on https://claudeers.com/claude-fba Repo: https://github.com/EbrahimElbagory/claude-fba Homepage/docs: — Detected install method: git-clone → git clone https://github.com/EbrahimElbagory/claude-fba Category: data. Platforms: cli, api. Read the repo's README for exact setup and env vars, then install it and wire it into my project. Claudeers Health Verdict: active; community-verified: false. Confirm the source before running anything.
git clone https://github.com/EbrahimElbagory/claude-fba
// compatibility
| Platforms | cli, api |
|---|---|
| Operating systems | — |
| AI compatibility | claude |
| License | MIT |
| Pricing | open-source |
| Language | HTML |
claude-fba
Your Amazon seller ops team in the terminal. Claude Code skills + a tiny stdlib-only Python toolkit that turn the Amazon Selling Partner API and the Helium 10 MCP into an audit → fix → measure loop for your own store.
Built by a seller, on a real store, in production. Day one on mine:
- Full-catalog audit (19 ASINs) — listing quality, keyword ranks, BSR trends — in ~25 API calls
- 437 review requests sent via the official Solicitations API (they'd been sitting eligible, unsolicited)
- Found a listing whose bullet points described a different product — converting at 2.7% while its siblings did 10–14%
- 4 listings patched (titles + empty backend keywords) with draft → approval → rollback safety
- Baseline captured + weekly tracker installed, so every change is measurable
🌐 Site: https://ebrahimelbagory.github.io/claude-fba/ · 📖 Setup · Helium 10 · Safety model
How it works
Claude Code (the brain)
├── Helium 10 MCP ──── market layer: keyword volumes, ranks, LQS, CPR, competitor data
├── SP-API (yours) ─── store layer: listings, orders, solicitations, reports, catalog
└── launchd/cron ───── keeps review requests + weekly tracking running without you
Five skills orchestrate it:
| Skill | What it does |
|---|---|
| store-audit | Full checkup of every listing (quality, keywords, rank, reviews, stock) diffed against the last audit |
| review-automation | Sends Amazon's official review request for every eligible order, then daily forever |
| listing-guard | Edits live listing text safely: you approve exact wording, old version saved for one-command undo |
| impact-tracker | Baseline before changes, weekly traffic/conversion/revenue after — proof instead of guessing |
| keyword-research | What competitors rank for that you don't, sorted by how cheap each keyword is to win |
Install
git clone https://github.com/EbrahimElbagory/claude-fba.git
cd claude-fba
mkdir -p .claude && cp -r skills .claude/skills
cp scripts/config.example.env scripts/config.env # fill in your SP-API creds
python3 scripts/sp_api.py # verify auth + detect region
claude
> audit my store
Requirements: Claude Code, Python 3.9+ (stdlib only — zero pip installs), a self-authorized SP-API app (30-min setup guide), and optionally a paid Helium 10 plan for the market-data layer (guide).
Safety
Live store, real money — so: read-only by default, every buyer-visible change goes draft → your approval → execute, every write backed up before it happens and verified after, all through official APIs. Full model: docs/SAFETY.md.
FAQ
Is this against Amazon ToS? No. It's your own store, your own self-authorized SP-API app, and Amazon's official endpoints — including the same review-request mechanism as the Seller Central button. Nothing is scraped.
Do I need Helium 10? Only for the keyword side (volumes, ranks, competitor data — their official MCP, paid plan). Everything else runs on the free SP-API app alone: review automation, listing edits, impact tracking, sales analytics.
What does it cost to run? Claude Code subscription + optionally Helium 10. The scripts themselves are free, stdlib-only, and run on a laptop.
Windows? The scripts and skills work anywhere Python does; the two
automation/ templates are macOS launchd — use Task Scheduler/cron equivalents.
License
MIT — Ebrahim Elbagory
// faq
What is claude-fba?
Your Amazon seller ops team in the terminal — Claude Code skills for store audits, review automation, safe listing edits, and impact tracking via SP-API + Helium 10 MCP. It is open-source on GitHub.
Is claude-fba free to use?
claude-fba is open-source under the MIT license, so it is free to use.
What category does claude-fba belong to?
claude-fba is listed under data in the Claudeers registry of Claude-compatible tools.
// embed badge
[](https://claudeers.com/claude-fba)
// retro hit counter
[](https://claudeers.com/claude-fba)
// reviews
// guestbook
// related in Data & Analytics
🔓Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 P…
🔓Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
🔓Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
🔓CLI tool for configuring and monitoring Claude Code