ai-shortfilm-prompts
๐ Browse the prompt library online โ prompts.aiolaola.com โ view any template/case and copy it with one click, no install.
๐งฉ Or skip straight to the prompt builder โ pick one of 21 genres, fill a few blanks, get the full multi-shot prompt + negative prompt. No Claude Code needed.
๐ ๅ
่ดน้
ๅฅๅญฆไน โ ไป้ถๅญฆไผ AI ็ผ็จ๏ผ180 ่๏ผ๏ผ ไป้ถๆๅปบ AI ๆบ่ฝไฝ๏ผ40 ่๏ผ
๐ Free companion courses in English ยท ๆฅๆฌ่ช ยท Espaรฑol ยท ํ๊ตญ์ด ยท ็น้ซไธญๆ
A Claude Code Skill that turns any idea into a cinematic, model-ready
video prompt โ for Sora ยท Kling ยท Veo ยท Seedance. 21 genre templates,
a 5-stage structure, eval-tested. Distilled from
Zombie Scavenger
by Mx-Shell โ the AI short Hollywood director PJ Ace called
"one of the best short films I've seen in years."
ไธญๆ็ โ
โก Quick start: one-page cheat sheet ยท
failureโfix gallery
๐ฌ The tweet that started it all
"This is one of the best short films I've seen in years.
Very soon, we'll stop calling it 'AI film' and just call it film."
Film name: Zombie Scavenger by MX-Shell.
โ PJ Ace (@PJaccetturo),
May 10, 2026
| 13.4M views | 82K likes | 7.4K reposts | 39K bookmarks | 2.3K replies |
|---|
Stats are from PJ Ace's original tweet (@PJaccetturo, May 10, 2026), as of mid-May 2026.
This repository is the complete workflow behind that film, made
available because Mx-Shell himself published his prompt collection
documents and walked through his entire method on a public Douyin
livestream.
โก The single-line magic prompt (try it tonight)
Copy this into Sora / Seedance / Kling / Veo. Replace {{...}}:
Anamorphic widescreen cinematic. Simulated IMAX film camera +
Panavision C-series lens (35mm focal, f/4 aperture). Handheld
shot โ extremely subtle, breath-like camera float throughout.
{{your scene description}}.
No score. Production audio only.
Why this works: real camera bodies + "breath-like float" anchor
the AI to actual film aesthetics โ not the vague "cinematic feel"
keyword everyone else uses. Full breakdown in
methodology.md.
โ vs โ
โ what the method actually changes
Same idea: a female mech warrior raises an energy shield in a thunderstorm.
โ The naive prompt (what most people write):
Epic cinematic shot of a beautiful female mech warrior activating a
stunning energy shield in the rain. Highly detailed, 4K, photorealistic,
movie-quality, dramatic lighting.
Vague praise โ epic / stunning / 4K / movie-quality โ gives the model
nothing concrete to anchor to. You get generic game-CG output.
โ
With the 5-stage method (excerpt):
Core theme: gritty hard sci-fi mech | rainy dock | battle-damage aesthetic | energy shield | post-apocalyptic live-action
Atmosphere: simulated IMAX film camera + Panavision C-series (35mm, f/4). Low-saturation teal base, film grain.
Camera: handheld โ extremely subtle, breath-like float throughout.
9โ12s: hexagonal energy cells light up unevenly, some flicker as if faulty; rain bends around a 2m dome.
Ending: no dialogue, no light burst โ just rain vaporizing on the shield, a lightning flash across the dock.
Real camera/lens names + physical reactions + battle damage + an empty
ending = visceral realism. Full sample with the 10-item self-check:
examples/02-skill-output-sample.md.
The story
May 2026. A 29-year-old vocational-school graduate from rural Yunnan,
China โ handle Mx-Shell โ used 10 days and ~20,000 RMB of
cloud credits to make a 3-minute AI short called Zombie Scavenger:
an atomic-punk robot wanders into a beachfront villa after a zombie
apocalypse, meets a confused ostrich, and starts dancing
1980s-style breakdance moves while kicking a zombie's head across
the floor.
