← 返回 Skills 市场

Amazon Listing Judge

Name: Amazon Listing Judge
Author: linbeihanda

作者 Handa · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install amazon-listing-judge

功能描述

Grade Amazon product listing quality. Input an ASIN, get a 0-100 score with dimension breakdown (title, bullets, rating, reviews, sales velocity, BSR, badges...

使用说明 (SKILL.md)

amazon-listing-judge

Score any Amazon product listing on a 0–100 scale across 7 dimensions. Returns a grade card with per-dimension scores and actionable improvement suggestions.

Setup

This skill requires a CLAW_KEY — purchase one at claw-school.com.

Create a .env file in the skill root directory (same level as this SKILL.md):

CLAW_KEY=CLAW-XXXX-XXXX-XXXX-XXXX
CLAW_API_BASE=\x3Cprovided-with-your-key>

No CLAW_KEY yet? Visit claw-school.com to get one. Each key is tied to one agent and does not expire.

Grade a listing

uv run \x3Cskill-dir>/scripts/grade.py \x3CASIN>

Example:

uv run \x3Cskill-dir>/scripts/grade.py B088FLY7S8

Scoring dimensions (100 pts total)

Dimension	Max	Logic
Title length	20	100–200 chars = 20; 50–100 or 200–250 = 12; else = 5
Bullet points	20	≥5 = 20; 3–4 = 14; 1–2 = 7; 0 = 0
Star rating	20	≥4.5 = 20; ≥4.0 = 14; ≥3.5 = 8; \x3C3.5 = 3
Review count	15	≥10K = 15; ≥1K = 12; ≥100 = 7; \x3C100 = 3
Sales velocity	15	"bought in past month" present = 15; absent = 0
BSR	10	Any BSR present = 10; absent = 0
Badges	10	Amazon's Choice + Best Seller = 10; either = 7; none = 0

Grade scale

Score	Grade
85–100	A — Excellent
70–84	B — Good
55–69	C — Average
40–54	D — Needs Work
0–39	F — Poor

Output format

{
  "asin": "B088FLY7S8",
  "title": "12 Pack Small American Flags...",
  "total_score": 82,
  "grade": "B (Good)",
  "breakdown": {
    "title": 12,
    "bullets": 20,
    "rating": 20,
    "reviews": 7,
    "sales_velocity": 15,
    "bsr": 10,
    "badges": 10
  },
  "suggestions": [
    "Title is 45 chars — optimal is 100-200 chars"
  ]
}

Interpreting results

Present the results as a structured report. Call out:

Total score and grade label
Strongest dimensions (highest scores)
Weakest dimensions with the suggestions
Overall priority action (the suggestion that would give the biggest score boost)

安全使用建议

Install only if you trust claw-school.com and the CLAW_API_BASE value provided with the key. Use an HTTPS API base, avoid sharing the .env file, and understand that each run sends your CLAW_KEY and the Amazon product URL to that configured service.

能力评估

✓ Purpose & Capability

The script's behavior matches the stated purpose: it takes an ASIN, requests Amazon product data through a configured API, then computes a local 0-100 listing score.

ℹ Instruction Scope

The documentation discloses the required CLAW_KEY and CLAW_API_BASE, but it could be clearer that the ASIN-derived Amazon URL and key are sent to that configured service.

✓ Install Mechanism

No package install hook or automatic setup was found; execution is user-invoked through uv with a single httpx dependency.

ℹ Credentials

Network access and an API credential are proportionate for outsourced Amazon scraping, but the endpoint is fully controlled by CLAW_API_BASE and is not allowlisted or scheme-validated.

✓ Persistence & Privilege

The skill only reads a local .env file for configuration and does not install persistence, request elevated privileges, modify user data, or spawn background workers.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install amazon-listing-judge
安装完成后，直接呼叫该 Skill 的名称或使用 /amazon-listing-judge 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release. Grades Amazon product listings 0-100 across 7 dimensions. Requires CLAW_KEY from claw-school.com.

元数据

Slug amazon-listing-judge

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题