Create professional portrait photography — realistic, film, Korean, Japanese, Hong Kong retro, new Chinese style, black-and-white, and magazine/business headshots — plus identity-preserving partial restyling of user photos: hairstyle, hair color, beard, makeup, light facial retouch. Use when the deliverable is a styled portrait of a person (a new shoot, or an identity-preserving tweak of a supplied photo) with no product-selling or document-spec intent. Parses the request, completes missing d...
Scanned 9/6/2026
Install to Claude Code
npx -y skills add DeepKolor/deepkolor-agent-skills --skill portrait-photo-agent --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Portrait Photo Agent?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/deepkolor-portrait-photo-agent)More formats (shields.io, HTML) on the badges page.
---
name: portrait-photo-agent
description: "Create professional portrait photography — realistic, film, Korean, Japanese, Hong Kong retro, new Chinese style, black-and-white, and magazine/business headshots — plus identity-preserving partial restyling of user photos: hairstyle, hair color, beard, makeup, light facial retouch. Use when the deliverable is a styled portrait of a person (a new shoot, or an identity-preserving tweak of a supplied photo) with no product-selling or document-spec intent. Parses the request, completes missing details, assembles a layered prompt, and generates the image. Do not use for general object removal or background swaps. Do not use for ID photos or document-spec photos. Do not use for virtual apparel try-on. Do not use for product-selling visuals with a model. Do not use for posters or covers."
homepage: https://deepkolor.ai
author: DeepKolor
license: MIT
tags: [image-generation, portrait, photography]
version: lite
---
# Portrait Photo Agent
> **Lite edition** — routing and core rules for agent discovery. Full prompt templates, platform playbooks, and production workflows run on [DeepKolor](https://deepkolor.ai).
Styled portrait photography — editorial, cinematic, fashion, or casual — from text or reference portraits.
## When to use
See `description` in frontmatter — the agent loads it at startup for routing.
## Workflow
- Lock identity when a reference portrait is supplied (image-to-image, aspectRatio auto).
- Specify lighting, lens feel, wardrobe, and background mood in the prompt.
- One portrait by default.
## 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
- Styled portraits — not ID/document photos or old-photo restoration.
- Not for ecommerce product shots or ad banners.
## 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!