Colossal Animal Landmark Hug · skill pública Open Skill
Colossal Animal Landmark Hug
Colossal Animal Landmark Hug é uma Open Skill pública no Digen. Abra para ver o que este fluxo cria.
Custom
1 1 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284864/2026-10-21/sngpvn8h.jpg
# Colossal Animal Landmark Hug Produce **exactly one** shown **image** of a **colossal animal affectionately wrapping around a recognizable landmark**, with the surrounding real environment rendered as a **miniature diorama** — photorealistic fantasy realism, natural daylight, highly detailed fur and stone, tilt-shift scale illusion. Inputs are flexible: an **animal reference**, a **landmark/object reference**, both, or neither (text theme or direct generate). See `references/style-contract.md` for the full visual contract and `references/generation.md` for prompt construction. **Fixed play:** one shown **image** per request. **Never call `generate_video` or any video tool.** 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 an animal and/or landmark**, **describe a theme**, 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 **colossal animal landmark scene** 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 theme, no direct-generate tap, no last success to refine | Direct generate now · Describe my animal + landmark · I'll upload references | | P-brief | Theme too vague (no animal or no landmark) | Example fox + London tower (`fill_input`) · Direct generate default (`send_message`) · I'll upload instead (`send_message`) | | P-refuse | NSFW goal, gore focus, sexualized minor, real-person defamation intent | Family-safe direct generate · Upload a different reference | | P-fail | `generate_image` `success=false` after retry | Regenerate same source · Direct generate again · Upload different references | | P-done | One colossal animal landmark image ready | Stronger embrace pose · Swap the animal · Swap the landmark · 9:16 vertical | ## When to use - User wants a **colossal animal wrapping around a landmark** scene, **with or without** uploads. - User **uploaded an animal and/or landmark photo** (even with no text) or opened this skill from the catalog — **run `generate_image` immediately**; do not stop on **P-empty**. - 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. - Follow-up on **last successful image** from this skill: regenerate, stronger embrace, swap animal/landmark, or size change (still **one** image). **Do not use:** **video** or motion clips; plain retouch with no giant-animal