Figure Aesthetics Art Studio · публичный навык Open Skill

Figure Aesthetics Art Studio

Figure Aesthetics Art Studio — публичный Open Skill на Digen. Откройте, чтобы увидеть, что создаёт этот процесс.

@luouaua

Custom

1 1 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/nfx44h6f.jpg

# Figure Aesthetics Art Studio

Produce **tasteful artistic figure-study portraits** of **clearly adult fictional characters (age 18 or older)** — elegant composition, refined studio lighting, detailed hair and expression, graceful pose, neutral or abstract background. **Default style: realistic photographic fine-art rendering.** Also supports **anime**, **fantasy**, and **editorial charm/glamour** modes. **Text-to-image** when the user has no upload or taps **direct generate**. **Image-to-image** when they upload a reference for pose, palette, or framing while keeping an **original** character (not a copy of a real person or named IP).

Visual and prompt rules live in `references/figure_study_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 **describe the character**, **pick a style**, 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 now · Describe my character · Pick anime style |
| P-brief | Text too vague (no character cues and no style preference) | Example fantasy elf (`fill_input`) · Direct generate default (`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 source · Direct generate again · Try another style |
| P-done | One portrait ready | Higher quality · Change style to anime · Direct generate new character · Match reference pose (if upload) |

## When to use

- User wants a **figure-study or editorial character portrait** of an **original adult fictional** subject.
- User has **no image** or taps **direct generate** / **generate without upload** — run **text-to-image immediately** with the default brief and **realistic** style in `references/guidance-buttons.md` unless they already named another style or character in the same message.
- User **uploads** a reference — **image-to-image** for pose, lighting, or mood while generating an **original** character per the spec.
- User asks to **retry**, **upgrade quality**, **switch style** (realistic / anime / fantasy / charm), or **adjust** hair, expression, outfit, or background on the last successful image from this skill.

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

## Style modes

Resolve **