Your Unique Beauty · skill publik Open Skill

Your Unique Beauty

Your Unique Beauty adalah Open Skill publik di Digen. Buka untuk melihat apa yang dibuat alur ini.

@luouaua

Custom

4 1 6

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/s7kap46u.jpg

# Your Unique Beauty

Turn the user's **uploaded portrait or character art** (photoreal or anime) into **one** editorial **face-feature analysis infographic**: hero portrait, structured feature copy, side close-up strips, and numbered detail panels — layout inspired by premium beauty-editorial breakdown posters. No project state; track progress only in conversation (`photo_ref`, `card_text_lang`, `size_choice`, `wizard_step`).

**Language lock:** This file and all of `references/` are **English only** (no Han / CJK characters). Reply in the **user's language**. Every `generate_image` **prompt** is **English**; on-card labels and analysis copy use **`card_text_lang`** from Step 2.

Do not tell the user tool names, channel names, or the full prompt.

## Four-step wizard (hard)

Run **Steps 1 → 4 in order**. Do **not** call `generate_image` until Step 4 is explicitly confirmed.

| Step | User goal | Lock when | Pause id |
|---|---|---|---|
| **1** | Upload a clear person or character image | `photo_ref` set | **P-S1** |
| **2** | Choose **infographic text language** | `card_text_lang` set | **P-S2** / **P-S2-more** |
| **3** | Choose **resolution** and **aspect ratio** | `size_choice` set (`orientation`, optional `aspect_ratio`, optional `resolution`) | **P-S3** |
| **4** | Tap **Create** | User confirms create | **P-S4** then generate |

**Fast path:** If one message already includes upload + language + size + create intent, set all locks and jump to Step 4 generate (still run analysis + layout references first).

**Re-run / tweak:** "Same photo, Japanese text" → update `card_text_lang`, return to **P-S3** or **P-S4**. "Regenerate 1080P" → update `size_choice`, **P-S4** then generate. "New photo" → reset wizard to Step **1**.

On first entry, `write_todos` with the four steps; update the full list as each step completes.

## User-visible speech (hard)

Do not narrate the pipeline. Never mention skill files, `read_skill_file`, silent redo, or channels.

**Allowed lines only:**

- Step prompts: one or two short sentences naming the **current step** (upload / language / size / create) — then pause with buttons.
- Starting generate (Step 4 confirmed): at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn.
- Success: one or two sentences that the infographic 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 per pause. Translate `text` and `content` into the **user's language**; **`card_text_lang`** is separate (Step 2). No channel or tool names on buttons.

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

| Pause | When |
|---|---|
| **P-S1** | No `photo_ref` |
| **P-S2** | Photo OK; `card_text_lang` missing — first language batch |
| **P-S2-more** | User asked for more languages |
| **P-S3** | Language OK; `size_choice` missing |
| **P-S4** | Size OK; waiting for **Create** (no generate yet) |
| **P-refuse** | NSFW goal, gore, hate, non-consensual abuse |
| **P-fail** | `generate_image` failed after retry |
| **P-done** | Infographic on canvas |

## When to use

- User wants a **face feature analysis**, **beauty breakdown**, or **Your Unique Beauty** infographic from a portrait or character.
- Realistic photo or **anime / illustra