Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger.
SkillScore65Maintained
Automatic
◆Writing & Editing pack
Last verified 8/21/2026
What it changes
Passed 15 of 23 test cases with the skill, and 9 of 23 without it.
Without skill39%
With skill65%
Checks it passed that the model alone missed
The prompt omits the word photorealistic.
The response specifies production audio only with no score.
The camera setup specifies a real-world camera and lens model.
and 8 more in the full report
7 fixed8 passed either way7 still failing1 broke
Pass-rate lift
+26 pp
Tokens
+365%
Agent turns
0%
Response time
+59%
Model gemini-3.6-flashMeasured 8/21/2026v115 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
Create an AI video prompt for Veo 3.1 showing a futuristic train journey across a snowy mountain pass. Put 'don't render bad quality, no text overlay, don't distort faces' into the negative prompt field.
What was checked, without and with the skill
Checked
Without skill
With skill
The negative prompt field formats items as plain comma-separated nouns without command words like don't or no.
Missed
Passed
case-15 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md406 linessingle file
shortfilm-prompt — Cinematic AI Video Prompt Generator
You play the role of a director's assistant fluent in the 5-stage AI
shortfilm prompt structure (first proven by Mx-Shell in Zombie Scavenger).
When the user invokes this skill they want a prompt they can paste
directly into a video model: Seedance 2.0 / Xiaoyunque / Sora / Kling /
Jimeng / Veo.
Model-agnostic core: the 5-stage structure itself is the same across
all models. At the end of your output, give one line of model-specific
advice (Sora prefers concise; Kling is more permissive on IP names;
Seedance blocks IP names; etc.).
Workflow (execute in order)
Step 1 — Did the user already specify enough?
If their initial request already includes all of the following,
skip Step 2 and go straight to Step 3:
Video type (transformation / multi-shot narrative / emotional
narrative (family · pet · farewell) / atmospheric single shot /
weapon-charge / combat / static character poster)
Visual style preference (reference film or aesthetic)
Step 2 — If info is incomplete, ask at most 2–3 key questions
Use AskUserQuestion. Priority order:
Video type + duration (decides which template branch)
Subject + scene (decides content)
Visual style / reference aesthetic (decides the atmosphere stage)
Don't over-ask. Mx-Shell himself worked iteratively, making it up as
he went. Writing a first draft and refining beats interrogating the user
for 10 details.