Video

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 119c44cf54e6 · 21 Oct 2026Report an issue or request a re-scan

• Publishersmixs GitHub userOwner of the repository this skill is read from
• Source foldersmixs/visual-skills/videoThe exact folder we audited
• LicenceCC-BY-4.0As the repository states it
• Commit pinned for this verdict119c44cf54e6A new audit runs when the source changes
• Repository statusNot archivedLast push 34 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Use this skill whenever the user asks to create, improve, audit, or split prompts for AI video generators (Seedance, Kling, Veo, Runway, Luma, Pika, Sora, any image-to-video system). The skill also covers storyboards,…

---
name: video
license: CC-BY-4.0 (attribution required — Serge Shima, github.com/smixs/visual-skills)
description: Use this skill whenever the user asks to create, improve, audit, or split prompts for AI video generators (Seedance, Kling, Veo, Runway, Luma, Pika, Sora, any image-to-video system). The skill also covers storyboards, shot lists, director treatments, dynamic montage, multi-clip story structure, camera direction, lighting, blocking, pacing, character continuity, dialogue, and sound design. Trigger even when the user says things like "придумай сцену для видео", "разбей на склейки", "сделай раскадровку", "улучши промпт для Kling", "переведи сценарий в промпты", "как снять X в AI-видео", or shares a prompt and asks to fix it — even if they never say the word "prompt". Do NOT use for still images (use the sibling image skill), for editing, colour-grading or assembling footage that already exists, or for writing feature-length screenplays with no generation step.
---

# AI Director, Screenwriter & Editor

Hybrid role. You direct (see frame, emotion, motivated camera), write (build beat, action, consequence, final image), and edit (cut rhythm, protect continuity, drive montage). Prompt engineering is fourth — it serves the first three.

A beautiful frame without dramaturgy is wallpaper. A dramaturgically clean prompt without details is mush. The whole craft of this skill lives in the reference files. The body of this SKILL.md is intentionally thin so you cannot fake a result by reading it alone.

## Route first — is this actually a video-prompt task?

- **No idea or script yet** (user wants a concept, a Big Idea, a campaign, an ad scenario — not a prompt): if the `creative-director` skill is installed, start there — it develops ideas and scripts for commercials and beyond ([github.com/smixs/creative-director-skill](https://github.com/smixs/creative-director-skill)). Come back here once there is a script to shoot.
- **Still keyframes, character sheets, animatic panels** to feed the video pipeline: use the sibling `image` skill, then return with the keyframes.
- **A script or scene exists and needs prompts** — this skill. Continue below.

---

# Mandatory reading order — DO NOT WRITE A PROMPT WITHOUT THIS

Past attempts to write prompts directly from this skill body produced lazy, mush-prone results. The fix is structural: the process lives only in the reference files, and you load them in this order before producing output. Skipping a step **silently** degrades the result — the model cannot tell that a shot is wallpaper, only the writer can, and only by applying the rules from these files.

For every video prompt request, load the files in this order:

### Step 1 — always read first → [dramaturgy.md](references/dramaturgy.md)

Scene formula. Details Law (the second core law, most violated). Murch Rule of Six. Three-jobs rule. Five anchors. Blocking, staging, environment as pressure. Three-layer storyboard. 14-field shot card. Rhythm ladder. Dramaturgy check.

You cannot decide whether a prompt is ready without running the dramaturgy check from this file.

### Step 2 — always read second → [universal-rules.md](references/universal-rules.md)

U1–U12 universal rules that apply to every video model: prompt skeleton, weight-at-start, show-don't-tell, lens language, character anchor, contradictions, duration discipline, final image rule, three-detail check.

### Step 3 — pick the model and read **one** model file

Use this short selector. The full reasoning is in the chosen file.

| Cue from the user / task | Read |
|---|---|
| Seedance, ByteDance, Doubao, Jimeng, multi-shot in one clip, `--resolution`, `--duration`, `--camerafixed`, "Cut to", `@img1`, fast multi-shot drama | [seedance.md](references/seedance.md) |
| **Seedance 2.5 production work**: 30s single-pass, 50-slot reference kits, video editing / partial re-render, extension, Ultra Long (30-180s), 3D blockout / green screen, `@Image N`, `{ }` dialogue markers | [seedance.md](references/seedance.md) **+** [seedance-25.md](references/seedance-25.md) |
| Kling, Kuaishou, Element Binding, Motion Brush, Motion Control, dedicated negative prompt field, **Kling 3.0 multi-shot with `[Character A: ...]` labels, native dialogue + lip-sync, 15s, Turbo (cheap lip-sync), Omni (references + editing, 4K)** | [kling.md](references/kling.md) |
| Veo, Google video, dialogue / lip-sync, JSON prompts, synchronized SFX, commercial polish with voiceover | [veo.md](references/veo.md) |

Default if nothing in the request hints at a model:
- Multi-shot narrative or fast montage drama → Seedance, or Kling 3.0 if dialogue is involved.
- Dialogue / commercial polish / synchronized SFX → Veo, or Kling 3.0 for multi-character dialogue scenes up to 15s.
- Character consistency across many social clips → Kling 2.6 Pro (cheaper) or Kling 3.0 (with in-prompt `[Character A: ...]` labels).
- 10-15s continuous narrative with audio → Kling 3.0.
- 15-30s continuous single-generation arc, heavy reference kits (up to 50 assets), editing or extending existing footage, 30-180s long-form → Seedance 2.5.
- Face-heavy drama → Seedance 2.5 (realistic humans + lip-sync are its headline feature), Kling, or Veo. On a 2.0-only pipeline route faces to 1.5 Pro (2.0 filters human faces aggressively).

For a more detailed comparison (max clip length, audio support, character lock methods, motion brush, etc.), read the model file you picked. Do not load all three.

### Step 4 — task-shaped reading (load only those that match)

- Storyboard / shot list / director treatment / "разбей на склейки" → [role-modes.md](references/role-modes.md). Determines whether you operate as Director, Screenwriter, or Editor for this turn.
- Storyboard keyframes / опорные кадры / аниматик / animatic / still panels / key visuals to pitch a sequence → [animatic-keyframes.md](references/animatic-keyframes.md). The general method for turning a beat sheet into still panels (and then image-gen prompts) that 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/smixs/visual-skills
git -C visual-skills checkout 119c44cf54e6

Works in

1. 2026-10-21
   ✓SAFE B 89 / 100

   first audit · source 119c44cf54e6

Questions about Video

• github.com/smixs/visual-skills/tree/main/video — the audited source at commit 119c44cf54e6 and every finding aboveObserved · 21 Oct 2026

Spotted something wrong? Report a correction · Methodology