# AI use cases for Sealeap Amazon Skills (xjli360/sealeap-amazon-skills)

Repo: [xjli360/sealeap-amazon-skills](https://github.com/xjli360/sealeap-amazon-skills) | Use cases: 3 | Page: https://dedupedai.com/use-cases/xjli360-sealeap-amazon-skills/

A GitHub repo of reusable Agent Skills, written in Chinese and drawn from public sources, for Amazon product research, listings, advertising, inventory, and operations.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Diagnose ACOS problems in an Amazon ad account: https://dedupedai.com/use-cases/xjli360-sealeap-amazon-skills/diagnose-acos-for-amazon-ads/
- Review and revise an Amazon listing with the listing optimizer: https://dedupedai.com/use-cases/xjli360-sealeap-amazon-skills/review-listing-with-listing-optimizer/
- Screen a product idea with the Douyin selection Skills: https://dedupedai.com/use-cases/xjli360-sealeap-amazon-skills/research-product-ideas-from-douyin-skills/

## How to diagnose ACOS problems in an Amazon ad account with Sealeap Amazon Skills

Repo: [xjli360/sealeap-amazon-skills](https://github.com/xjli360/sealeap-amazon-skills) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Run the ACOS diagnostics Skill to find whether ACOS comes from clicks, conversion, traffic mix, or profit.

**Who it is for:** An Amazon advertiser whose ACOS rose and who needs to know which part of the ad funnel to check first.

**The problem:** High ACOS has several possible causes, and it is slow to check each one by hand.

**The outcome:** A diagnosis that separates click cost, conversion, traffic structure, and profit structure, with listed data gaps and optimization options to verify.

### Steps

1. Run `git clone https://github.com/xjli360/sealeap-amazon-skills.git`
2. Run `cd sealeap-amazon-skills`
3. Open amazon-skills/amazon-official/sealeap-amazon-acos-diagnostics/ and read its SKILL.md
4. Copy that Skill folder into your agent's Skills directory, keeping its references/, agents/, and scripts/ folders
5. Give the agent the marketplace, the time range, and the goal, then ask it to list the data it needs first

### Prompt to paste into your agent

```text
Using the sealeap-amazon-skills repo, run sealeap-amazon-acos-diagnostics for <marketplace> over <time range>, with the goal of finding whether ACOS comes from click cost, conversion, traffic structure, or profit structure. Expect a list of required data, a diagnosis, the evidence gaps, and verifiable optimization options. Check that every conclusion names the data it used and marks missing data as unknown.
```

### Caveat

The README says course examples and past experience must be rechecked against the current account, marketplace, and official Amazon rules before acting on them.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xjli360-sealeap-amazon-skills/diagnose-acos-for-amazon-ads/

## How to review and revise an Amazon listing with the listing optimizer with Sealeap Amazon Skills

Repo: [xjli360/sealeap-amazon-skills](https://github.com/xjli360/sealeap-amazon-skills) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Use the Listing optimizer Skill to get a revised listing draft and a list of claims to verify.

**Who it is for:** A seller or brand team with a weak or outdated product listing that needs a structured review before changes go live.

**The problem:** Listing edits are often made by feel, without a clear checklist or a record of what was changed and why.

**The outcome:** A revised listing draft, a list of changes with reasons, and the claims that still need checking against official rules.

### Steps

1. Run `git clone https://github.com/xjli360/sealeap-amazon-skills.git`
2. Run `cd sealeap-amazon-skills`
3. Open amazon-skills/amazon-official/sealeap-amazon-listing-optimizer/ and read its SKILL.md
4. Copy the folder into your agent's Skills directory
5. Paste the current listing text and the target market, then ask the agent to flag any claim it cannot verify

### Prompt to paste into your agent

```text
Using the sealeap-amazon-skills repo, run sealeap-amazon-listing-optimizer on the current listing for <product or listing name> in <marketplace>. Expect a revised draft, a change log with reasons, and a list of claims needing verification. Confirm that each change is tied to a stated reason and that no claim is presented as verified without a source.
```

### Caveat

The README says the Skill content is a distillation of course and public material, so any revised listing needs review against Amazon's current listing rules and your account before publishing.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xjli360-sealeap-amazon-skills/review-listing-with-listing-optimizer/

## How to screen a product idea with the Douyin selection Skills with Sealeap Amazon Skills

Repo: [xjli360/sealeap-amazon-skills](https://github.com/xjli360/sealeap-amazon-skills) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Load the Douyin public-knowledge Skills to check a product idea before buying inventory.

**Who it is for:** A seller with a product idea who wants a structured selection check before committing money to stock.

**The problem:** Product selection often depends on scattered tips with no clear decision inputs or steps.

**The outcome:** A selection workflow with input checklist, decision basis, and steps, applied to one product idea, with missing data marked.

### Steps

1. Run `git clone https://github.com/xjli360/sealeap-amazon-skills.git`
2. Run `cd sealeap-amazon-skills`
3. Open amazon-skills/douyin/ and pick a selection or market research Skill from the catalog
4. Copy that Skill folder into your agent's Skills directory
5. Give the agent the product idea and the target marketplace, and ask for the input checklist first

### Prompt to paste into your agent

```text
Using the sealeap-amazon-skills repo, run a selection Skill from amazon-skills/douyin/ on the product idea <product idea> for <marketplace>. Expect an input checklist, the decision basis, a step-by-step screen, and a list of unknown data. Check that the agent marks every missing number as unknown rather than estimating it as fact.
```

### Caveat

The Douyin material was distilled from public creator sharing and has no creator identities, so the agent cannot check who said what, and results should be tested against current marketplace data.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xjli360-sealeap-amazon-skills/research-product-ideas-from-douyin-skills/