Step Into the Scene · skill pubblica Open Skill

Step Into the Scene

Step Into the Scene è una Open Skill pubblica su Digen. Aprila per vedere cosa crea questo workflow.

@akjshdk

Custom

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4173183/2026-10-15/ysu92eyh.jpg

# Step Into the Scene

Deliver one **10-second cinematic clip**: the subject **steps through a glowing portal** from a mundane room into a **spectacular destination world** they describe (or a curated default). **Upload path:** identity-preserving hero still (I2I), then `ref2v` motion clip, then ambient BGM mix. **Direct generate:** text-to-image hero still, then the same pipeline—**upload is never required**.

Prompt templates and timed beats live in `references/`. No structured project state.

**Language lock:** This file and all of `references/` are **English only**. Reply in the **user's language**. Every `generate_image`, `generate_video`, and `generate_music` `prompt` is **English**.

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

## User-visible speech (hard)

**Allowed lines only:**

- Need input: one short note that they may **upload a photo**, **describe a destination world**, 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 **portal scene video** 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 final video**, 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`, `generate_video`, `generate_music`, `mix_clips`, 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. Localize `text` and `content` to 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 world brief, no direct-generate tap, no last video to refine | Direct generate now · Describe my world · I'll upload my photo |
| P-brief | Destination too vague (no genre or mood cues) | Example world brief (`fill_input`) · Direct generate default (`send_message`) |
| P-refuse | NSFW goal, sexualized minor, hate target, real-person humiliation | Family-safe direct generate · Upload a different photo |
| P-fail | Generation or mix `success=false` after retry | Regenerate same source · Direct generate again · Video only, skip music |
| P-done | Final **mixed portal video** ready | New destination world · Landscape version · Regenerate music · Direct generate new hero |

## When to use

- User uploads a **photo** and wants to **appear inside another world** (fantasy, sci-fi, historical, underwater, etc.) with a **portal transition** and **10-second cinematic motion**.
- User has **no photo** or taps **direct generate** / **generate without upload**—run **T2I hero still + portal video + music mix** using the default in `references/guidance-buttons.md` unless they already named a different world in the same message.
- User asks to **retry**, change **orientation**, pick a **new destination**, refresh **music only**, or keep the **same photo** with a new environment.
- User wants only a **hero still** (portal keyframe)—deliver the still, then offer full video via **P-done** buttons.

**Do not use:** unrelated static portrait requests with no world/portal intent, multi-minute films (default is **one 10s clip** per request), or identity swap onto another person without their photo.

## Reference files

| File | When |
|---|---|
| `references/hero_still_spec.md` | Before every `generate_image`—