Liquid Chrome Avatar · skill pública Open Skill
Liquid Chrome Avatar
Liquid Chrome Avatar é uma Open Skill pública no Digen. Abra para ver o que este fluxo cria.
Custom
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/s3tdma8d.jpg
# Liquid Chrome Avatar Produce **exactly one** shown image in the **Liquid Chrome Avatar** look from either: - an **uploaded photo** of a **person**, **pet**, or **object** with **clear outlines and readable silhouettes**, or - **no upload** — user **describes a subject**, taps **direct generate**, or asks to **create from text**. The look: the subject reads as a **single cohesive liquid-chrome / mirror-polished silver sculpture** — molten mercury poured into the **exact pose and proportions** of the source. **Facial landmarks, fur markings, product geometry, and clothing fold lines** remain **recognizable as embossed chrome topography**, not replaced by armor panels or a different outfit. **Environment reflections** streak across the metal; highlights are bright, shadows deep. This is **material transformation**, **not** mecha suit, **not** robot replacement, **not** a normal photo with a silver filter only. **Fixed play:** each user request yields **one** new shown result. No multi-panel batches. No project state. **Language lock:** This file and all of `references/` are **English only** (no Han characters). Reply in the **user's language**. Every `generate_image` `prompt` is **English**. Do not tell the user tool names, channel names, or the full prompt. ## User-visible speech (hard) Do not narrate the pipeline. Never mention skill files, `read_skill_file`, silent redo, or channels. **Allowed lines only:** - Need input: one short note that they may **upload**, **describe a subject**, 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 liquid chrome avatar 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. Translate `text` and `content` into 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 success to refine | Direct generate now · Describe a subject · I'll upload a photo | | P-brief | Text too vague (no subject or setting) | Example scene (`fill_input`) · Direct generate default scene (`send_message`) | | P-refuse | NSFW goal, gore focus, sexualized minor | Family-safe direct generate · Upload a wholesome photo | | P-fail | `generate_image` `success=false` after retry | Regenerate same source · Direct generate again · Upload a different photo | | P-done | One chrome result ready | Stronger mirror reflections · Sharper face fold detail · Direct generate new subject · Change to 9:16 vertical | ## When to use - User wants **liquid chrome** / **chrome avatar** / **silver sculpture portrait** **with or without** an upload. - User taps **direct generate**, **generate now**, or similar — **run text-to-image immediately** with the default scene in `references/guidance-buttons.md` unless they already gave a different brief in the same message. - Subject is a **person**, **pet**, or **object** (from photo or description). - Follow-up on **last successful output from this skill**: **regenerate**, **stro