My City Giant Screen — Open Skill
My City Giant Screen
My City Giant Screen is a public Open Skill on Digen. Open it to see what this workflow creates.
Custom
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/j5cx3cpp.jpg
# My City Giant Screen Produce **exactly one** shown image in the **My City Giant Screen** look from either: - an **uploaded photo** (one person, **multiple people in one file**, or **product / packshot**) whose content should appear **inside** a giant urban LED billboard at night, or - **two or more separate uploads** in the **same user message** (typically two portraits) with **no real brief** — treat as **implicit intent**: **both people together in one joint portrait on the LED screen** (side-by-side or natural duo framing), **without asking** which file to use, or - **no upload** — user **describes who or what is on the screen**, taps **direct generate**, or asks to **create from text**. The look: a **cinematic night metropolis** (busy square, glass towers, neon signs, wet reflective pavement). A **massive curved or flat LED screen** on a building shows the **portrait or product content** as believable digital signage. In the **lower foreground**, the **same people** (when the subject is people) stand **normal human scale**, **backs to the camera**, on wet pavement **looking up** at the screen — aspirational “see yourself on the billboard” mood. **Colored light from the screen** spills onto them, architecture, and the street. **Low-angle scale** makes the billboard feel monumental. **Hard distinction:** faces and hero portrait live **on the LED only** at billboard scale; ground figures are **small, from behind, never colossal**. This is **not** entity gigantization — **no** building-sized person or product standing in traffic. **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 what goes on the screen**, 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 city giant-screen image 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 screen content · I'll upload a photo | | P-brief | Text too vague (no subject for the screen and no city mood) | Example scene (`fill_input`) · Direct generate default (`send_message`) | | P-refuse | NSFW goal, gore focus, sexualized minor | Family-safe direct generate · Upload a different photo | | P-fail | `generate_image` `success=false` after retry | Regenerate same source · Direct generate again · Upload a differe