On the cost: the widely-quoted "3,000 RMB" figure came from Mx-Shell
himself, but on livestream he later revised it to "tens of thousands /
20k+." The real spend was likely well above 3,000 โ still far below a
comparable live-action shoot.
Hollywood director PJ Ace (@PJaccetturo) retweeted the film,
calling it "one of the best short films I've seen in years" and started a
search for the author.
A few weeks later Mx-Shell went on a Douyin livestream and gave
away his entire workflow โ the prompts, the camera language, the
failure modes, the reroll counts.
This repo is the result of digesting 130,000 characters of his
materials into a structured, reusable system.
What's in here
ai-shortfilm-prompts/
โโโ README.md You're here. English entry point.
โโโ README.zh.md Chinese version.
โโโ cheatsheet.md One-page cheat sheet (the whole method at a glance).
โโโ cheatsheet.zh.md Chinese version.
โโโ cases.md Failureโfix gallery: common bad output and the fix.
โโโ cases.zh.md Chinese version.
โโโ methodology.md The 5-stage prompt structure, explained.
โโโ methodology.zh.md Chinese version.
โโโ faq.md Q&A: tools, failures, costs, edge cases.
โโโ faq.zh.md Chinese version.
โโโ credits.md Sources & attribution.
โโโ credits.zh.md Chinese version.
โโโ showcase.md Things people made with the method.
โโโ CONTRIBUTING.md Submission template & rules for new prompts.
โโโ LICENSE MIT (this work)
โโโ NOTICE Attribution + Mx-Shell ARR details (dual-licensing)
โ
โโโ prompts/ Mx-Shell's complete original prompts.
โ Body kept in Chinese (his authorial
โ voice), with English header on each file.
โ โโโ README.md Index of all prompt archives
โ โโโ index.json Machine-readable index of every prompt
โ โโโ zombie-scavenger.md *Zombie Scavenger*
โ โโโ kamen-rider-transformations.md Kamen Rider transformation ร 6 (5 riders + flight)
โ โโโ kaisa-transformation.md LoL Kai'Sa transformation ร 3 versions
โ โโโ pacific-rim-gundam.md Pacific Rim + Gundam mech-drop
โ โโโ cyber-wuxia.md Shaw Brothers + steampunk wuxia template
โ โโโ metal-gear-charge-combat.md Weapon-charge + combat composite
โ
โโโ templates/ IP-stripped generalized templates (EN + .zh.md siblings).
โ Authored by jnMetaCode based on Mx-Shell's structure.
โ โโโ 15s-transformation.md 15-second transformation
โ โโโ multi-shot-narrative.md Multi-shot edited narrative
โ โโโ atmosphere-prefabs.md 8 reusable atmosphere/look prefabs
โ โโโ negative-prompts.md Reusable negative-prompt prefab (per-model)
โ โโโ genre-camera-sop.md Camera-movement SOP for 5 film genres
โ โโโ camera-move-library.md 50 camera moves in 5 technique modules
โ โโโ pet-lifetime-narrative.md Worked example: pet ร family emotional narrative
โ โโโ family-recipe-farewell.md Worked example: a mother's recipe handed down
โ โโโ elderly-cat-companion.md Worked example: grandmother & cat, empty-nest
โ โโโ product-commercial.md Worked example: beat-driven product hero ad
โ โโโ food-asmr.md Worked example: food ASMR / native synced audio
โ โโโ animal-vlog.md Worked example: talking-animal selfie vlog
โ โโโ movie-trailer.md Worked example: escalating teaser trailer
โ โโโ cyberpunk-city.md Worked example: atmospheric neon-city roam
โ โโโ claymation.md Worked example: 12fps stop-motion / claymation
โ โโโ nature-timelapse.md Worked example: landscape timelapse, locked grade
โ โโโ found-footage-horror.md Worked example: CCTV / security-cam dread
โ โโโ anime-to-real.md Worked example: 2D character โ live-action
โ โโโ music-video.md Worked example: beat-synced performance MV
โ โโโ sports-slowmo.md Worked example: high-speed slow-motion sports
โ โโโ fashion-film.md Worked example: editorial fashion film
โ โโโ travel-vlog.md Worked example: travel vlog, sense of place
โ โโโ drone-fpv.md Worked example: FPV/aerial continuous flight
โ โโโ micro-drama.md Worked example: vertical short-drama (hook+cliffhanger)
โ โโโ sci-fi-space.md Worked example: hard sci-fi space / zero-G
โ โโโ car-commercial.md Worked example: automotive commercial
โ โโโ dance.md Worked example: continuous-motion dance film
โ
โโโ assets/ Diagrams + the README hero-demo prompt.
