← 返回 Skills 市场

Ai Product Description From Image

Name: Ai Product Description From Image
Author: loutai0307-prog

作者 loutai0307-prog · GitHub ↗ · v2.0.1 · 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 ai-product-description-from-image

功能描述

Convert local product images (JPG/PNG/WEBP) to descriptions using Grok Vision AI. Requires XAI_API_KEY. Use when generating e-commerce copy from local photo...

使用说明 (SKILL.md)

AI Product Description from Image (Local Files)

Convert local product images to professional descriptions using Grok Vision AI.

What This Skill Owns

Single image description from local file path (JPG/PNG/WEBP)
Batch processing of all images in a folder
Output in 4 styles and 3 languages

What This Skill Does Not Cover

Image URLs (use ai-product-description-generator-from-image)
Non-image files (PDF, DOCX, etc.)
Publishing to Shopify/WooCommerce directly

Commands

describe

Generate description from a single local image file.

XAI_API_KEY=your-key bash scripts/script.sh describe --image ./product.jpg
XAI_API_KEY=your-key bash scripts/script.sh describe --image ./shoe.png --style luxury --lang zh

batch

Process all images in a folder.

XAI_API_KEY=your-key bash scripts/script.sh batch --folder ./product-images
XAI_API_KEY=your-key bash scripts/script.sh batch --folder ./products --style seo

Credentials

Variable	Required	Description
XAI_API_KEY	Yes	Grok API key from console.x.ai

Requirements

python3 (standard library only)
Internet connection (calls api.x.ai)
Local image files: jpg, jpeg, png, webp

Feedback

https://bytesagain.com/feedback/ Powered by BytesAgain | bytesagain.com

安全使用建议

This skill appears to do what it claims, but installing it means local images you pass will be uploaded (as base64 data URLs) to api.x.ai (Grok). Before using: 1) do not send sensitive images (personal data, documents, or anything with private info) without confirming Grok's data retention/privacy policy; strip EXIF/metadata if needed; 2) protect the XAI_API_KEY like any secret (rotate if leaked) and monitor billing/usage; 3) review the script if you want to modify behavior (e.g., remove metadata or change the endpoint) or to run a local/approved vision model instead; 4) test with non-sensitive images first.

功能分析

Type: OpenClaw Skill Name: ai-product-description-from-image Version: 2.0.1 The skill provides functionality to generate product descriptions from local images using the Grok Vision AI API. The implementation in `scripts/script.sh` uses a bash wrapper around a Python script that utilizes standard libraries (`urllib`, `base64`, `json`) to process images and communicate with the official X.AI endpoint (`api.x.ai`). No indicators of data exfiltration, malicious execution, or prompt injection were found.

能力标签

requires-sensitive-credentials

能力评估

✓ Purpose & Capability

Name/description request Grok vision access and the skill only requires an XAI_API_KEY and local image files. The declared requirement (XAI_API_KEY) maps directly to the script's use of api.x.ai. No unrelated credentials or binaries are requested.

ℹ Instruction Scope

Runtime instructions and the included script only read user-supplied image files and a single env var, base64-encode the image into a data URL, and send it to https://api.x.ai/v1/chat/completions. This behavior is expected for the stated purpose but has privacy implications: any image data (and embedded EXIF/metadata) is transmitted to an external service.

✓ Install Mechanism

No install specification; the skill is instruction/script-only and uses only system python3 and shell. Nothing is downloaded or written by an install step.

✓ Credentials

Only a single API key (XAI_API_KEY) is required which is proportionate to the integration. The script does not request other secrets or config paths. Users should, however, be aware that their images are uploaded to the external Grok API and that API keys can be used for billing/requests.

✓ Persistence & Privilege

The skill is not forced always-on, it doesn't modify other skills or system configs, and it does not request persistent platform privileges.

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 ai-product-description-from-image
安装完成后，直接呼叫该 Skill 的名称或使用 /ai-product-description-from-image 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

v2.0.1

Add XAI_API_KEY to frontmatter env block; fix registry metadata

v2.0.0

Rewrite: env var credentials, proper SKILL.md frontmatter, no hardcoded keys

v1.0.2

Add Triggers on, bytesagain brand, fix syntax

v1.0.1

Rewrite: use Grok AI instead of OpenAI, no user API key required

v1.0.0

Initial release

元数据

Slug ai-product-description-from-image

版本 2.0.1

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 5

常见问题