image-refiner

Community

Photoreal product placement in AI scenes.

AuthorDunc4nJ
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Refine base scene images by compositing real product photos into AI-generated scenes, enabling photorealistic product placement for marketing, catalogs, and launches. This skill orchestrates base image input, metadata, S3 asset retrieval, and Gemini-based editing with a built-in human QC gate.

Core Features & Use Cases

  • Automated image refinement: Retrieve a base image and metadata, download product reference photos from S3, and drive Gemini to edit the scene with accurate product placement.
  • Batch and single-image workflows: Supports individual refinements or batch runs with a QC gate between steps.
  • End-to-end provenance: Updates metadata with refined image path, reference assets used, and approval status for auditability.

Quick Start

Provide a base image and its associated metadata then run the image-refiner workflow to output a refined image after QC.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: image-refiner
Download link: https://github.com/Dunc4nJ/agent-skills/archive/main.zip#image-refiner

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.