โ โโโ demo-prompt.md Copy-paste 15s prompt the Skill wrote (hero slot)
โ โโโ 5-stage-structure.svg The structure diagram
โ
โโโ skills/shortfilm-prompt/ Claude Code Skill
โ โโโ SKILL.md How Claude should generate prompts (7 hard rules + 10-item checklist)
โ โโโ TESTING.md How to run rigorous skill tests in another Claude window
โ โโโ examples/ 4 test cases (5 files) with expected outputs
โ
โโโ .claude-plugin/ Plugin metadata (plugin.json + marketplace.json)
TL;DR โ The 5-stage prompt structure
Every Mx-Shell video prompt follows the same skeleton. The order matters:
1. Core theme โ 3-6 style tags separated by |
2. Character & scene โ Face / clothing / environment
3. Atmosphere & quality โ Visual base / color tone / style core
4. Camera rules โ Single-shot or multi-shot / angle / breathing
5. Storyboard โ Per-second OR per-shot breakdown
Three counter-intuitive rules
-
Specify real camera + lens models.
Don't write "cinematic feel". Write
"simulated IMAX film camera, Panavision C-series lens, 35mm focal,
f/4 aperture." AI training data binds those exact strings to real
movie aesthetics.
-
Describe imperfections.
"Battle-damaged armor, paint worn off, oil in the joints, minor
facial blemishes preserved." Perfection looks fake. The visceral
realism comes from the flaws.
-
Leave the ending empty.
"No dialogue. No explosion. No blinding light.
Just a figure standing in the smoke, a meteor crossing the sky."
Full methodology in methodology.md.
Install (Claude Code)
Option 1 โ Plugin Marketplace โญ (one-line install)
/plugin marketplace add jnMetaCode/ai-shortfilm-prompts
/plugin install ai-shortfilm-prompts@ai-shortfilm-prompts
Then in Claude Code:
/ai-shortfilm-prompts:shortfilm-prompt Help me write a 15-second prompt for a
robot transformation, green color palette,
energy core in the belt buckle,
post-apocalyptic jungle background
Option 2 โ Try it inside this repo
git clone https://github.com/jnMetaCode/ai-shortfilm-prompts.git
cd ai-shortfilm-prompts
claude --plugin-dir . # then: /ai-shortfilm-prompts:shortfilm-prompt
Option 3 โ Make it available globally (manual copy)
mkdir -p ~/.claude/skills
cp -r ai-shortfilm-prompts/skills/shortfilm-prompt \
~/.claude/skills/
Option 4 โ As a submodule in your own project
git submodule add https://github.com/jnMetaCode/ai-shortfilm-prompts.git \
vendor/ai-shortfilm-prompts
claude --plugin-dir vendor/ai-shortfilm-prompts # loads the plugin + skill
The Skill walks through the 5-stage structure, runs a 10-item self-check,
and warns you about IP names that may be blocked by Seedance 2.0.
