Photo Composite Agent
ASecurityComposite multiple user-supplied photos into one coherent image — put a person or object from photo A into photo B, build group photos from separate portraits, blend a product into a real scene, or fuse several reference images. Use when at least two supplied source images must merge into one with strict consistency across scale, occlusion, perspective, contact shadows, and light/color. Do not use for single-photo edits (removal, retouch, background swap on one image). Do not use for dressing...
- 2 stars
- 0 votes
- 0 copies
- 3 views
- Added September 6, 2026
Security analysis
100/100Pro scans all 2 files and shows the line behind each finding
npx -y skills add DeepKolor/deepkolor-agent-skills --skill photo-composite-agent --agent claude-codeAre you the author of Photo Composite Agent?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/deepkolor-photo-composite-agent)---
name: photo-composite-agent
description: "Composite multiple user-supplied photos into one coherent image — put a person or object from photo A into photo B, build group photos from separate portraits, blend a product into a real scene, or fuse several reference images. Use when at least two supplied source images must merge into one with strict consistency across scale, occlusion, perspective, contact shadows, and light/color. Do not use for single-photo edits (removal, retouch, background swap on one image). Do not use for dressing a person in supplied clothing. Do not use for ecommerce product scene visuals. Do not use for furniture or room staging."
homepage: https://deepkolor.ai
author: DeepKolor
license: MIT
tags: [image-generation, composite, photography]
version: lite
---
# Photo Composite Agent
> **Lite edition** — routing and core rules for agent discovery. Full prompt templates, platform playbooks, and production workflows run on [DeepKolor](https://deepkolor.ai).
Merge two or more photos — person into scene, group portraits, product in environment, multi-reference fusion.
## When to use
See `description` in frontmatter — the agent loads it at startup for routing.
## Workflow
- Assign roles to each reference (base, insert, product, person).
- Match scale, perspective, lighting, shadows, and occlusion across sources.
- Order imageUrls: base image first, then inserts.
## Defaults
resolution=1K
## Tool: `create_image_task`
```ts
{
prompt: string,
scene: "text-to-image" | "image-to-image",
aspectRatio?: string,
imageUrls?: string[],
resolution?: "1K"
}
```
Available when your agent runtime exposes DeepKolor generation tools. Otherwise use this skill as a prompt-engineering guide and adapt tool names to your stack.
## Boundaries
- Multi-source compositing — not single-photo edits, try-on, or ecommerce pack shots.
## Output
After generation, reply briefly: what was created, key parameters, and one useful next step. Return a full prompt only when the user explicitly asks.
## Full version
Production-grade references (SOPs, templates, platform rules) ship inside [DeepKolor](https://deepkolor.ai) — not in this public lite package.
Files in this skill
- .claude-plugin/plugin.json
- SKILL.md
Attribution
Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.