Edit user-supplied photos — remove or replace objects and bystanders, swap backgrounds (solid color, transparent-look, scene replacement), retouch skin, adjust color and lighting, convert to anime/comic styles (Ghibli, Pixar, manga, sticker presets), extend or re-crop the canvas, enhance clarity, replace text in images. Use when the goal is to modify one existing photo while preserving everything not asked to change. One main change per generation. Do not use for dressing a person in supplied...
Scanned 9/6/2026
Install to Claude Code
npx -y skills add DeepKolor/deepkolor-agent-skills --skill photo-editing-agent --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Photo Editing Agent?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/deepkolor-photo-editing-agent)More formats (shields.io, HTML) on the badges page.
---
name: photo-editing-agent
description: "Edit user-supplied photos — remove or replace objects and bystanders, swap backgrounds (solid color, transparent-look, scene replacement), retouch skin, adjust color and lighting, convert to anime/comic styles (Ghibli, Pixar, manga, sticker presets), extend or re-crop the canvas, enhance clarity, replace text in images. Use when the goal is to modify one existing photo while preserving everything not asked to change. One main change per generation. Do not use for dressing a person in supplied clothing. Do not use for product or ecommerce selling visuals. Do not use for ID-photo specs or document background recolor. Do not use for repairing damaged or faded old photos. Do not use for new styled portraits from scratch. Do not use for combining multiple photos into one. Do not use for interior staging or room redesign."
homepage: https://deepkolor.ai
author: DeepKolor
license: MIT
tags: [image-generation, photo-editing, retouch]
version: lite
---
# Photo Editing Agent
> **Lite edition** — routing and core rules for agent discovery. Full prompt templates, platform playbooks, and production workflows run on [DeepKolor](https://deepkolor.ai).
Edit one existing photo — remove/replace objects, swap backgrounds, retouch, color grade, style transfer, extend canvas.
## When to use
See `description` in frontmatter — the agent loads it at startup for routing.
## Workflow
- One main change per generation; preserve everything not asked to change.
- Always image-to-image with the source photo in imageUrls.
- Confirm multi-step edit plans before executing.
## Defaults
aspectRatio=auto, 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
- Single-photo edits — not compositing, try-on, ecommerce scenes, ID photos, or interior staging.
## 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.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!