I'm Calm, Background's Busy · Open Skill 公開技能
I'm Calm, Background's Busy
I'm Calm, Background's Busy 是 Digen 上的公開 Open Skill。開啟後即可了解此工作流能製作什麼。
Custom
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/8gdta9at.jpg
# I'm Calm, Background's Busy Produce **exactly one** shown image in the **I'm Calm, Background's Busy** look from either: - an **uploaded photo** (person or pet with a **readable face and expression**; **simple** background works best), or - **no upload** — user **describes a scene**, taps **direct generate**, or asks to **create from text**. The joke: **foreground subject stays calm, composed, and structurally the same** (expression, pose, framing) while the **background explodes into harmless, exaggerated visual farce** — slapstick chaos, absurd props, cartoon-level disaster energy — **without** hurting the subject, **without** copying a specific copyrighted meme character, and **without** forcing a new pose or re-staging the body. **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 scene**, 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 calm-vs-chaos 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 a scene · I'll upload a photo | | P-brief | Text too vague (no subject or setting) | Example calm-at-table scene (`fill_input`) · Direct generate default (`send_message`) | | P-refuse | NSFW goal, gore/injury focus, real disaster exploitation, copy meme character ask | 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 calm-vs-chaos result ready | Wilder background chaos · Softer farce · Direct generate new scene · Change to 9:16 vertical | ## When to use - User wants **calm expression + chaotic background** contrast **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** or **pet** with a **clear face** (from photo or description). - Follow-up on **last successful output from this skill**: **regenerate**, **wilder chaos**, **softer farce**, **remove/add headline text**, or **size** change (still **one** image). **Do not use:** copying **This is Fine** dog or othe