Kung Fu Punch · skill pubblica Open Skill
Kung Fu Punch
Kung Fu Punch è una Open Skill pubblica su Digen. Aprila per vedere cosa crea questo workflow.
Custom
4 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284864/2026-10-20/twr2xews.jpg
# Kung Fu Punch Deliver one **cinematic full-body kung fu clip** from a single uploaded reference photo. The subject **drops the raised leg into a stable fighting stance** and **unleashes rapid alternating left-right punches** with **sharp snap-back motion**, **small mist bursts**, and a **low dynamic push-in camera**. The **whole body stays visible from head to ground** in every frame. **Identity lock:** same person, same face, same hairstyle, same outfit as the uploaded photo. No identity drift, no outfit changes, no cropped or partial-body framing. **Upload path (default):** the uploaded photo is the identity and outfit anchor for **`i2v`** generation. **Direct generate path:** only when the user explicitly asks for a text-to-video clip without a photo; then generate a full-body cinematic martial arts keyframe first and animate it. Upload is **required** for the standard image-to-video flow. Prompt templates and motion 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` 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 should **upload a full-body photo** (or ask for a text-to-video clip if they have no photo)—then pause **P-empty**. - 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 **kung fu punch clip** 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**. If the user already uploaded a photo and asked to generate, **do not** re-ask—read the prompt references, apply defaults, and generate. ## 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`, `video_agent`, 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 brief, no direct-generate tap, no last clip to refine | Upload full-body photo · Generate without a photo · Describe the fighter | | P-refuse | Real-person face used without consent, gore, hate, NSFW, real celebrity likeness | Upload a different photo · Generate a fictional fighter | | P-fail | Generation or `video_agent` `success=false` after retry | Try again · Regenerate from last still · Softer motion, same punch beats | | P-done | Final kung fu punch clip ready | Upload another photo · Faster punches · Wider full-body framing · Text-to-video version | ## When to use - User wants **Kung Fu Punch Animation** / **kung fu video from photo** / **animate my photo into martial arts** as a **cinematic full-body clip**. - User uploads a **full-body reference photo** and wants the **fighting stance + rapid alternating punches + mist bursts + low push-in camera** while **keeping identity and outfit**. - User has **no photo** and explicitly asks for a **text-to-video** martial arts clip—generate a full-body cinematic keyframe first, then animate it. - User asks to **retry**, **regenerate from the last still**, **speed u