Medical Transformation · Open Skill 公開スキル

Medical Transformation

Medical Transformation は Digen 上の公開 Open Skill です。開くと、このワークフローが何を作るか分かります。

@akjshdk

Custom

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4173183/2026-10-15/yx54q4fx.jpg

# Medical Transformation

Create **one photorealistic portrait** in a **medical / clinical** look: the subject wears **professional medical attire** (scrubs, lab coat, or hospital uniform) and appears in an **authentic hospital environment** (emergency room, corridor, waiting area, or patient room). **Clean clinical lighting** and accurate medical setting details. **Image-to-image** from an upload **fully preserves** the person's **facial features and identity**. **Text-to-image** builds an **original adult fictional clinician** when the user has no image or taps **direct generate**.

Visual lock lives in `references/medical_portrait_spec.md`.

No project state.

**Language lock:** This file and all of `references/` are **English only**. Reply in the **user's language**. Every `generate_image` `prompt` is **English**.

Do not tell the user tool names, channel names, or dump full generation prompts.

## User-visible speech (hard)

**Allowed lines only:**

- Need input: one short note that they may **upload a portrait**, **describe a subject**, pick a **preset direct generate**, or **tap direct generate** — then pause **P-empty** or **P-brief**.
- Starting generate: at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn.
- Success: one or two sentences that the **medical portrait** is ready — no URL, no prompt dump. Pause **P-done**.
- Tool failure: brief honest note. Pause **P-fail**.
- Safety block: one polite refusal. Pause **P-refuse**.

## Pause = clickable buttons (hard)

Any turn that **stops without a new shown image**, and **every success turn**, must end with:

1. One or two short sentences (user language).
2. **`set_guidance`** in the **same turn**, with **at least two** clickable options. **No tool calls after `set_guidance`.**

Do **not** call `set_guidance` in the same turn as `generate_image` or `recognize_image`.

Each button is an object with `text` and `action` (not bare strings):

- **`send_message`**: `content` is the full sentence sent when tapped.
- **`fill_input`**: `content` is starter text the user can edit.

Offer **2–4** options. Localize `text` and `content` to the user's language. No channel or tool names on buttons.

Before every pause turn, `read_skill_file` → `references/guidance-buttons.md`.

| Pause | When | Example intents (localize) |
|---|---|---|
| P-empty | No upload, no usable brief, no direct-generate tap, no last image to refine | Direct generate (ER physician) · Scrubs corridor preset · Lab coat waiting area · Upload portrait |
| P-brief | Wants medical portrait but subject or setting too vague | ER physician preset · Nurse scrubs preset · fill_input custom subject |
| P-refuse | NSFW goal, sexualized minor, hate target, non-consensual humiliation | Family-safe direct generate · Upload a different portrait |
| P-fail | `generate_image` `success=false` after retry | Direct generate again · Regenerate from same upload · Higher quality |
| P-done | One medical portrait ready | Different hospital zone · Lab coat instead of scrubs · Warmer lighting · Square crop · Direct generate new clinician |

## When to use

- User wants a **medical-themed portrait** with **clinical clothing** and **hospital background**, keeping **face identity** when a photo is provided.
- User has **no image** or taps **direct generate** / **generate without upload** — run **T2I immediately** using a preset from `references/guidance-buttons.md` unless they already gave a full brief in the same message.
- User **uploads a portrait or character photo** — **I2I** with face-preserving rule in `medical_portrait_spec.md`.
- User asks to **retry**, **change setting** (ER vs corridor vs waiting room), **change attire** (scrubs vs lab coat), **lighting**, **framing**, or **refine** the last successful image from this skill.

**Do not use:** unrelated non-medical art styles; video; explicit NSFW; gore or graphic surgery imagery.

## Preset examples (T2I — no upload required)

First