Amonen O · skill pubblica Open Skill

Amonen O

Amonen O è una Open Skill pubblica su Digen. Aprila per vedere cosa crea questo workflow.

@luouaua

Custom

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/qwb6rpnf.jpg

# Amonen O

Produce **SFW, photorealistic editorial portraits** of **Amonen O** — an **original young adult woman (18+)** with the canonical gentle face in `references/character_spec.md`. Every image must include a full **visual design**: **appearance** (hair, outfit, makeup), **scene**, **action/pose**, and **lighting** from `references/visual_design.md`. Default generation uses **`t2i.hd.gpt`** / **`i2i.hd.gpt`** per `references/generation.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 **describe tweaks**, **pick a look**, 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 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 (studio package) · Cherry blossom scene · Describe full design (`fill_input`) |
| P-brief | Text too vague (no scene or framing preference and no direct-generate tap) | Example café scene (`fill_input`) · Direct generate package A (`send_message`) |
| P-refuse | NSFW goal, sexualized minor, hate target, request to clone a real person or trademarked character | Family-safe direct generate · Upload a different reference |
| P-fail | `generate_image` `success=false` after retry | Regenerate same design · Direct generate new package · Try same scene new pose |
| P-done | One portrait ready | New scene (rotate package) · Softer smile same lighting · Window-light reading scene · Match reference (if upload) |

## When to use

- User wants the **Amonen O** look or a **gentle young adult woman portrait** with the feature set in `references/character_spec.md`.
- User has **no image** or taps **direct generate** / **generate without upload** — run **text-to-image immediately** with the **Direct generate default** in `references/guidance-buttons.md` unless they already gave a different brief in the same message.
- User **uploads** a reference — **image-to-image** for pose, framing, or palette while keeping the **canonical face character** from the spec (original fiction — not a copy of a real person or named IP).
- User asks to **retry**, **upgrade quality**, change **lighting/background/expression/outfit**, or **refine** the last successful image from this skill.

**Do not use:** video; explicit NSFW; requests to depict real people or named franchise characters.

## Visual design (required)

Before **`generate_image`**, `read_skill_file` → **`references/visual_design.md`** and lock **four layers**:

1. **Appearance** — hair ID, wardrobe ID, makeup (catalog table