Compatible video models
The 5-stage structure is model-agnostic. Here's how the major 2026
engines compare โ single-shot ceiling, negative-prompt support, IP filter,
preferred prompt language, and the one gotcha that trips people up:
| Model | Max single shot | Negative prompt | IP filter | Lang | Notes / gotcha |
|---|
| Seedance 2.0 (Doubao / Jimeng / Xiaoyunque, ByteDance) โ Mx-Shell's primary engine | ~10โ15s โ but the Doubao app is locked to 5s/10s preset buttons; the full 4โ15s range only on Jimeng/Dreamina web + VolcEngine console | Partial โ no reliable dedicated field in the consumer app; negate by describing what you do want | Strict โ domestic platforms aggressively reject named celebrities + branded IP | Either (ZH native, EN works) | Duration depends entirely on the front-end. Don't promise 15s if the user is on the Doubao app. Native synced audio-video is its standout strength. |
| Veo 3 / 3.1 (Google) | 8s per clip (4/6/8s); Extend adds 7s hops up to ~148s, but quality degrades after 4โ5 extensions | Yes โ dedicated field. List unwanted elements as plain nouns (extra limbs, glitch morphs); no no/don't command phrasing | Strict โ rejects public figures, brands, voice/likeness; scans prompt and frames | EN | The negative field wants descriptive phrases, not commands โ no rain style instructions can backfire. Best-in-class native audio + realism. |
| Kling 2.x / 3.0 (Kuaishou) | 2.5: 5โ10s (Pro ~12s); 3.0: up to ~15s single-prompt multi-shot | Yes โ dedicated field. Use for stability artifacts (sliding feet, extra fingers, morphing), not generic "quality" words | Strict โ a pre-gen banned-word filter rejects the whole prompt on one match; hypersensitive | Either (ZH native, EN strong; 3.0 multilingual dialogue) | The banned-word filter is notoriously over-sensitive โ a benign body/contact word can block a clean prompt. Sanitize wording first. Excellent action/motion realism. |
| Hailuo / MiniMax (02 / 2.3) | ~6โ10s โ 1080p caps ~6s, 768p extends ~10s |
Durations and negative-prompt mechanics for Veo 3.1, Runway Gen-4, Kling,
Wan, and Sora are consistent across multiple 2026 vendor/help-doc sources;
Seedance 2.0 and Hailuo figures lean on third-party guides (treat ~ as
approximate). "Veo ~148s", "Sora/Pika ~25s" come from extension/keyframe
features, not plain single-shot generation. IP-filter "strictness" labels
are qualitative.
Tool names link to their sign-up pages; Xiaoyunque / Jimeng / Kling are invite links (both sides get free credits).
Sister projects (by the same author)
This is the video-prompt sibling of the AI-coding ecosystem maintained
by @jnMetaCode:
All projects share the same SKILL.md format. The video skill stacks
freely with any of them.
Contributing
The roadmap is to collect more AI-shortfilm creators' methods, structured the
same way. New prompts, templates, fixes, and translations are welcome โ see
CONTRIBUTING.md for the submission template and rules
(public source required, credit the original creator).
Made something with the method? It goes on the showcase.
Follow ยท ๅ
ณๆณจไฝ่
ๅพฎไฟกๅ
ฌไผๅทใAI ไธๆญข่ฏญใ ยท ๆ้ณ @AIไธๆญข่ฏญ๏ผAIBZY๏ผ ยท X @jnMetaCode ยท aiOlaOla โ ๅ
่ดนๅญฆ AI ็ผ็จ
๐ Live prompt library โ prompts.aiolaola.com
License
MIT License for everything authored by jnMetaCode
(methodology, FAQ, templates, Skill, metadata). Free for any use
including commercial โ just keep the copyright notice.
Mx-Shell's original prompts and document excerpts โ sourced from his
fan-group documents and public Douyin livestream that he himself
distributed โ remain ยฉ Mx-Shell, all rights reserved. Archived here
for educational reference; commercial use requires contacting Mx-Shell
directly. Full dual-licensing details: NOTICE ยท
attribution: credits.md.
A line worth remembering
"For creation, the equipment is not what matters.
The idea is what matters."
โ Mx-Shell, May 12, 2026 livestream
