Halloween 3D Ghost Video · مهارة Open Skill عامة
Halloween 3D Ghost Video
Halloween 3D Ghost Video هي Open Skill عامة على Digen. افتحها لتعرف ماذا ينشئ هذا التدفق.
Custom
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/m7haeymm.gif
# Halloween 3D Ghost Video Deliver one **short Halloween ghost video** in **stylized 3D cel-shaded anime** look: translucent floating figure, soft glowing edges, atmospheric spooky-playful mood, gentle drift motion and a slow camera push-in. **Reference photo path:** transform the subject into the ghost hero still, then animate from that still. **Direct generate:** text-to-image ghost still, then the same video step — **upload is never required**. Visual rules and prompt templates live in `references/`. No project state. **Language lock:** This file and all of `references/` are **English only**. Reply in the **user's language**. Every `generate_image` and `generate_video` `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 reference photo**, **describe the ghost**, 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 **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 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`, 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 brief, no direct-generate tap, no last video to refine | Direct generate now · Describe my ghost · I'll upload a photo | | P-brief | Text too vague (no subject or scene cues) | Example ghost scene (`fill_input`) · Direct generate default (`send_message`) | | P-refuse | NSFW goal, sexualized minor, gore focus, hate target | Family-safe direct generate · Upload a different photo | | P-fail | `generate_image` or `generate_video` `success=false` after retry | Regenerate same source · Direct generate again · Upload a different photo | | P-done | Ghost **video** ready | Longer clip · Landscape version · More playful motion · Direct generate new ghost | ## When to use - User uploads a **reference photo** (person, pet, object, or scene) and wants a **Halloween 3D ghost animation** inspired by it. - User has **no photo** or taps **direct generate** / **generate without upload** — run **text-to-image still + reference video** immediately using the default in `references/guidance-buttons.md` unless they already gave a different brief in the same message. - User asks to **retry**, change **duration** or **orientation**, or tweak motion while keeping the **same ghost aesthetic**. - User wants only a **new still** (ghost keyframe) — deliver the still, then offer video via **P-done** buttons. **Do not use:** unrelated non-Halloween genres, realistic horror gore, or long multi-scene films (single clip only). ## Reference files | File | When | |---|---| | `references/ghost_visual_spec.md` | Before every `generate_image` — style lock + I2I/T2I templates | | `references/video_prompt.md` | Before every `generate_video` — motion, camera, Halloween mood | | `references/generation.md` | Before every generation call — channels, sizing, re