amazon-listing

amazon-listing is a skill for Claude Code from zpoint/vibe-seller. It costs 149 tokens per session (2,829 once invoked), scanned A, original, Apache-2.0.

A tool for creating, editing, linking, and deleting Amazon product listings through spreadsheet uploads. It can handle a product family with a parent listing and colour or size variants in one file.

In plain words
What is it for?
Use it to build variation families, update product details, change parent-child links, remove SKUs, or turn a supplier product link into an Amazon listing.
Why use it?
It avoids editing each Amazon SKU separately and reduces mistakes caused by changing many listing fields by hand.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **PREREQUISITE:** read `../amazon-shared/SKILL.md` for login, Ziniao.

Good fit Use it to build variation families, update product details, change parent-child links, remove SKUs, or turn a supplier product link into an Amazon listing.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/zpoint/vibe-seller
agentmods
npx agentmods add skills/zpoint/vibe-seller/amazon-listing

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for amazon-listing

README.md
[![agentmods](https://agentmods.dev/badge/skills/zpoint/vibe-seller/amazon-listing/github.svg)](https://agentmods.dev/skills/zpoint/vibe-seller/amazon-listing)
Your own site
<a href="https://agentmods.dev/skills/zpoint/vibe-seller/amazon-listing"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/amazon-listing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for amazon-listing

Your own site · 80×15
<a href="https://agentmods.dev/skills/zpoint/vibe-seller/amazon-listing"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/amazon-listing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,829 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00149 $0.02829
Opus 5 $0.00075 $0.01414
Sonnet 5 $0.00030 $0.00566
Haiku 4.5 $0.00015 $0.00283

Measured 10d ago against content hash 7d2929872a88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

amazon-listing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/listing_bulk.py, scripts/ocr_1688.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

app/skills/amazon-listing/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Amazon — Listing CRUD (flat-file upload)

PREREQUISITE: read ../amazon-shared/SKILL.md for login, Ziniao auto-fill / OTP, marketplace TLDs, hamburger navigation, and the capture rule (live data → /tmp/<task>/, never knowledge/).

Amazon's Add Products via Upload takes a category flat-file template — a macro-enabled .xlsm whose Template sheet is a wide table (one column per attribute). One upload creates or edits a whole variation family (a Parent plus N colour/size Children) at once. This is the batch equivalent of the per-SKU web wizard, and the default for anything touching more than one variant.

Two references, load what the task needs:

  • references/template-round-trip.md — the download → inspect → fill → upload → read-feedback loop, the operation column (create/update/partialupdate/delete), and the parent-child cluster. Load for any listing CRUD.
  • references/1688-sourcing.md — turning a supplier link into a filled template: page extraction, local no-GPU OCR of detail images, AI-generated copy, the bilingual review step, and image handling. Load when the task starts from a product link.

Work it like a human: upload → read the report → fix → repeat

The template, its required fields, valid values, and even the upload mechanics change per product type and over time. Do not follow a fixed recipe from memory. Run the loop a human runs:

  1. Download a FRESH template for the exact product type — Amazon's own error messages say "download the latest template". Never reuse a stale one.
  2. inspect it. The field set / required fields / valid values for THIS category are the ground truth, not this doc.
  3. Fill, upload, then download the processing report and run parse-feedback REPORT.xlsm. It reads the summary tables and the per-cell comments (批注) on the report's Template tab — where Amazon writes the precise, field-level verdict per SKU — and prints sku=… field=… : MESSAGE.
  4. For each ERROR line, fix exactly the field it names — set it to a value from the template's own valid set (inspect --field NAME). Do not reinterpret or theorise a root cause; act on the report's words. (If a WARNING names a key defining attribute like material/pattern, fix it too — that's often what unblocks new-ASIN creation.)
  5. Re-upload and repeat until only expected noise remains (see the main-image rule below).
  6. Final verify — the two sources of truth, not the feed count: the downloaded report shows 0 blocking errors, AND the Manage Inventory page shows the family (parent's "Variations (N)", each child a real ASIN — not - — with title / description / bullets).

Read the full file on GitHub · 197 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 197 lines · 149 tokens per session scan A 7d2929872a88

Subscribe to this mod's changes

amazon-listing is a skill published in the GitHub repository zpoint/vibe-seller (66 stars, last pushed yesterday), licensed Apache-2.0. It adds 149 tokens to every session and 2,829 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.